diff --git a/docs/reference-matrix.md b/docs/reference-matrix.md
index 4be14b07c..c1c81052e 100644
--- a/docs/reference-matrix.md
+++ b/docs/reference-matrix.md
@@ -248,6 +248,7 @@ SSD/OS systems columns.
| JiusiServe/vllm-evolve @ 43cc82c | search | scheduling-algorithm evolution, search policy | `optimization-search-policy`, `dense-performance-evidence`, `inference-benchmark-design` |
| [OpenBMB/JustGoal repo + paired paper](https://github.com/OpenBMB/JustGoal/tree/f052fc0b28fc7f10b2ef1ae7aa4682aabbbe868d) @ `f052fc0b28fc7f10b2ef1ae7aa4682aabbbe868d` (repository Apache-2.0 default; NOTICE BSD exceptions; paper license UNKNOWN) | evaluation | Bounded direct inspection, 2026-11-02: complete 21-page paper/appendices and selected DSA wrapper/CUDA workspace/stream contracts; [exact readset and exclusions](../src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/justgoal-source.json). Source-only methodology; author-reported comparisons, released failures versus repaired timing and official/stricter oracle differences retained | [inference-benchmark-design reference](../src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/justgoal-evaluation-contracts.md); candidate/not_run, efficacy not_evaluated; no new implementation/backend coverage or full campaign runner |
| [AutoTuneBench repo + paper v1](https://github.com/li-ch/autotunebench/tree/64cc8d7ca5d0ee40c4e2189b2c2c8dfb1a2a7c2f) @ `64cc8d7ca5d0ee40c4e2189b2c2c8dfb1a2a7c2f`; [arXiv:2609.18123v1](https://arxiv.org/abs/2609.18123v1) (selected repository code/data MIT; paper CC BY 4.0) | evaluation | Bounded source inspection, 2026-11-02: treatment delivery, arm-validity precedence, exported protocol/check/record gaps, weak-denominator and anomaly counterexamples; complete 15-page paper, 6 figures, 7 tables and [exact selected readset/rights](../src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/autotunebench-source.json) | [inference-benchmark-design reference](../src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/autotunebench-trial-validity.md); source-derived candidate/not_run, efficacy not_evaluated; invalid-arm/source-median conflicts retained, no new controller or measured implementation coverage |
+| [Xe-Forge repo + paper v1](https://github.com/IntelLabs/Xe-Forge/tree/6cd3ee98dfe32746b345a6abe521fa4cb9bdc187) @ `6cd3ee98dfe32746b345a6abe521fa4cb9bdc187`; [arXiv:2605.26118v1](https://arxiv.org/html/2605.26118v1) (repository Apache-2.0; paper CC BY 4.0) | evaluation | Bounded source inspection, 2026-11-02: 18-file trial identity/origin, external outcome, selection/finalization/reporting and baseline-oracle readset; complete paper HTML/appendix/tables/algorithm/listing/captions, unused graphic values unverified; [exact hashes, rights and exclusions](../src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/xeforge-source.json) | [`inference-benchmark-design` reference](../src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/xeforge-trial-evidence.md); candidate/not_run, efficacy not_evaluated; two measured meanings, named-verdict update limits and manual versus measured-only defaults retained; no runtime integration or whole-model/backend promotion |
| Dong1017/OmniRSI @ `codex/skill-eval-bootstrap` (82218b4) | evaluation | skill_distill / skill_eval harness, no_skill/human/distilled contract, Tier A pilot | `npu-skill-factory` (evaluation contract) |
| InferMatrixLab/InferRSI PR #9 @ 4ad551a9 | reference | `skill_library/` layout + knowledge records | `npu-skill-factory` (bundle layout) |
| RRSI — arXiv 2609.24972v3 | search; mined via reviewed Pack F | bounded harness proposals; calibrated noise/cost/novelty gates; grouped-ablation limits, replacing the earlier generic constraint summary | `optimization-search-policy`; [exact ledger](../src/inferrsi/data/skill_library/methods/optimization-search-policy/references/papers-20261015/references/source-notes.md#f1--rrsi) |
diff --git a/docs/searchspace-matrix.md b/docs/searchspace-matrix.md
index aad404af3..41774f067 100644
--- a/docs/searchspace-matrix.md
+++ b/docs/searchspace-matrix.md
@@ -600,6 +600,12 @@ NOASSERTION and InferRSI's repository license.
| --- | --- | --- | --- |
| Accelerator (methodology only) | Verify: trace treatment to the eligible consumer, apply frozen arm validity before interpreting a null, and separate declared protocol, reached checks and persisted gate evidence | [inference-benchmark-design reference](../src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/autotunebench-trial-validity.md) and [source record](../src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/autotunebench-source.json); AutoTuneBench repo + paired paper | Source-derived candidate / empirical not_run; paper measurements remain author-reported, efficacy not_evaluated. Contextual source bars are not InferRSI defaults. No new implementation, measured hardware/resource coverage, backend compatibility, or RAM/Storage/Network/OS coverage. |
+## Xe-Forge trial-evidence guidance (source-derived)
+
+| Resource | Stage and mechanism | Source and owner | Evidence boundary |
+| --- | --- | --- | --- |
+| Accelerator (methodology only) | Verify: bind saved candidate and comparator identities, distinguish tool origin from resolved performance, inspect host gate/ratio persistence, and follow manual versus measured-only delivery and baseline-oracle boundaries | [inference-benchmark-design reference](../src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/xeforge-trial-evidence.md) and [source record](../src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/xeforge-source.json); Xe-Forge repo + paired paper | Source-derived candidate / empirical not_run; paper/README results remain author-reported, efficacy not_evaluated. No new implementation, measured hardware/resource coverage, backend compatibility, whole-model/service promotion or RAM/Storage/Network/OS coverage; draft extensions remain proposals. |
+
## TorchNPU framework source procedures
| Resource | Stage / mechanism | Canonical owner | Evidence boundary |
diff --git a/docs/skill-coverage.md b/docs/skill-coverage.md
index 50c3f1b6c..af0f281df 100644
--- a/docs/skill-coverage.md
+++ b/docs/skill-coverage.md
@@ -4,7 +4,7 @@ Generated from the registry, the skill sidecars and the two maintained
matrices. **Do not edit by hand**; regenerate after any registry, skill,
matrix or frozen-plan change.
-- Input digest: `sha256:7640b171256091efd1514a33d5e434eef3feaed238fc92fe3eeba02fee94e9ff`
+- Input digest: `sha256:0dcdead4b319f996fcf0f1a3125de5f1ae4717ba6c8aa34cb3f1fa6dbf5494f3`
- Regenerate: `python tools/build_skill_coverage.py`
- Verify without writing: `python tools/build_skill_coverage.py --check`
@@ -131,7 +131,7 @@ optimization is fully covered or that any procedure has measured benefit.
| [choose-parallel-training-plan](../src/inferrsi/data/skill_library/methods/choose-parallel-training-plan/SKILL.md) | common | Compare stage, device-mesh and operator-sharding candidates for static distributed training while accounting for ... | Comparing stage, device-mesh and operator-sharding candidates for static distributed ... | failure_modes, input_contract, produced_artifact, refusal_point
3 advice | 1 Accelerator · Diagnose / Configure / Optimize / Verify
4 Network · Diagnose / Configure / Optimize / Verify | 1 · Systems sources (Alpa — [2201.12023v3](https://arxiv.org/abs/2201.12023v3)) | candidate · not_run · 1 readset(s) | no-eval |
| [dense-performance-evidence](../src/inferrsi/data/skill_library/methods/dense-performance-evidence/SKILL.md) | common | Taxonomy of performance evidence an optimization agent needs, ordered by collection cost and diagnostic power. Maps ... | Deciding which performance evidence to collect next and which claim each evidence level ... | failure_modes, input_contract, produced_artifact, refusal_point
4 advice | 1 Accelerator · Observe / Profile / Verify
2 RAM/Host · Verify
4 Network · Verify | 1 · Systems sources (NVIDIA/TensorRT-LLM @ f33e0e5fd)
2 · Methodology and corpus references (JiusiServe/vllm-evolve @ 43cc82c)
2 · Methodology and corpus references (microsoft/SkillOpt @ 343db22) | candidate · not_run · 0 readset(s) | — |
| [evaluate-elastic-serving-placement](../src/inferrsi/data/skill_library/methods/evaluate-elastic-serving-placement/SKILL.md) | common | Compare migrating an LLM request between model replicas with changing its sequence-parallel execution group, including ... | Comparing migration of a running LLM request between compatible model replicas with ... | failure_modes, input_contract, produced_artifact, refusal_point
3 advice | 1 Accelerator · Diagnose / Configure / Optimize / Verify
2 RAM/Host · Diagnose / Configure / Optimize / Verify
4 Network · Diagnose / Configure / Optimize / Verify | 1 · Systems sources (Llumnix — [2406.03243v1](https://arxiv.org/abs/2406.03243v1)) | candidate · not_run · 1 readset(s) | no-eval |
-| [inference-benchmark-design](../src/inferrsi/data/skill_library/methods/inference-benchmark-design/SKILL.md) | common | Select task quality gates, reference parity checks and performance workloads for text, agentic coding, work agents ... | Selecting task quality gates, reference parity checks and performance workloads for text ... | failure_modes, input_contract, produced_artifact, refusal_point
5 advice | N/A: SKILL.md §§ Select the task and its evaluation contract, Statistical requirements, Shared-machine measurement discipline, and Search integrity and final-state verification design comparable evaluation; hardware identity and allocation isolation are comparison controls, not a hardware-resource mechanism. | 2 · Methodology and corpus references (JiusiServe/vllm-evolve @ 43cc82c)
Task-specific benchmark selection (issue #60) ([Issue #60 report](https://github.com/InferMatrixLab/InferRSI/issues/6 ...)
Task-specific benchmark selection (issue #60) ([NVIDIA/NeMo-Speech.cpp @ 20999cc9](https://github.com/NVIDIA/NeMo-Spe ...) | candidate · not_run · 7 readset(s) | — |
+| [inference-benchmark-design](../src/inferrsi/data/skill_library/methods/inference-benchmark-design/SKILL.md) | common | Select task quality gates, reference parity checks and performance workloads for text, agentic coding, work agents ... | Selecting task quality gates, reference parity checks and performance workloads for text ... | failure_modes, input_contract, produced_artifact, refusal_point
6 advice | N/A: SKILL.md §§ Select the task and its evaluation contract, Statistical requirements, Shared-machine measurement discipline, and Search integrity and final-state verification design comparable evaluation; hardware identity and allocation isolation are comparison controls, not a hardware-resource mechanism. | 2 · Methodology and corpus references (JiusiServe/vllm-evolve @ 43cc82c)
2 · Methodology and corpus references ([Xe-Forge repo + paper v1](https://github.com/IntelLabs/Xe-Forge/tree/ ...)
Task-specific benchmark selection (issue #60) ([Issue #60 report](https://github.com/InferMatrixLab/InferRSI/issues/6 ...)
Task-specific benchmark selection (issue #60) ([NVIDIA/NeMo-Speech.cpp @ 20999cc9](https://github.com/NVIDIA/NeMo-Spe ...) | candidate · not_run · 9 readset(s) | — |
| [inference-optimization-casebook](../src/inferrsi/data/skill_library/methods/inference-optimization-casebook/SKILL.md) | common | How to structure and use a casebook of past optimization decisions as a decision-support tool. Extracts the casebook ... | Structuring and querying a casebook of past optimization decisions as decision support ... | failure_modes, input_contract, produced_artifact, refusal_point
4 advice | 1 Accelerator · Optimize | 1 · Systems sources (NVIDIA/TensorRT-LLM @ f33e0e5fd) | candidate · not_run · 0 readset(s) | no-eval |
| [kernel-writing-guide](../src/inferrsi/data/skill_library/methods/kernel-writing-guide/SKILL.md) | common | Decision guide for writing custom inference kernels: when to write one, which framework to choose (Triton, CuTe DSL ... | Deciding whether to write a custom inference kernel, routing a kernel pattern to Triton ... | failure_modes, input_contract, produced_artifact, refusal_point
6 advice | 1 Accelerator · Optimize / Diagnose / Configure / Verify | 1 · Systems sources (Dao-AILab/causal-conv1d @ `cd81f0413cad2fc1e6f17e785ac39f59aae690cd` ...)
1 · Systems sources (NVIDIA/TensorRT-LLM @ f33e0e5fd)
1 · Systems sources (huggingface/transformers @ `0dad7b822255a0ae261ec45ae937371e859ffd1a` ...)
1 · Systems sources (mindspore-ai/akg @ `5aa15f3fe4d856eb60cd3b27447e04f5f1fb4dff` ...)
1 · Systems sources (sgl-project/sglang @ `16176278d0180f1a1a578e53e6eef432577876c2` ...)
1 · Systems sources (vllm-project/vllm @ `537a79f0fc5ba564d2bef43d54915b2f80f9f77d` (root ...) | candidate · not_run · 7 readset(s) | no-eval |
| [optimization-search-policy](../src/inferrsi/data/skill_library/methods/optimization-search-policy/SKILL.md) | common | Policy for how an optimization agent should select, order, and stop optimization experiments. Covers candidate ... | Selecting, ordering and stopping optimization experiments: candidate generation ... | failure_modes, input_contract, produced_artifact, refusal_point
4 advice | 1 Accelerator · Optimize | 2 · Methodology and corpus references (JiusiServe/vllm-evolve @ 43cc82c)
2 · Methodology and corpus references (RRSI — arXiv 2609.24972v3)
2 · Methodology and corpus references (arXiv 2608.01867 (CRISP))
2 · Methodology and corpus references (microsoft/SkillOpt @ 343db22) | candidate · not_run · 9 readset(s) | no-eval |
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/README.md b/src/inferrsi/data/repo_packs/inferrsi/knowledge/README.md
index 86ee95d7e..2b3fc4aa0 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/README.md
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/README.md
@@ -15,7 +15,7 @@ These are knowledge abstracts (`--kind knowledge`), with namespaced package
IDs distinct from explicitly selected `checkout_ref` skills. Ascend/CUDA
procedures use their corresponding backend; shared methods use `common`.
-Source snapshot: [7aa3344bf84c42467f43b3a927e1c7d13642bd55](https://github.com/InferMatrixLab/InferRSI/tree/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library).
+Source snapshot: [bb4720992ac2a515adc09b645e1e3cfda47e9d69](https://github.com/InferMatrixLab/InferRSI/tree/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library).
```bash
inferrsi knowledge search 'profiling' --repo-type inferrsi --limit 50
@@ -29,7 +29,7 @@ contain the current input paths and bytes (Git checkout filters are respected).
```bash
python tools/build_skill_index.py --source-revision
-python tools/build_skill_index.py --source-revision 7aa3344bf84c42467f43b3a927e1c7d13642bd55 --check
+python tools/build_skill_index.py --source-revision bb4720992ac2a515adc09b645e1e3cfda47e9d69 --check
```
`--check` detects missing, stale and unexpected generated records without writing.
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-aclgraph-capture-replay.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-aclgraph-capture-replay.json
index d628bdadd..da231b6c2 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-aclgraph-capture-replay.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-aclgraph-capture-replay.json
@@ -21,8 +21,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/ascend-aclgraph-capture-replay/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/hardware/ascend/ascend-aclgraph-capture-replay/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/hardware/ascend/ascend-aclgraph-capture-replay/SKILL.md",
"src/inferrsi/data/skill_library/hardware/ascend/ascend-aclgraph-capture-replay/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-device-health.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-device-health.json
index f4b372d19..23fd78e62 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-device-health.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-device-health.json
@@ -23,8 +23,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/ascend-device-health/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/hardware/ascend/ascend-device-health/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/hardware/ascend/ascend-device-health/SKILL.md",
"src/inferrsi/data/skill_library/hardware/ascend/ascend-device-health/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-distributed-parallel.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-distributed-parallel.json
index 4b940539c..478185b48 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-distributed-parallel.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-distributed-parallel.json
@@ -27,8 +27,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/ascend-distributed-parallel/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/hardware/ascend/ascend-distributed-parallel/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/hardware/ascend/ascend-distributed-parallel/SKILL.md",
"src/inferrsi/data/skill_library/hardware/ascend/ascend-distributed-parallel/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-graph-mode.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-graph-mode.json
index 5c1c8590b..573f294ab 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-graph-mode.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-graph-mode.json
@@ -26,8 +26,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/ascend-graph-mode/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/hardware/ascend/ascend-graph-mode/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/hardware/ascend/ascend-graph-mode/SKILL.md",
"src/inferrsi/data/skill_library/hardware/ascend/ascend-graph-mode/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-model-adaptation.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-model-adaptation.json
index 971e9813a..310dad6b1 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-model-adaptation.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-model-adaptation.json
@@ -22,8 +22,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/ascend-model-adaptation/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/hardware/ascend/ascend-model-adaptation/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/hardware/ascend/ascend-model-adaptation/SKILL.md",
"src/inferrsi/data/skill_library/hardware/ascend/ascend-model-adaptation/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-operator-profiling.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-operator-profiling.json
index e8d595cbc..b9cc513fd 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-operator-profiling.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-operator-profiling.json
@@ -23,8 +23,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/ascend-operator-profiling/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/hardware/ascend/ascend-operator-profiling/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/hardware/ascend/ascend-operator-profiling/SKILL.md",
"src/inferrsi/data/skill_library/hardware/ascend/ascend-operator-profiling/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-operator-tuning.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-operator-tuning.json
index 64816a247..7f0f121a6 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-operator-tuning.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-operator-tuning.json
@@ -24,8 +24,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/ascend-operator-tuning/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/hardware/ascend/ascend-operator-tuning/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/hardware/ascend/ascend-operator-tuning/SKILL.md",
"src/inferrsi/data/skill_library/hardware/ascend/ascend-operator-tuning/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-optimization-casebook.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-optimization-casebook.json
index 7521c9f69..fedbf917e 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-optimization-casebook.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-optimization-casebook.json
@@ -22,8 +22,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/ascend-optimization-casebook/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/hardware/ascend/ascend-optimization-casebook/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/hardware/ascend/ascend-optimization-casebook/SKILL.md",
"src/inferrsi/data/skill_library/hardware/ascend/ascend-optimization-casebook/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-performance-analysis.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-performance-analysis.json
index 2a4a0ace2..49df7496b 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-performance-analysis.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-performance-analysis.json
@@ -22,8 +22,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/ascend-performance-analysis/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/hardware/ascend/ascend-performance-analysis/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/hardware/ascend/ascend-performance-analysis/SKILL.md",
"src/inferrsi/data/skill_library/hardware/ascend/ascend-performance-analysis/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-video-diffusion-optimization.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-video-diffusion-optimization.json
index a2d677d4d..bd6a15e90 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-video-diffusion-optimization.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-video-diffusion-optimization.json
@@ -26,8 +26,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/ascend-video-diffusion-optimization/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/hardware/ascend/ascend-video-diffusion-optimization/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/hardware/ascend/ascend-video-diffusion-optimization/SKILL.md",
"src/inferrsi/data/skill_library/hardware/ascend/ascend-video-diffusion-optimization/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascendc-tiling-design.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascendc-tiling-design.json
index ea618b662..5a7f432ef 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascendc-tiling-design.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascendc-tiling-design.json
@@ -24,8 +24,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/ascendc-tiling-design/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/hardware/ascend/ascendc-tiling-design/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/hardware/ascend/ascendc-tiling-design/SKILL.md",
"src/inferrsi/data/skill_library/hardware/ascend/ascendc-tiling-design/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/cann-attribution-overlap.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/cann-attribution-overlap.json
index ca740b5b7..ba3f62e98 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/cann-attribution-overlap.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/cann-attribution-overlap.json
@@ -24,8 +24,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/cann-attribution-overlap/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/hardware/ascend/cann-attribution-overlap/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/hardware/ascend/cann-attribution-overlap/SKILL.md",
"src/inferrsi/data/skill_library/hardware/ascend/cann-attribution-overlap/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/torch-npu.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/torch-npu.json
index 7c1cde5ed..2663993f5 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/torch-npu.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/torch-npu.json
@@ -20,8 +20,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/frameworks/torch-npu/torch-npu/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/frameworks/torch-npu/torch-npu/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/frameworks/torch-npu/torch-npu/SKILL.md",
"src/inferrsi/data/skill_library/frameworks/torch-npu/torch-npu/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/torchnpu-device-memory-lifecycle.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/torchnpu-device-memory-lifecycle.json
index d6676b490..e47f82d33 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/torchnpu-device-memory-lifecycle.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/torchnpu-device-memory-lifecycle.json
@@ -22,8 +22,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/torchnpu-device-memory-lifecycle/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/hardware/ascend/torchnpu-device-memory-lifecycle/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/hardware/ascend/torchnpu-device-memory-lifecycle/SKILL.md",
"src/inferrsi/data/skill_library/hardware/ascend/torchnpu-device-memory-lifecycle/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/torchnpu-pinned-host-memory-lifecycle.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/torchnpu-pinned-host-memory-lifecycle.json
index d6ea1871c..a29cea9e9 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/torchnpu-pinned-host-memory-lifecycle.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/torchnpu-pinned-host-memory-lifecycle.json
@@ -22,8 +22,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/torchnpu-pinned-host-memory-lifecycle/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/hardware/ascend/torchnpu-pinned-host-memory-lifecycle/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/hardware/ascend/torchnpu-pinned-host-memory-lifecycle/SKILL.md",
"src/inferrsi/data/skill_library/hardware/ascend/torchnpu-pinned-host-memory-lifecycle/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/assess-serving-preemption.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/assess-serving-preemption.json
index 12aeca1fd..98a3fc635 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/assess-serving-preemption.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/assess-serving-preemption.json
@@ -16,8 +16,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/assess-serving-preemption/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/methods/assess-serving-preemption/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/methods/assess-serving-preemption/SKILL.md",
"src/inferrsi/data/skill_library/methods/assess-serving-preemption/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/assess-split-backward-schedule.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/assess-split-backward-schedule.json
index 7c6e81473..5e6707c15 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/assess-split-backward-schedule.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/assess-split-backward-schedule.json
@@ -16,8 +16,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/assess-split-backward-schedule/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/methods/assess-split-backward-schedule/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/methods/assess-split-backward-schedule/SKILL.md",
"src/inferrsi/data/skill_library/methods/assess-split-backward-schedule/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-fixed-workload-claim.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-fixed-workload-claim.json
index a3b85ccdc..6ea9889ec 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-fixed-workload-claim.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-fixed-workload-claim.json
@@ -20,8 +20,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/audit-fixed-workload-claim/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/methods/audit-fixed-workload-claim/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/methods/audit-fixed-workload-claim/SKILL.md",
"src/inferrsi/data/skill_library/methods/audit-fixed-workload-claim/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-h3-metal-fasth3-semantics.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-h3-metal-fasth3-semantics.json
index 50b90d31b..11c0c1f52 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-h3-metal-fasth3-semantics.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-h3-metal-fasth3-semantics.json
@@ -29,8 +29,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/h3-metal/audit-h3-metal-fasth3-semantics/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/repositories/h3-metal/audit-h3-metal-fasth3-semantics/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/repositories/h3-metal/audit-h3-metal-fasth3-semantics/LICENSE",
"src/inferrsi/data/skill_library/repositories/h3-metal/audit-h3-metal-fasth3-semantics/SKILL.md",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-h3-runtime-residency.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-h3-runtime-residency.json
index c01e0e11f..80833a04b 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-h3-runtime-residency.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-h3-runtime-residency.json
@@ -30,8 +30,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/h3-c/audit-h3-runtime-residency/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/repositories/h3-c/audit-h3-runtime-residency/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/repositories/h3-c/audit-h3-runtime-residency/LICENSE",
"src/inferrsi/data/skill_library/repositories/h3-c/audit-h3-runtime-residency/SKILL.md",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-llama-runtime-state.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-llama-runtime-state.json
index 3adab00f6..edcd6136a 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-llama-runtime-state.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-llama-runtime-state.json
@@ -23,8 +23,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/llama-cpp/audit-llama-runtime-state/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/repositories/llama-cpp/audit-llama-runtime-state/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/repositories/llama-cpp/audit-llama-runtime-state/SKILL.md",
"src/inferrsi/data/skill_library/repositories/llama-cpp/audit-llama-runtime-state/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-recurrent-kv-finalization.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-recurrent-kv-finalization.json
index d5ab3d293..31109435d 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-recurrent-kv-finalization.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-recurrent-kv-finalization.json
@@ -26,8 +26,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/vllm-rlt/audit-recurrent-kv-finalization/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/repositories/vllm-rlt/audit-recurrent-kv-finalization/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/repositories/vllm-rlt/audit-recurrent-kv-finalization/LICENSE",
"src/inferrsi/data/skill_library/repositories/vllm-rlt/audit-recurrent-kv-finalization/SKILL.md",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-sd-cpp-residency.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-sd-cpp-residency.json
index 8b883145a..2472e8b2a 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-sd-cpp-residency.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-sd-cpp-residency.json
@@ -25,8 +25,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/stable-diffusion-cpp/audit-sd-cpp-residency/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/repositories/stable-diffusion-cpp/audit-sd-cpp-residency/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/repositories/stable-diffusion-cpp/audit-sd-cpp-residency/LICENSE",
"src/inferrsi/data/skill_library/repositories/stable-diffusion-cpp/audit-sd-cpp-residency/SKILL.md",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-sglang-diffusion-lifetimes.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-sglang-diffusion-lifetimes.json
index 2dab44411..bf0fdd81d 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-sglang-diffusion-lifetimes.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-sglang-diffusion-lifetimes.json
@@ -23,8 +23,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/sglang/audit-sglang-diffusion-lifetimes/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/repositories/sglang/audit-sglang-diffusion-lifetimes/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/repositories/sglang/audit-sglang-diffusion-lifetimes/LICENSE",
"src/inferrsi/data/skill_library/repositories/sglang/audit-sglang-diffusion-lifetimes/SKILL.md",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-vllm-kv-lifetimes.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-vllm-kv-lifetimes.json
index a4074b797..9d3fe86c2 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-vllm-kv-lifetimes.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-vllm-kv-lifetimes.json
@@ -21,8 +21,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/vllm/audit-vllm-kv-lifetimes/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/repositories/vllm/audit-vllm-kv-lifetimes/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/repositories/vllm/audit-vllm-kv-lifetimes/SKILL.md",
"src/inferrsi/data/skill_library/repositories/vllm/audit-vllm-kv-lifetimes/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/bound-windowed-attention-replay.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/bound-windowed-attention-replay.json
index 3c226dfe4..e4a6ae56b 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/bound-windowed-attention-replay.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/bound-windowed-attention-replay.json
@@ -23,8 +23,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/deepinfer/bound-windowed-attention-replay/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/repositories/deepinfer/bound-windowed-attention-replay/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/repositories/deepinfer/bound-windowed-attention-replay/SKILL.md",
"src/inferrsi/data/skill_library/repositories/deepinfer/bound-windowed-attention-replay/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/budget-speculative-verification.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/budget-speculative-verification.json
index bb08f2ed5..cd595f4c8 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/budget-speculative-verification.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/budget-speculative-verification.json
@@ -23,8 +23,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/deepinfer/budget-speculative-verification/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/repositories/deepinfer/budget-speculative-verification/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/repositories/deepinfer/budget-speculative-verification/SKILL.md",
"src/inferrsi/data/skill_library/repositories/deepinfer/budget-speculative-verification/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/calibrate-serving-simulation.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/calibrate-serving-simulation.json
index 3e86452fe..a32200f74 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/calibrate-serving-simulation.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/calibrate-serving-simulation.json
@@ -16,8 +16,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/calibrate-serving-simulation/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/methods/calibrate-serving-simulation/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/methods/calibrate-serving-simulation/SKILL.md",
"src/inferrsi/data/skill_library/methods/calibrate-serving-simulation/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/cgroup-resource-controls.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/cgroup-resource-controls.json
index a88384b33..181748878 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/cgroup-resource-controls.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/cgroup-resource-controls.json
@@ -25,8 +25,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/host/cgroup-resource-controls/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/hardware/host/cgroup-resource-controls/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/hardware/host/cgroup-resource-controls/SKILL.md",
"src/inferrsi/data/skill_library/hardware/host/cgroup-resource-controls/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/checkpoint-recovery-consistency.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/checkpoint-recovery-consistency.json
index 3572a1f8c..821d94c90 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/checkpoint-recovery-consistency.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/checkpoint-recovery-consistency.json
@@ -22,8 +22,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/checkpoint-recovery-consistency/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/methods/checkpoint-recovery-consistency/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/methods/checkpoint-recovery-consistency/SKILL.md",
"src/inferrsi/data/skill_library/methods/checkpoint-recovery-consistency/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/choose-parallel-training-plan.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/choose-parallel-training-plan.json
index d5ce0bdbf..a7dc39721 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/choose-parallel-training-plan.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/choose-parallel-training-plan.json
@@ -16,8 +16,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/choose-parallel-training-plan/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/methods/choose-parallel-training-plan/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/methods/choose-parallel-training-plan/SKILL.md",
"src/inferrsi/data/skill_library/methods/choose-parallel-training-plan/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/cite-check-downstream-pr.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/cite-check-downstream-pr.json
index ded00b5e0..840b7b60e 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/cite-check-downstream-pr.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/cite-check-downstream-pr.json
@@ -22,8 +22,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/workflows/cite-check-downstream-pr/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/workflows/cite-check-downstream-pr/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/skill-index.json",
"src/inferrsi/data/skill_library/workflows/cite-check-downstream-pr/SKILL.md",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/claim-contract.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/claim-contract.json
index a7f2bfa5d..d60cfb691 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/claim-contract.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/claim-contract.json
@@ -22,8 +22,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/workflows/claim-contract/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/workflows/claim-contract/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/skill-index.json",
"src/inferrsi/data/skill_library/workflows/claim-contract/SKILL.md",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/comfy-ui.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/comfy-ui.json
index acdc57b97..cbe943851 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/comfy-ui.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/comfy-ui.json
@@ -22,8 +22,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/comfy-ui/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/repositories/comfy-ui/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/repositories/comfy-ui/LICENSE",
"src/inferrsi/data/skill_library/repositories/comfy-ui/SKILL.md",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/competitor-scan.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/competitor-scan.json
index 0f5b0fb34..fad5b64d4 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/competitor-scan.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/competitor-scan.json
@@ -21,8 +21,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/workflows/competitor-scan/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/workflows/competitor-scan/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/skill-index.json",
"src/inferrsi/data/skill_library/workflows/competitor-scan/SKILL.md",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/dcp-async-save-performance.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/dcp-async-save-performance.json
index 064e2ca25..20ccfaab7 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/dcp-async-save-performance.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/dcp-async-save-performance.json
@@ -23,8 +23,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/frameworks/pytorch/dcp-async-save-performance/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/frameworks/pytorch/dcp-async-save-performance/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/frameworks/pytorch/dcp-async-save-performance/SKILL.md",
"src/inferrsi/data/skill_library/frameworks/pytorch/dcp-async-save-performance/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/dense-performance-evidence.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/dense-performance-evidence.json
index b20edd811..84e4341d6 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/dense-performance-evidence.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/dense-performance-evidence.json
@@ -21,8 +21,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/dense-performance-evidence/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/methods/dense-performance-evidence/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/methods/dense-performance-evidence/SKILL.md",
"src/inferrsi/data/skill_library/methods/dense-performance-evidence/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/diagnose-vllm-admission-pressure.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/diagnose-vllm-admission-pressure.json
index 70fd8e8a5..f86dbb84e 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/diagnose-vllm-admission-pressure.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/diagnose-vllm-admission-pressure.json
@@ -21,8 +21,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/vllm/diagnose-vllm-admission-pressure/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/repositories/vllm/diagnose-vllm-admission-pressure/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/repositories/vllm/diagnose-vllm-admission-pressure/SKILL.md",
"src/inferrsi/data/skill_library/repositories/vllm/diagnose-vllm-admission-pressure/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/diffusers-invocation-state.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/diffusers-invocation-state.json
index 3a883cf9a..60cdc2831 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/diffusers-invocation-state.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/diffusers-invocation-state.json
@@ -22,8 +22,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/frameworks/diffusers/diffusers-invocation-state/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/frameworks/diffusers/diffusers-invocation-state/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/frameworks/diffusers/diffusers-invocation-state/SKILL.md",
"src/inferrsi/data/skill_library/frameworks/diffusers/diffusers-invocation-state/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/draft-acceptance-issue.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/draft-acceptance-issue.json
index e90c2488d..ab4af1cd5 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/draft-acceptance-issue.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/draft-acceptance-issue.json
@@ -22,8 +22,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/workflows/draft-acceptance-issue/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/workflows/draft-acceptance-issue/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/skill-index.json",
"src/inferrsi/data/skill_library/workflows/draft-acceptance-issue/SKILL.md",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/dwarfstar.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/dwarfstar.json
index c456f30e9..7e3b9cd86 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/dwarfstar.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/dwarfstar.json
@@ -25,8 +25,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/dwarfstar/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/repositories/dwarfstar/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/repositories/dwarfstar/LICENSE",
"src/inferrsi/data/skill_library/repositories/dwarfstar/SKILL.md",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/evaluate-elastic-serving-placement.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/evaluate-elastic-serving-placement.json
index 3482d1338..79f5474ab 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/evaluate-elastic-serving-placement.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/evaluate-elastic-serving-placement.json
@@ -16,8 +16,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/evaluate-elastic-serving-placement/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/methods/evaluate-elastic-serving-placement/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/methods/evaluate-elastic-serving-placement/SKILL.md",
"src/inferrsi/data/skill_library/methods/evaluate-elastic-serving-placement/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/generation-cache-lifecycle.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/generation-cache-lifecycle.json
index 7d68adf8b..318cecea6 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/generation-cache-lifecycle.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/generation-cache-lifecycle.json
@@ -22,8 +22,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/mlx-lm/generation-cache-lifecycle/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/repositories/mlx-lm/generation-cache-lifecycle/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/repositories/mlx-lm/generation-cache-lifecycle/SKILL.md",
"src/inferrsi/data/skill_library/repositories/mlx-lm/generation-cache-lifecycle/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/host-memory-management.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/host-memory-management.json
index bb39eac1d..c4f1d9eea 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/host-memory-management.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/host-memory-management.json
@@ -30,8 +30,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/host/host-memory-management/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/hardware/host/host-memory-management/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/hardware/host/host-memory-management/SKILL.md",
"src/inferrsi/data/skill_library/hardware/host/host-memory-management/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/host-overhead-optimization.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/host-overhead-optimization.json
index 9f20ba9d7..d81f60d73 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/host-overhead-optimization.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/host-overhead-optimization.json
@@ -22,8 +22,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/host/host-overhead-optimization/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/hardware/host/host-overhead-optimization/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/hardware/host/host-overhead-optimization/SKILL.md",
"src/inferrsi/data/skill_library/hardware/host/host-overhead-optimization/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/husky.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/husky.json
index 3dee4b666..50d9ffac9 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/husky.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/husky.json
@@ -21,8 +21,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/husky/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/repositories/husky/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/repositories/husky/SKILL.md",
"src/inferrsi/data/skill_library/repositories/husky/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/inference-benchmark-design.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/inference-benchmark-design.json
index 3b2327374..e3263203a 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/inference-benchmark-design.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/inference-benchmark-design.json
@@ -27,7 +27,11 @@
"stream-boundaries",
"treatment-delivery",
"trial-validity",
- "protocol-audit"
+ "protocol-audit",
+ "trial-evidence",
+ "result-origin",
+ "oracle-boundary",
+ "candidate-selection"
],
"origin": [
"external"
@@ -35,8 +39,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/inference-benchmark-design/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/methods/inference-benchmark-design/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/methods/inference-benchmark-design/SKILL.md",
"src/inferrsi/data/skill_library/methods/inference-benchmark-design/metadata.json",
@@ -47,9 +51,11 @@
"src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/justgoal-evaluation-contracts.md",
"src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/justgoal-source.json",
"src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/task-benchmark-selection.md",
+ "src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/xeforge-source.json",
+ "src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/xeforge-trial-evidence.md",
"src/inferrsi/data/skill_library/skill-index.json"
],
- "content_sha256": "7fd7f557f5c99ca4ec4c46f2d97e67ecf280f5f0fdf071871a14cc08a7cb1c84"
+ "content_sha256": "a7ea13bc11b1ef42227d3103447c47d154d3929aa39bbbe89643f249d2d39828"
}
],
"index_type": "packaged-skill",
@@ -58,8 +64,8 @@
},
"checkout_ref": "checkout:inference-benchmark-design",
"source_files": {
- "src/inferrsi/data/skill_library/methods/inference-benchmark-design/SKILL.md": "7fd7f557f5c99ca4ec4c46f2d97e67ecf280f5f0fdf071871a14cc08a7cb1c84",
- "src/inferrsi/data/skill_library/methods/inference-benchmark-design/metadata.json": "a646de55162cb8160f3f0947cab4b6ecac81927c3225019044b3f909087ba048",
+ "src/inferrsi/data/skill_library/methods/inference-benchmark-design/SKILL.md": "a7ea13bc11b1ef42227d3103447c47d154d3929aa39bbbe89643f249d2d39828",
+ "src/inferrsi/data/skill_library/methods/inference-benchmark-design/metadata.json": "cf42c6937c09ca5036cc124a43fe03a18d00dc5cbf59f0e2a0c3bad8cb3a1884",
"src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/autotunebench-source.json": "bc343ece2bf40c4e8aa4bd8d84f32465d00633255557feda5fe7799ce24e8688",
"src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/autotunebench-trial-validity.md": "cb3a7a5d94d056f868af07f92a16a6fef31eafd3199ed07ae79e93798e320b1d",
"src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/benchmark-commands.md": "0898424e0bff3a6246e1eeeda6abd6c5bd974c047fe32f3bbd5ab9d31ce17cd3",
@@ -67,6 +73,8 @@
"src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/justgoal-evaluation-contracts.md": "d25df795fd301e8a1bb436e5f8122d0bac2441c43104e59a3b310fd5a64f2f3e",
"src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/justgoal-source.json": "60f2784384ea1a3b08a2ecafb60207d8e3707247dc7bc177b95b463d81f1cc16",
"src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/task-benchmark-selection.md": "0d4bb080a754e26846e81680023db0dff5e6a4c96be4327c411c3b72ac4ef8e2",
+ "src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/xeforge-source.json": "6c21791b9c8ecbc9645c6deb659bd897e17f70525536ea25e884a62fc5fb6b25",
+ "src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/xeforge-trial-evidence.md": "802c4dfe83983cbd6740231d5d0e2b459792b685de8dfbefb6dc51a912e23604",
"src/inferrsi/data/skill_library/skill-index.json": "9ea8b2ef190777e683a3905f0614612a37782be4d655d230c000188b0c7073db"
},
"skill_metadata": {
@@ -90,7 +98,11 @@
"stream-boundaries",
"treatment-delivery",
"trial-validity",
- "protocol-audit"
+ "protocol-audit",
+ "trial-evidence",
+ "result-origin",
+ "oracle-boundary",
+ "candidate-selection"
],
"status": "candidate",
"profile": "local-skill-v1",
@@ -310,14 +322,61 @@
"Tables 1-7"
],
"readset": "references/autotunebench-trial-validity.md"
+ },
+ {
+ "type": "git",
+ "url": "https://github.com/IntelLabs/Xe-Forge",
+ "commit": "6cd3ee98dfe32746b345a6abe521fa4cb9bdc187",
+ "paths": [
+ "CONTRIBUTING.md",
+ "LICENSE",
+ "README.md",
+ "docs/CORRECTNESS.md",
+ "docs/KERNEL_REPO.md",
+ "pyproject.toml",
+ "src/xe_forge/claude/generator.py",
+ "src/xe_forge/claude/templates/CLAUDE.md.j2",
+ "src/xe_forge/cli.py",
+ "src/xe_forge/core/trial_manager.py",
+ "src/xe_forge/engines/claude_engine.py",
+ "src/xe_forge/external.py",
+ "src/xe_forge/skills/__init__.py",
+ "src/xe_forge/skills/benchmark.py",
+ "src/xe_forge/skills/trial.py",
+ "src/xe_forge/skills/upstream.py",
+ "tests/test_benchmark_gate.py",
+ "tests/test_trial_manager_ranking.py"
+ ],
+ "readset": "references/xeforge-source.json",
+ "license": "Apache-2.0 repository default; DCO and curated-example exclusions retained",
+ "scope": "Selected source-bound trial origin/comparison identity, host outcomes, measured-only selection and baseline-oracle contracts; source-only, no execution"
+ },
+ {
+ "type": "paper",
+ "id": "arxiv:2605.26118",
+ "version": "v1",
+ "url": "https://arxiv.org/html/2605.26118v1",
+ "sections": [
+ "Abstract",
+ "I-VIII",
+ "References",
+ "Appendix A",
+ "Tables 1-3",
+ "Algorithm 1",
+ "Listing 1",
+ "Figure captions 1-15"
+ ],
+ "readset": "references/xeforge-source.json",
+ "license": "CC-BY-4.0",
+ "scope": "Complete HTML text/appendix and captions; historical author-reported context, unused graphic values remain unverified"
}
],
"empirical_validation": "not_run",
"applicability": {
- "scope": "Selecting task quality gates, reference parity checks and performance workloads for text, agentic coding, work agents, cache-aware ASR, TTS, full-duplex audio/video, image and video inference, and designing goodput-based multi-regime comparisons that fit InferRSI's evidence trail; interpreting treatment delivery, arm validity and stated-versus-observed protocol enforcement in supplied tuning reports",
+ "scope": "Selecting task quality gates, reference parity checks and performance workloads for text, agentic coding, work agents, cache-aware ASR, TTS, full-duplex audio/video, image and video inference, and designing goodput-based multi-regime comparisons that fit InferRSI's evidence trail; interpreting treatment delivery, arm validity and stated-versus-observed protocol enforcement in supplied tuning reports; interpreting source-bound kernel trial origin, host evaluator outcomes, unresolved performance and measured-only versus manual candidate selection",
"prerequisites": "The primary objective, timing boundary, quality gates, sample/failure accounting, required regimes, repetitions, seeds and decision rule are frozen before optimization; baseline and candidate share hardware, software stack, input distribution, benchmark configuration, warmup and measurement protocol, and on a shared machine also one time window and dedicated devices; cache-aware ASR also requires the selected model/config and first/steady geometry, decoded clock and reset/EOU/EOF boundaries to be established",
- "input_contract": "The task family and deployment use case; candidate quality evaluators and reference parity; the declared SLO and the caller's policy on which regimes must improve or must not regress; for an audit, a supplied fixed-workload report with request-to-trial grouping, exclusion and failure counts and the declared aggregation rule; for a treatment audit, the frozen delivery/arm-validity rules, run/candidate identities, feedback and consumer-input evidence, and per-arm raw records",
- "produced_artifact": "A frozen benchmark design with evaluators, reference parity, primary objective, timing boundary, quality gates, required regimes, repetition and seed rules and an explicit decision config, plus the evidence-tree layout a PASS claim must produce; for a supplied report, the computed threshold result and missing evidence. Candidate knowledge, not qualification of any model or backend; for a treatment audit, a contract-bound eligibility and interpretation report separating treatment exposure, observed checks, comparator identity, anomaly disposition and source conflicts",
+ "input_contract": "The task family and deployment use case; candidate quality evaluators and reference parity; the declared SLO and the caller's policy on which regimes must improve or must not regress; for an audit, a supplied fixed-workload report with request-to-trial grouping, exclusion and failure counts and the declared aggregation rule; for a treatment audit, the frozen delivery/arm-validity rules, run/candidate identities, feedback and consumer-input evidence, and per-arm raw records; for a kernel trial audit, complete saved candidate bytes and IDs, baseline/spec/reference/variant identities, result-origin fields, raw host outcome and return code, named gate and persisted ratio, actual oracle and the selecting/delivering caller",
+ "produced_artifact": "A frozen benchmark design with evaluators, reference parity, primary objective, timing boundary, quality gates, required regimes, repetition and seed rules and an explicit decision config, plus the evidence-tree layout a PASS claim must produce; for a supplied report, the computed threshold result and missing evidence. Candidate knowledge, not qualification of any model or backend; for a treatment audit, a contract-bound eligibility and interpretation report separating treatment exposure, observed checks, comparator identity, anomaly disposition and source conflicts; for a kernel trial audit, a source-bound interpretation separating artifact/cohort identity, origin, oracle, performance resolution and selected-versus-delivered eligibility, without promoting kernel parity into a gain or whole-model acceptance",
"failure_modes": [
"Raw throughput is optimized in place of goodput, so requests served outside the SLO count toward a win",
"One concurrency level or one undisclosed aggregate score stands in for all required regimes",
@@ -329,16 +388,20 @@
"A cache-aware ASR EOU is treated as EOF or full reset, nominal chunk duration as the decoded mel frontier, or shape-only geometry PASS as a native model-state test",
"An enabled treatment or stored feedback summary is taken as proof of delivery to the next eligible consumer",
"A failed arm-validity condition is overridden by a favorable best timing or a saturation/null interpretation",
- "Complete gate keys or zero recorded failures are read as proof that every declared protocol check ran"
+ "Complete gate keys or zero recorded failures are read as proof that every declared protocol check ran",
+ "A tool-origin measured marker or completed status is treated as a resolved performance gain",
+ "A displayed/manual best, baseline copy or edited candidate is reported as the eligible measured delivery",
+ "Ratio omission alone is assumed to clear an earlier ratio, or baseline agreement is treated as independent semantic correctness"
],
- "refusal_point": "Records missing coverage and high-variance results as INCONCLUSIVE rather than a win; a run without a frozen RunSpec, or whose validator changed after the plan was frozen, is INCONCLUSIVE regardless of metric values; sets no universal numeric gate or noise threshold; withholds causal treatment benefit/null conclusions when required delivery or arm eligibility is unverified, and preserves conflicts between stated protocol, exported code and source reports"
+ "refusal_point": "Records missing coverage and high-variance results as INCONCLUSIVE rather than a win; a run without a frozen RunSpec, or whose validator changed after the plan was frozen, is INCONCLUSIVE regardless of metric values; sets no universal numeric gate or noise threshold; withholds causal treatment benefit/null conclusions when required delivery or arm eligibility is unverified, and preserves conflicts between stated protocol, exported code and source reports; withholds a kernel gain for unresolved performance or an unbound comparison and identifies missing independent semantic evidence when only baseline agreement is available"
},
"recommendations": [
"Freeze one primary objective, timing boundary, quality gates and sample/failure accounting before optimization.",
"Choose the required regimes from the deployment use case, report each separately, and record which must improve or must not regress in a versioned decision config.",
"Use the replay trace that matches the actual deployment pattern.",
"State the concurrency, trace, model, SKU and microbenchmark scope boundaries in any report that cites benchmark results.",
- "Trace treatment to its eligible consumer and apply the frozen arm-validity precedence before attributing benefit, saturation or a null."
+ "Trace treatment to its eligible consumer and apply the frozen arm-validity precedence before attributing benefit, saturation or a null.",
+ "Bind the complete saved candidate and comparator cohort; keep result origin, actual oracle, named gate/ratio and delivered eligibility separate."
],
"limitations": [
"Source-derived candidate; no local efficacy validation.",
@@ -347,7 +410,8 @@
"Benchmark feasibility and package-consumption checks do not promote this candidate or replace task quality, repeated A/B and service qualification.",
"The pinned NeMo-Speech.cpp ASR reference covers selected source/test definitions and author-reported benchmark boundaries; native model/device, decoder internals, quality, long-audio/load and service behavior remain not_run.",
"JustGoal contributes source-only controlled-evaluation and kernel-acceptance guidance; its repaired/retested timings, released-pass counts and protocol differences are author-reported, not locally reproduced or a complete campaign runner.",
- "The AutoTuneBench reference is source-only: original operational checkpoint/prompt receipts remain unavailable, source contradictions remain explicit, and no tuning, device/performance or agent-efficacy validation was run."
+ "The AutoTuneBench reference is source-only: original operational checkpoint/prompt receipts remain unavailable, source contradictions remain explicit, and no tuning, device/performance or agent-efficacy validation was run.",
+ "The Xe-Forge reference is source-only and limited to inspected host/manual/Claude trial paths; named-verdict update predicates and caller defaults remain explicit. Native tests, backend/model/quality/performance/service behavior and agent efficacy were not evaluated, and source/package checks do not promote whole-model support."
],
"provenance_readsets": [
"references/task-benchmark-selection.md",
@@ -356,7 +420,9 @@
"references/justgoal-evaluation-contracts.md",
"references/justgoal-source.json",
"references/autotunebench-trial-validity.md",
- "references/autotunebench-source.json"
+ "references/autotunebench-source.json",
+ "references/xeforge-trial-evidence.md",
+ "references/xeforge-source.json"
],
"references": [
"../inference-optimization-casebook/cases/admission-drain-occupancy.md",
@@ -366,10 +432,10 @@
"searchspace_not_applicable": "SKILL.md §§ Select the task and its evaluation contract, Statistical requirements, Shared-machine measurement discipline, and Search integrity and final-state verification design comparable evaluation; hardware identity and allocation isolation are comparison controls, not a hardware-resource mechanism."
},
"applicability": {
- "scope": "Selecting task quality gates, reference parity checks and performance workloads for text, agentic coding, work agents, cache-aware ASR, TTS, full-duplex audio/video, image and video inference, and designing goodput-based multi-regime comparisons that fit InferRSI's evidence trail; interpreting treatment delivery, arm validity and stated-versus-observed protocol enforcement in supplied tuning reports",
+ "scope": "Selecting task quality gates, reference parity checks and performance workloads for text, agentic coding, work agents, cache-aware ASR, TTS, full-duplex audio/video, image and video inference, and designing goodput-based multi-regime comparisons that fit InferRSI's evidence trail; interpreting treatment delivery, arm validity and stated-versus-observed protocol enforcement in supplied tuning reports; interpreting source-bound kernel trial origin, host evaluator outcomes, unresolved performance and measured-only versus manual candidate selection",
"prerequisites": "The primary objective, timing boundary, quality gates, sample/failure accounting, required regimes, repetitions, seeds and decision rule are frozen before optimization; baseline and candidate share hardware, software stack, input distribution, benchmark configuration, warmup and measurement protocol, and on a shared machine also one time window and dedicated devices; cache-aware ASR also requires the selected model/config and first/steady geometry, decoded clock and reset/EOU/EOF boundaries to be established",
- "input_contract": "The task family and deployment use case; candidate quality evaluators and reference parity; the declared SLO and the caller's policy on which regimes must improve or must not regress; for an audit, a supplied fixed-workload report with request-to-trial grouping, exclusion and failure counts and the declared aggregation rule; for a treatment audit, the frozen delivery/arm-validity rules, run/candidate identities, feedback and consumer-input evidence, and per-arm raw records",
- "produced_artifact": "A frozen benchmark design with evaluators, reference parity, primary objective, timing boundary, quality gates, required regimes, repetition and seed rules and an explicit decision config, plus the evidence-tree layout a PASS claim must produce; for a supplied report, the computed threshold result and missing evidence. Candidate knowledge, not qualification of any model or backend; for a treatment audit, a contract-bound eligibility and interpretation report separating treatment exposure, observed checks, comparator identity, anomaly disposition and source conflicts",
+ "input_contract": "The task family and deployment use case; candidate quality evaluators and reference parity; the declared SLO and the caller's policy on which regimes must improve or must not regress; for an audit, a supplied fixed-workload report with request-to-trial grouping, exclusion and failure counts and the declared aggregation rule; for a treatment audit, the frozen delivery/arm-validity rules, run/candidate identities, feedback and consumer-input evidence, and per-arm raw records; for a kernel trial audit, complete saved candidate bytes and IDs, baseline/spec/reference/variant identities, result-origin fields, raw host outcome and return code, named gate and persisted ratio, actual oracle and the selecting/delivering caller",
+ "produced_artifact": "A frozen benchmark design with evaluators, reference parity, primary objective, timing boundary, quality gates, required regimes, repetition and seed rules and an explicit decision config, plus the evidence-tree layout a PASS claim must produce; for a supplied report, the computed threshold result and missing evidence. Candidate knowledge, not qualification of any model or backend; for a treatment audit, a contract-bound eligibility and interpretation report separating treatment exposure, observed checks, comparator identity, anomaly disposition and source conflicts; for a kernel trial audit, a source-bound interpretation separating artifact/cohort identity, origin, oracle, performance resolution and selected-versus-delivered eligibility, without promoting kernel parity into a gain or whole-model acceptance",
"failure_modes": [
"Raw throughput is optimized in place of goodput, so requests served outside the SLO count toward a win",
"One concurrency level or one undisclosed aggregate score stands in for all required regimes",
@@ -381,16 +447,20 @@
"A cache-aware ASR EOU is treated as EOF or full reset, nominal chunk duration as the decoded mel frontier, or shape-only geometry PASS as a native model-state test",
"An enabled treatment or stored feedback summary is taken as proof of delivery to the next eligible consumer",
"A failed arm-validity condition is overridden by a favorable best timing or a saturation/null interpretation",
- "Complete gate keys or zero recorded failures are read as proof that every declared protocol check ran"
+ "Complete gate keys or zero recorded failures are read as proof that every declared protocol check ran",
+ "A tool-origin measured marker or completed status is treated as a resolved performance gain",
+ "A displayed/manual best, baseline copy or edited candidate is reported as the eligible measured delivery",
+ "Ratio omission alone is assumed to clear an earlier ratio, or baseline agreement is treated as independent semantic correctness"
],
- "refusal_point": "Records missing coverage and high-variance results as INCONCLUSIVE rather than a win; a run without a frozen RunSpec, or whose validator changed after the plan was frozen, is INCONCLUSIVE regardless of metric values; sets no universal numeric gate or noise threshold; withholds causal treatment benefit/null conclusions when required delivery or arm eligibility is unverified, and preserves conflicts between stated protocol, exported code and source reports"
+ "refusal_point": "Records missing coverage and high-variance results as INCONCLUSIVE rather than a win; a run without a frozen RunSpec, or whose validator changed after the plan was frozen, is INCONCLUSIVE regardless of metric values; sets no universal numeric gate or noise threshold; withholds causal treatment benefit/null conclusions when required delivery or arm eligibility is unverified, and preserves conflicts between stated protocol, exported code and source reports; withholds a kernel gain for unresolved performance or an unbound comparison and identifies missing independent semantic evidence when only baseline agreement is available"
},
"recommendations": [
"Freeze one primary objective, timing boundary, quality gates and sample/failure accounting before optimization.",
"Choose the required regimes from the deployment use case, report each separately, and record which must improve or must not regress in a versioned decision config.",
"Use the replay trace that matches the actual deployment pattern.",
"State the concurrency, trace, model, SKU and microbenchmark scope boundaries in any report that cites benchmark results.",
- "Trace treatment to its eligible consumer and apply the frozen arm-validity precedence before attributing benefit, saturation or a null."
+ "Trace treatment to its eligible consumer and apply the frozen arm-validity precedence before attributing benefit, saturation or a null.",
+ "Bind the complete saved candidate and comparator cohort; keep result origin, actual oracle, named gate/ratio and delivered eligibility separate."
],
"limitations": [
"This generated abstract points to the complete packaged skill; external evidence and upstream repositories remain source links.",
@@ -403,7 +473,8 @@
"Benchmark feasibility and package-consumption checks do not promote this candidate or replace task quality, repeated A/B and service qualification.",
"The pinned NeMo-Speech.cpp ASR reference covers selected source/test definitions and author-reported benchmark boundaries; native model/device, decoder internals, quality, long-audio/load and service behavior remain not_run.",
"JustGoal contributes source-only controlled-evaluation and kernel-acceptance guidance; its repaired/retested timings, released-pass counts and protocol differences are author-reported, not locally reproduced or a complete campaign runner.",
- "The AutoTuneBench reference is source-only: original operational checkpoint/prompt receipts remain unavailable, source contradictions remain explicit, and no tuning, device/performance or agent-efficacy validation was run."
+ "The AutoTuneBench reference is source-only: original operational checkpoint/prompt receipts remain unavailable, source contradictions remain explicit, and no tuning, device/performance or agent-efficacy validation was run.",
+ "The Xe-Forge reference is source-only and limited to inspected host/manual/Claude trial paths; named-verdict update predicates and caller defaults remain explicit. Native tests, backend/model/quality/performance/service behavior and agent efficacy were not evaluated, and source/package checks do not promote whole-model support."
],
"verification": {
"locally_verified": false,
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/inference-optimization-casebook.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/inference-optimization-casebook.json
index 3d6372c43..c8ed81c96 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/inference-optimization-casebook.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/inference-optimization-casebook.json
@@ -21,8 +21,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/inference-optimization-casebook/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/methods/inference-optimization-casebook/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/methods/inference-optimization-casebook/SKILL.md",
"src/inferrsi/data/skill_library/methods/inference-optimization-casebook/cases/admission-drain-occupancy.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/kernel-writing-guide.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/kernel-writing-guide.json
index 1040189df..8c1161fd4 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/kernel-writing-guide.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/kernel-writing-guide.json
@@ -39,8 +39,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/kernel-writing-guide/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/methods/kernel-writing-guide/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/methods/kernel-writing-guide/SKILL.md",
"src/inferrsi/data/skill_library/methods/kernel-writing-guide/cases/causal-conv1d-dispatch-state.md",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/kv-tier-management.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/kv-tier-management.json
index 1c1f0ac80..1413f0bda 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/kv-tier-management.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/kv-tier-management.json
@@ -24,8 +24,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/lmcache/kv-tier-management/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/repositories/lmcache/kv-tier-management/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/repositories/lmcache/kv-tier-management/SKILL.md",
"src/inferrsi/data/skill_library/repositories/lmcache/kv-tier-management/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/lazy-evaluation-stream-lifetimes.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/lazy-evaluation-stream-lifetimes.json
index c3b8b61d3..0201dd62d 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/lazy-evaluation-stream-lifetimes.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/lazy-evaluation-stream-lifetimes.json
@@ -22,8 +22,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/frameworks/mlx/lazy-evaluation-stream-lifetimes/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/frameworks/mlx/lazy-evaluation-stream-lifetimes/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/frameworks/mlx/lazy-evaluation-stream-lifetimes/SKILL.md",
"src/inferrsi/data/skill_library/frameworks/mlx/lazy-evaluation-stream-lifetimes/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/lily.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/lily.json
index 8c592e80d..84aca0d0c 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/lily.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/lily.json
@@ -25,8 +25,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/lily/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/repositories/lily/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/repositories/lily/LICENSE",
"src/inferrsi/data/skill_library/repositories/lily/NOTICE.md",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/lithos-metal.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/lithos-metal.json
index 26722f7f4..735680576 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/lithos-metal.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/lithos-metal.json
@@ -21,8 +21,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/lithos-metal/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/repositories/lithos-metal/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/repositories/lithos-metal/LICENSE",
"src/inferrsi/data/skill_library/repositories/lithos-metal/SKILL.md",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/local-dream.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/local-dream.json
index cb94c8a24..c93287c90 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/local-dream.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/local-dream.json
@@ -29,8 +29,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/local-dream/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/repositories/local-dream/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/repositories/local-dream/SKILL.md",
"src/inferrsi/data/skill_library/repositories/local-dream/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/mistral-rs.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/mistral-rs.json
index 636fbe213..481ece93b 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/mistral-rs.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/mistral-rs.json
@@ -26,8 +26,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/mistral-rs/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/repositories/mistral-rs/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/repositories/mistral-rs/LICENSE",
"src/inferrsi/data/skill_library/repositories/mistral-rs/SKILL.md",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/mlc-llm.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/mlc-llm.json
index b94c5f561..3e71781f9 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/mlc-llm.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/mlc-llm.json
@@ -27,8 +27,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/mlc-llm/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/repositories/mlc-llm/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/repositories/mlc-llm/LICENSE",
"src/inferrsi/data/skill_library/repositories/mlc-llm/SKILL.md",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/mlx-swift-lm.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/mlx-swift-lm.json
index fef01f452..e34e39165 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/mlx-swift-lm.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/mlx-swift-lm.json
@@ -27,8 +27,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/mlx-swift-lm/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/repositories/mlx-swift-lm/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/repositories/mlx-swift-lm/LICENSE",
"src/inferrsi/data/skill_library/repositories/mlx-swift-lm/SKILL.md",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/npu-skill-factory.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/npu-skill-factory.json
index 1adcbdc00..2ff84503e 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/npu-skill-factory.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/npu-skill-factory.json
@@ -22,8 +22,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/workflows/npu-skill-factory/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/workflows/npu-skill-factory/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/skill-index.json",
"src/inferrsi/data/skill_library/workflows/npu-skill-factory/SKILL.md",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/optimization-search-policy.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/optimization-search-policy.json
index 8965fb642..97ae8764e 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/optimization-search-policy.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/optimization-search-policy.json
@@ -21,8 +21,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/optimization-search-policy/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/methods/optimization-search-policy/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/methods/optimization-search-policy/SKILL.md",
"src/inferrsi/data/skill_library/methods/optimization-search-policy/cases/sarathi-chunk-budget.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/os-process-placement.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/os-process-placement.json
index 8c0cf7b12..dafa2143c 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/os-process-placement.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/os-process-placement.json
@@ -24,8 +24,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/host/os-process-placement/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/hardware/host/os-process-placement/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/hardware/host/os-process-placement/SKILL.md",
"src/inferrsi/data/skill_library/hardware/host/os-process-placement/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/performance-ceiling-analysis.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/performance-ceiling-analysis.json
index ae1810d82..390828963 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/performance-ceiling-analysis.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/performance-ceiling-analysis.json
@@ -22,8 +22,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/SKILL.md",
"src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/plan-activation-residency.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/plan-activation-residency.json
index 5ccb28ffe..24ca9b403 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/plan-activation-residency.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/plan-activation-residency.json
@@ -16,8 +16,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/plan-activation-residency/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/methods/plan-activation-residency/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/methods/plan-activation-residency/SKILL.md",
"src/inferrsi/data/skill_library/methods/plan-activation-residency/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/project-maya.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/project-maya.json
index abec7ae74..f5a2f6383 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/project-maya.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/project-maya.json
@@ -25,8 +25,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/project-maya/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/repositories/project-maya/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/repositories/project-maya/LICENSE",
"src/inferrsi/data/skill_library/repositories/project-maya/SKILL.md",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/pytorch.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/pytorch.json
index 97d160bec..2d4c3b117 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/pytorch.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/pytorch.json
@@ -24,8 +24,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/frameworks/pytorch/pytorch/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/frameworks/pytorch/pytorch/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/frameworks/pytorch/pytorch/LICENSE",
"src/inferrsi/data/skill_library/frameworks/pytorch/pytorch/SKILL.md",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/repository-evolution-analysis.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/repository-evolution-analysis.json
index 27968f7c8..64ad439dc 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/repository-evolution-analysis.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/repository-evolution-analysis.json
@@ -21,8 +21,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/repository-evolution-analysis/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/methods/repository-evolution-analysis/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/methods/repository-evolution-analysis/SKILL.md",
"src/inferrsi/data/skill_library/methods/repository-evolution-analysis/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/rsi-evidence.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/rsi-evidence.json
index 465739baa..c77676e10 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/rsi-evidence.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/rsi-evidence.json
@@ -22,8 +22,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/workflows/rsi-evidence/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/workflows/rsi-evidence/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/skill-index.json",
"src/inferrsi/data/skill_library/workflows/rsi-evidence/SKILL.md",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/skill-evolution-playbook.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/skill-evolution-playbook.json
index c470e93b8..820022512 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/skill-evolution-playbook.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/skill-evolution-playbook.json
@@ -21,8 +21,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/skill-evolution-playbook/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/methods/skill-evolution-playbook/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/methods/skill-evolution-playbook/SKILL.md",
"src/inferrsi/data/skill_library/methods/skill-evolution-playbook/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/splash.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/splash.json
index a9476f7cf..c47cac828 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/splash.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/splash.json
@@ -25,8 +25,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/splash/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/repositories/splash/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/repositories/splash/LICENSE",
"src/inferrsi/data/skill_library/repositories/splash/SKILL.md",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/storage-io-measurement.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/storage-io-measurement.json
index fc715e09f..88f6da49d 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/storage-io-measurement.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/storage-io-measurement.json
@@ -24,8 +24,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/host/storage-io-measurement/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/hardware/host/storage-io-measurement/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/hardware/host/storage-io-measurement/SKILL.md",
"src/inferrsi/data/skill_library/hardware/host/storage-io-measurement/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/training-input-pipeline.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/training-input-pipeline.json
index 045b18bc4..eaeb5178e 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/training-input-pipeline.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/training-input-pipeline.json
@@ -23,8 +23,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/training-input-pipeline/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/methods/training-input-pipeline/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/methods/training-input-pipeline/SKILL.md",
"src/inferrsi/data/skill_library/methods/training-input-pipeline/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/training-resource-budget.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/training-resource-budget.json
index a2429cac2..101fb19de 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/training-resource-budget.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/training-resource-budget.json
@@ -23,8 +23,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/training-resource-budget/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/methods/training-resource-budget/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/methods/training-resource-budget/SKILL.md",
"src/inferrsi/data/skill_library/methods/training-resource-budget/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/video-diffusion-optimization.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/video-diffusion-optimization.json
index 2fbb6eebc..e8740dd6a 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/video-diffusion-optimization.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/video-diffusion-optimization.json
@@ -26,8 +26,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/video-diffusion-optimization/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/methods/video-diffusion-optimization/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/methods/video-diffusion-optimization/SKILL.md",
"src/inferrsi/data/skill_library/methods/video-diffusion-optimization/assets/campaign.template.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/vllm-metal.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/vllm-metal.json
index 179f342ea..53daba30d 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/vllm-metal.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/vllm-metal.json
@@ -26,8 +26,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/vllm-metal/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/repositories/vllm-metal/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/repositories/vllm-metal/LICENSE",
"src/inferrsi/data/skill_library/repositories/vllm-metal/SKILL.md",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/weight-loading-optimization.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/weight-loading-optimization.json
index 3cc50bdee..5a197dc6f 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/weight-loading-optimization.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/weight-loading-optimization.json
@@ -29,8 +29,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/weight-loading-optimization/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/methods/weight-loading-optimization/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/methods/weight-loading-optimization/SKILL.md",
"src/inferrsi/data/skill_library/methods/weight-loading-optimization/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/audit-afd-p2p-exchanges.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/audit-afd-p2p-exchanges.json
index 42b227ef5..b65516470 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/audit-afd-p2p-exchanges.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/audit-afd-p2p-exchanges.json
@@ -23,8 +23,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/afd-plugin/audit-afd-p2p-exchanges/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/repositories/afd-plugin/audit-afd-p2p-exchanges/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/repositories/afd-plugin/audit-afd-p2p-exchanges/SKILL.md",
"src/inferrsi/data/skill_library/repositories/afd-plugin/audit-afd-p2p-exchanges/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/audit-flare-session-lifecycle.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/audit-flare-session-lifecycle.json
index 0fc99822c..b5d060888 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/audit-flare-session-lifecycle.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/audit-flare-session-lifecycle.json
@@ -29,8 +29,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/flare-local-inference/audit-flare-session-lifecycle/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/repositories/flare-local-inference/audit-flare-session-lifecycle/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/repositories/flare-local-inference/audit-flare-session-lifecycle/LICENSE",
"src/inferrsi/data/skill_library/repositories/flare-local-inference/audit-flare-session-lifecycle/SKILL.md",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/diagnose-attention-bottlenecks.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/diagnose-attention-bottlenecks.json
index 19f847d38..fe1ca0a30 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/diagnose-attention-bottlenecks.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/diagnose-attention-bottlenecks.json
@@ -16,8 +16,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/cuda/diagnose-attention-bottlenecks/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/hardware/cuda/diagnose-attention-bottlenecks/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/hardware/cuda/diagnose-attention-bottlenecks/SKILL.md",
"src/inferrsi/data/skill_library/hardware/cuda/diagnose-attention-bottlenecks/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/host-overhead-profiling.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/host-overhead-profiling.json
index 7fac0bc38..730e91d17 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/host-overhead-profiling.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/host-overhead-profiling.json
@@ -22,8 +22,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/cuda/host-overhead-profiling/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/hardware/cuda/host-overhead-profiling/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/hardware/cuda/host-overhead-profiling/SKILL.md",
"src/inferrsi/data/skill_library/hardware/cuda/host-overhead-profiling/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/reason-hopper-kernels.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/reason-hopper-kernels.json
index 55040913f..3dce40e6d 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/reason-hopper-kernels.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/reason-hopper-kernels.json
@@ -36,8 +36,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/cuda/reason-hopper-kernels/SKILL.md",
- "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/hardware/cuda/reason-hopper-kernels/SKILL.md",
+ "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
"paths": [
"src/inferrsi/data/skill_library/hardware/cuda/reason-hopper-kernels/SKILL.md",
"src/inferrsi/data/skill_library/hardware/cuda/reason-hopper-kernels/metadata.json",
diff --git a/src/inferrsi/data/skill_library/methods/inference-benchmark-design/SKILL.md b/src/inferrsi/data/skill_library/methods/inference-benchmark-design/SKILL.md
index b40a52d2c..9409c9cc6 100644
--- a/src/inferrsi/data/skill_library/methods/inference-benchmark-design/SKILL.md
+++ b/src/inferrsi/data/skill_library/methods/inference-benchmark-design/SKILL.md
@@ -185,6 +185,11 @@ Keep model/budget/task scope, independent acceptance, released versus repaired
artifacts and workspace/stream/cache contracts explicit. Its results remain
author-reported; it adds no runner or device/performance qualification.
+For source-bound kernel trial records, read
+[trial identity, evaluator evidence and candidate selection](references/xeforge-trial-evidence.md).
+Keep tool origin, actual oracle, unresolved performance, selection and delivered
+eligibility distinct; a retained parity candidate is not a measured gain.
+
## Evidence trail requirements (InferRSI compatibility)
A benchmark campaign that claims PASS under InferRSI's evidence framework
diff --git a/src/inferrsi/data/skill_library/methods/inference-benchmark-design/metadata.json b/src/inferrsi/data/skill_library/methods/inference-benchmark-design/metadata.json
index e6ea1ff3b..d9ddd38ad 100644
--- a/src/inferrsi/data/skill_library/methods/inference-benchmark-design/metadata.json
+++ b/src/inferrsi/data/skill_library/methods/inference-benchmark-design/metadata.json
@@ -17,7 +17,11 @@
"stream-boundaries",
"treatment-delivery",
"trial-validity",
- "protocol-audit"
+ "protocol-audit",
+ "trial-evidence",
+ "result-origin",
+ "oracle-boundary",
+ "candidate-selection"
],
"status": "candidate",
"profile": "local-skill-v1",
@@ -237,14 +241,61 @@
"Tables 1-7"
],
"readset": "references/autotunebench-trial-validity.md"
+ },
+ {
+ "type": "git",
+ "url": "https://github.com/IntelLabs/Xe-Forge",
+ "commit": "6cd3ee98dfe32746b345a6abe521fa4cb9bdc187",
+ "paths": [
+ "CONTRIBUTING.md",
+ "LICENSE",
+ "README.md",
+ "docs/CORRECTNESS.md",
+ "docs/KERNEL_REPO.md",
+ "pyproject.toml",
+ "src/xe_forge/claude/generator.py",
+ "src/xe_forge/claude/templates/CLAUDE.md.j2",
+ "src/xe_forge/cli.py",
+ "src/xe_forge/core/trial_manager.py",
+ "src/xe_forge/engines/claude_engine.py",
+ "src/xe_forge/external.py",
+ "src/xe_forge/skills/__init__.py",
+ "src/xe_forge/skills/benchmark.py",
+ "src/xe_forge/skills/trial.py",
+ "src/xe_forge/skills/upstream.py",
+ "tests/test_benchmark_gate.py",
+ "tests/test_trial_manager_ranking.py"
+ ],
+ "readset": "references/xeforge-source.json",
+ "license": "Apache-2.0 repository default; DCO and curated-example exclusions retained",
+ "scope": "Selected source-bound trial origin/comparison identity, host outcomes, measured-only selection and baseline-oracle contracts; source-only, no execution"
+ },
+ {
+ "type": "paper",
+ "id": "arxiv:2605.26118",
+ "version": "v1",
+ "url": "https://arxiv.org/html/2605.26118v1",
+ "sections": [
+ "Abstract",
+ "I-VIII",
+ "References",
+ "Appendix A",
+ "Tables 1-3",
+ "Algorithm 1",
+ "Listing 1",
+ "Figure captions 1-15"
+ ],
+ "readset": "references/xeforge-source.json",
+ "license": "CC-BY-4.0",
+ "scope": "Complete HTML text/appendix and captions; historical author-reported context, unused graphic values remain unverified"
}
],
"empirical_validation": "not_run",
"applicability": {
- "scope": "Selecting task quality gates, reference parity checks and performance workloads for text, agentic coding, work agents, cache-aware ASR, TTS, full-duplex audio/video, image and video inference, and designing goodput-based multi-regime comparisons that fit InferRSI's evidence trail; interpreting treatment delivery, arm validity and stated-versus-observed protocol enforcement in supplied tuning reports",
+ "scope": "Selecting task quality gates, reference parity checks and performance workloads for text, agentic coding, work agents, cache-aware ASR, TTS, full-duplex audio/video, image and video inference, and designing goodput-based multi-regime comparisons that fit InferRSI's evidence trail; interpreting treatment delivery, arm validity and stated-versus-observed protocol enforcement in supplied tuning reports; interpreting source-bound kernel trial origin, host evaluator outcomes, unresolved performance and measured-only versus manual candidate selection",
"prerequisites": "The primary objective, timing boundary, quality gates, sample/failure accounting, required regimes, repetitions, seeds and decision rule are frozen before optimization; baseline and candidate share hardware, software stack, input distribution, benchmark configuration, warmup and measurement protocol, and on a shared machine also one time window and dedicated devices; cache-aware ASR also requires the selected model/config and first/steady geometry, decoded clock and reset/EOU/EOF boundaries to be established",
- "input_contract": "The task family and deployment use case; candidate quality evaluators and reference parity; the declared SLO and the caller's policy on which regimes must improve or must not regress; for an audit, a supplied fixed-workload report with request-to-trial grouping, exclusion and failure counts and the declared aggregation rule; for a treatment audit, the frozen delivery/arm-validity rules, run/candidate identities, feedback and consumer-input evidence, and per-arm raw records",
- "produced_artifact": "A frozen benchmark design with evaluators, reference parity, primary objective, timing boundary, quality gates, required regimes, repetition and seed rules and an explicit decision config, plus the evidence-tree layout a PASS claim must produce; for a supplied report, the computed threshold result and missing evidence. Candidate knowledge, not qualification of any model or backend; for a treatment audit, a contract-bound eligibility and interpretation report separating treatment exposure, observed checks, comparator identity, anomaly disposition and source conflicts",
+ "input_contract": "The task family and deployment use case; candidate quality evaluators and reference parity; the declared SLO and the caller's policy on which regimes must improve or must not regress; for an audit, a supplied fixed-workload report with request-to-trial grouping, exclusion and failure counts and the declared aggregation rule; for a treatment audit, the frozen delivery/arm-validity rules, run/candidate identities, feedback and consumer-input evidence, and per-arm raw records; for a kernel trial audit, complete saved candidate bytes and IDs, baseline/spec/reference/variant identities, result-origin fields, raw host outcome and return code, named gate and persisted ratio, actual oracle and the selecting/delivering caller",
+ "produced_artifact": "A frozen benchmark design with evaluators, reference parity, primary objective, timing boundary, quality gates, required regimes, repetition and seed rules and an explicit decision config, plus the evidence-tree layout a PASS claim must produce; for a supplied report, the computed threshold result and missing evidence. Candidate knowledge, not qualification of any model or backend; for a treatment audit, a contract-bound eligibility and interpretation report separating treatment exposure, observed checks, comparator identity, anomaly disposition and source conflicts; for a kernel trial audit, a source-bound interpretation separating artifact/cohort identity, origin, oracle, performance resolution and selected-versus-delivered eligibility, without promoting kernel parity into a gain or whole-model acceptance",
"failure_modes": [
"Raw throughput is optimized in place of goodput, so requests served outside the SLO count toward a win",
"One concurrency level or one undisclosed aggregate score stands in for all required regimes",
@@ -256,16 +307,20 @@
"A cache-aware ASR EOU is treated as EOF or full reset, nominal chunk duration as the decoded mel frontier, or shape-only geometry PASS as a native model-state test",
"An enabled treatment or stored feedback summary is taken as proof of delivery to the next eligible consumer",
"A failed arm-validity condition is overridden by a favorable best timing or a saturation/null interpretation",
- "Complete gate keys or zero recorded failures are read as proof that every declared protocol check ran"
+ "Complete gate keys or zero recorded failures are read as proof that every declared protocol check ran",
+ "A tool-origin measured marker or completed status is treated as a resolved performance gain",
+ "A displayed/manual best, baseline copy or edited candidate is reported as the eligible measured delivery",
+ "Ratio omission alone is assumed to clear an earlier ratio, or baseline agreement is treated as independent semantic correctness"
],
- "refusal_point": "Records missing coverage and high-variance results as INCONCLUSIVE rather than a win; a run without a frozen RunSpec, or whose validator changed after the plan was frozen, is INCONCLUSIVE regardless of metric values; sets no universal numeric gate or noise threshold; withholds causal treatment benefit/null conclusions when required delivery or arm eligibility is unverified, and preserves conflicts between stated protocol, exported code and source reports"
+ "refusal_point": "Records missing coverage and high-variance results as INCONCLUSIVE rather than a win; a run without a frozen RunSpec, or whose validator changed after the plan was frozen, is INCONCLUSIVE regardless of metric values; sets no universal numeric gate or noise threshold; withholds causal treatment benefit/null conclusions when required delivery or arm eligibility is unverified, and preserves conflicts between stated protocol, exported code and source reports; withholds a kernel gain for unresolved performance or an unbound comparison and identifies missing independent semantic evidence when only baseline agreement is available"
},
"recommendations": [
"Freeze one primary objective, timing boundary, quality gates and sample/failure accounting before optimization.",
"Choose the required regimes from the deployment use case, report each separately, and record which must improve or must not regress in a versioned decision config.",
"Use the replay trace that matches the actual deployment pattern.",
"State the concurrency, trace, model, SKU and microbenchmark scope boundaries in any report that cites benchmark results.",
- "Trace treatment to its eligible consumer and apply the frozen arm-validity precedence before attributing benefit, saturation or a null."
+ "Trace treatment to its eligible consumer and apply the frozen arm-validity precedence before attributing benefit, saturation or a null.",
+ "Bind the complete saved candidate and comparator cohort; keep result origin, actual oracle, named gate/ratio and delivered eligibility separate."
],
"limitations": [
"Source-derived candidate; no local efficacy validation.",
@@ -274,7 +329,8 @@
"Benchmark feasibility and package-consumption checks do not promote this candidate or replace task quality, repeated A/B and service qualification.",
"The pinned NeMo-Speech.cpp ASR reference covers selected source/test definitions and author-reported benchmark boundaries; native model/device, decoder internals, quality, long-audio/load and service behavior remain not_run.",
"JustGoal contributes source-only controlled-evaluation and kernel-acceptance guidance; its repaired/retested timings, released-pass counts and protocol differences are author-reported, not locally reproduced or a complete campaign runner.",
- "The AutoTuneBench reference is source-only: original operational checkpoint/prompt receipts remain unavailable, source contradictions remain explicit, and no tuning, device/performance or agent-efficacy validation was run."
+ "The AutoTuneBench reference is source-only: original operational checkpoint/prompt receipts remain unavailable, source contradictions remain explicit, and no tuning, device/performance or agent-efficacy validation was run.",
+ "The Xe-Forge reference is source-only and limited to inspected host/manual/Claude trial paths; named-verdict update predicates and caller defaults remain explicit. Native tests, backend/model/quality/performance/service behavior and agent efficacy were not evaluated, and source/package checks do not promote whole-model support."
],
"provenance_readsets": [
"references/task-benchmark-selection.md",
@@ -283,7 +339,9 @@
"references/justgoal-evaluation-contracts.md",
"references/justgoal-source.json",
"references/autotunebench-trial-validity.md",
- "references/autotunebench-source.json"
+ "references/autotunebench-source.json",
+ "references/xeforge-trial-evidence.md",
+ "references/xeforge-source.json"
],
"references": [
"../inference-optimization-casebook/cases/admission-drain-occupancy.md",
diff --git a/src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/xeforge-source.json b/src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/xeforge-source.json
new file mode 100644
index 000000000..9aa863ce0
--- /dev/null
+++ b/src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/xeforge-source.json
@@ -0,0 +1,464 @@
+{
+ "record_type": "source_readset",
+ "title": "Xe-Forge repository and paired paper: trial identity, evaluator evidence and selection",
+ "owner": "inference-benchmark-design",
+ "content": "xeforge-trial-evidence.md",
+ "source_state": "source_derived_candidate",
+ "inspected_on": "2026-11-02",
+ "repository": {
+ "url": "https://github.com/IntelLabs/Xe-Forge",
+ "commit": "6cd3ee98dfe32746b345a6abe521fa4cb9bdc187",
+ "tree": "b7b393353055962bae473c13b60669db8538cd45",
+ "declared_version": "0.4.0 in pyproject.toml; not an installed runtime observation",
+ "license": "Apache-2.0",
+ "selected_file_count": 18,
+ "files": [
+ {
+ "path": "CONTRIBUTING.md",
+ "git_blob": "3b253e011739bfd1437876e533e694a7a9991e3b",
+ "sha256": "13a7147447cf0063cf52c2db378a7e849afbac73d0c66ba98eac64976fff4fd5",
+ "bytes": 2589,
+ "url": "https://github.com/IntelLabs/Xe-Forge/blob/6cd3ee98dfe32746b345a6abe521fa4cb9bdc187/CONTRIBUTING.md",
+ "inspected_line_ranges": [
+ [
+ 1,
+ 79
+ ]
+ ],
+ "license": "Apache-2.0 repository default",
+ "redistributed": false,
+ "rights_note": "Embeds the Linux Foundation DCO 1.1 verbatim-copy notice; no DCO text is redistributed."
+ },
+ {
+ "path": "LICENSE",
+ "git_blob": "261eeb9e9f8b2b4b0d119366dda99c6fd7d35c64",
+ "sha256": "c71d239df91726fc519c6eb72d318ec65820627232b2f796219e87dcf35d0ab4",
+ "bytes": 11357,
+ "url": "https://github.com/IntelLabs/Xe-Forge/blob/6cd3ee98dfe32746b345a6abe521fa4cb9bdc187/LICENSE",
+ "inspected_line_ranges": [
+ [
+ 1,
+ 201
+ ]
+ ],
+ "license": "Apache-2.0 repository default",
+ "redistributed": false
+ },
+ {
+ "path": "README.md",
+ "git_blob": "3c1f2109de129152cb4a032777dacc5318c4d509",
+ "sha256": "14cacb884bf566d9363a84d8b05457b8fc6f8c5f054618b469870e6359410f39",
+ "bytes": 30880,
+ "url": "https://github.com/IntelLabs/Xe-Forge/blob/6cd3ee98dfe32746b345a6abe521fa4cb9bdc187/README.md",
+ "inspected_line_ranges": [
+ [
+ 1,
+ 80
+ ],
+ [
+ 217,
+ 235
+ ],
+ [
+ 735,
+ 777
+ ]
+ ],
+ "license": "Apache-2.0 repository default",
+ "redistributed": false
+ },
+ {
+ "path": "docs/CORRECTNESS.md",
+ "git_blob": "30ce56dbac047f577aff350bda00fb0df1e0f3fa",
+ "sha256": "a1a8ec8d0ad8cb8a18450f3709d20822712a30814df297bb4d6b22d543baf965",
+ "bytes": 3497,
+ "url": "https://github.com/IntelLabs/Xe-Forge/blob/6cd3ee98dfe32746b345a6abe521fa4cb9bdc187/docs/CORRECTNESS.md",
+ "inspected_line_ranges": [
+ [
+ 1,
+ 49
+ ]
+ ],
+ "license": "Apache-2.0 repository default",
+ "redistributed": false
+ },
+ {
+ "path": "docs/KERNEL_REPO.md",
+ "git_blob": "adbf75d5a4a41788d0aa2b6057e80ea501581578",
+ "sha256": "dad3ae4909875ea1f8c93a037120ac16f2f2ec254f618bd9bf2d7580d0b54cb1",
+ "bytes": 3686,
+ "url": "https://github.com/IntelLabs/Xe-Forge/blob/6cd3ee98dfe32746b345a6abe521fa4cb9bdc187/docs/KERNEL_REPO.md",
+ "inspected_line_ranges": [
+ [
+ 1,
+ 88
+ ]
+ ],
+ "license": "Apache-2.0 repository default",
+ "redistributed": false
+ },
+ {
+ "path": "pyproject.toml",
+ "git_blob": "420904782abb5f3161b3effd3a2006d63aea7520",
+ "sha256": "0f0eba02032ff5e4f389c99195548b95a870be5f53ec76e4e5b9fb6bd63141be",
+ "bytes": 2303,
+ "url": "https://github.com/IntelLabs/Xe-Forge/blob/6cd3ee98dfe32746b345a6abe521fa4cb9bdc187/pyproject.toml",
+ "inspected_line_ranges": [
+ [
+ 1,
+ 108
+ ]
+ ],
+ "license": "Apache-2.0 repository default",
+ "redistributed": false
+ },
+ {
+ "path": "src/xe_forge/claude/generator.py",
+ "git_blob": "39cca38bbdaa854c9d88a795c2cf36689e9622c3",
+ "sha256": "f6552181df7eed367c8a1ef0b6266f2701473d369783697550d6e53dac319f5c",
+ "bytes": 12744,
+ "url": "https://github.com/IntelLabs/Xe-Forge/blob/6cd3ee98dfe32746b345a6abe521fa4cb9bdc187/src/xe_forge/claude/generator.py",
+ "inspected_line_ranges": [
+ [
+ 1,
+ 332
+ ]
+ ],
+ "license": "Apache-2.0 repository default",
+ "redistributed": false
+ },
+ {
+ "path": "src/xe_forge/claude/templates/CLAUDE.md.j2",
+ "git_blob": "f10f5aa691420310a747525426aa8aa6329eff6c",
+ "sha256": "4d7f2ec02d4adccf07746a0006b787369569a7c50b8294258de6226e706904e9",
+ "bytes": 35125,
+ "url": "https://github.com/IntelLabs/Xe-Forge/blob/6cd3ee98dfe32746b345a6abe521fa4cb9bdc187/src/xe_forge/claude/templates/CLAUDE.md.j2",
+ "inspected_line_ranges": [
+ [
+ 1,
+ 100
+ ],
+ [
+ 323,
+ 470
+ ]
+ ],
+ "license": "Apache-2.0 repository default",
+ "redistributed": false
+ },
+ {
+ "path": "src/xe_forge/cli.py",
+ "git_blob": "8259b9681b6e1df168d342bbb7dc911939a4381b",
+ "sha256": "024165a47c11d48100f490da3c1ab95f68c28830a177e3dba781cce319c0e1ce",
+ "bytes": 27264,
+ "url": "https://github.com/IntelLabs/Xe-Forge/blob/6cd3ee98dfe32746b345a6abe521fa4cb9bdc187/src/xe_forge/cli.py",
+ "inspected_line_ranges": [
+ [
+ 270,
+ 485
+ ],
+ [
+ 511,
+ 741
+ ]
+ ],
+ "license": "Apache-2.0 repository default",
+ "redistributed": false
+ },
+ {
+ "path": "src/xe_forge/core/trial_manager.py",
+ "git_blob": "ff59d673b5f3362bab1fa5a925fd580f51d57952",
+ "sha256": "8de74c960bb4c03d59a8f7557fe84b055cab2dd4bb8c4369883578be363269d6",
+ "bytes": 25461,
+ "url": "https://github.com/IntelLabs/Xe-Forge/blob/6cd3ee98dfe32746b345a6abe521fa4cb9bdc187/src/xe_forge/core/trial_manager.py",
+ "inspected_line_ranges": [
+ [
+ 1,
+ 591
+ ]
+ ],
+ "license": "Apache-2.0 repository default",
+ "redistributed": false
+ },
+ {
+ "path": "src/xe_forge/engines/claude_engine.py",
+ "git_blob": "011491b891959e2596352617f42d17691fb77cdc",
+ "sha256": "e798528170a77e3bf21a93fad13de1e241d32ae438f7a8759f2917b6a606e32c",
+ "bytes": 9338,
+ "url": "https://github.com/IntelLabs/Xe-Forge/blob/6cd3ee98dfe32746b345a6abe521fa4cb9bdc187/src/xe_forge/engines/claude_engine.py",
+ "inspected_line_ranges": [
+ [
+ 1,
+ 230
+ ]
+ ],
+ "license": "Apache-2.0 repository default",
+ "redistributed": false
+ },
+ {
+ "path": "src/xe_forge/external.py",
+ "git_blob": "5fdc0139461fa464b6952016fedbecf324eec90b",
+ "sha256": "4a31227f24a83ee2a4b67b71918a2d0af0a3082cd36b7149c587fe978cfbe308",
+ "bytes": 6971,
+ "url": "https://github.com/IntelLabs/Xe-Forge/blob/6cd3ee98dfe32746b345a6abe521fa4cb9bdc187/src/xe_forge/external.py",
+ "inspected_line_ranges": [
+ [
+ 1,
+ 188
+ ]
+ ],
+ "license": "Apache-2.0 repository default",
+ "redistributed": false
+ },
+ {
+ "path": "src/xe_forge/skills/__init__.py",
+ "git_blob": "1ceb708723bb333ef05fa4bd99039e24862cf329",
+ "sha256": "d9ace36ca41d8a70fa02e49bda8198ff10ebbec86680dd639a4cec7c28d3f679",
+ "bytes": 10058,
+ "url": "https://github.com/IntelLabs/Xe-Forge/blob/6cd3ee98dfe32746b345a6abe521fa4cb9bdc187/src/xe_forge/skills/__init__.py",
+ "inspected_line_ranges": [
+ [
+ 1,
+ 146
+ ]
+ ],
+ "license": "Apache-2.0 repository default",
+ "redistributed": false
+ },
+ {
+ "path": "src/xe_forge/skills/benchmark.py",
+ "git_blob": "13f12f89b8dcbc7ad976ef9f6bb4da3145bc6e5e",
+ "sha256": "a2b7f643399173b546ebc38a8c40cf7e338db854bf5942f019d6077596a043cf",
+ "bytes": 18724,
+ "url": "https://github.com/IntelLabs/Xe-Forge/blob/6cd3ee98dfe32746b345a6abe521fa4cb9bdc187/src/xe_forge/skills/benchmark.py",
+ "inspected_line_ranges": [
+ [
+ 1,
+ 463
+ ]
+ ],
+ "license": "Apache-2.0 repository default",
+ "redistributed": false
+ },
+ {
+ "path": "src/xe_forge/skills/trial.py",
+ "git_blob": "c25d35dc106c02365321bdaa17739dbbb69d4864",
+ "sha256": "e7c6437a3c54a091750f1b88ed743776531dac7e6bbd03fbb879a530bd59dca3",
+ "bytes": 3911,
+ "url": "https://github.com/IntelLabs/Xe-Forge/blob/6cd3ee98dfe32746b345a6abe521fa4cb9bdc187/src/xe_forge/skills/trial.py",
+ "inspected_line_ranges": [
+ [
+ 1,
+ 100
+ ]
+ ],
+ "license": "Apache-2.0 repository default",
+ "redistributed": false
+ },
+ {
+ "path": "src/xe_forge/skills/upstream.py",
+ "git_blob": "ac46ebafc4e12481a16b3e7725909f321522aee7",
+ "sha256": "36b642cef79d4e5688f33d3d1f0dcf16ea0d5fb3f2edc65641adee55d8aa982a",
+ "bytes": 7313,
+ "url": "https://github.com/IntelLabs/Xe-Forge/blob/6cd3ee98dfe32746b345a6abe521fa4cb9bdc187/src/xe_forge/skills/upstream.py",
+ "inspected_line_ranges": [
+ [
+ 1,
+ 168
+ ]
+ ],
+ "license": "Apache-2.0 repository default",
+ "redistributed": false
+ },
+ {
+ "path": "tests/test_benchmark_gate.py",
+ "git_blob": "ed3c921f838cc7efe27c5cac969910415a464cb9",
+ "sha256": "2acf13fd304c4fdb21a32b529fd1d9428283a9d52340372585f3d3ecbe9faf8e",
+ "bytes": 34821,
+ "url": "https://github.com/IntelLabs/Xe-Forge/blob/6cd3ee98dfe32746b345a6abe521fa4cb9bdc187/tests/test_benchmark_gate.py",
+ "inspected_line_ranges": [
+ [
+ 764,
+ 785
+ ]
+ ],
+ "license": "Apache-2.0 repository default",
+ "redistributed": false,
+ "read_scope": "AST definition inventory and the listed assertion bodies only; not executed"
+ },
+ {
+ "path": "tests/test_trial_manager_ranking.py",
+ "git_blob": "42676685a0e1959f95c703619d2eeb44d062e3ee",
+ "sha256": "e2972a7f7671aac8ab10649d3484d2acb07a3febb1a599a33a775d619ec3f824",
+ "bytes": 11276,
+ "url": "https://github.com/IntelLabs/Xe-Forge/blob/6cd3ee98dfe32746b345a6abe521fa4cb9bdc187/tests/test_trial_manager_ranking.py",
+ "inspected_line_ranges": [
+ [
+ 1,
+ 99
+ ],
+ [
+ 203,
+ 283
+ ]
+ ],
+ "license": "Apache-2.0 repository default",
+ "redistributed": false,
+ "read_scope": "AST definition inventory and the listed assertion bodies only; not executed"
+ }
+ ]
+ },
+ "paper": {
+ "type": "paper",
+ "id": "arxiv:2605.26118",
+ "version": "v1",
+ "title": "Xe-Forge: Multi-Stage LLM-Powered Kernel Optimization for Intel GPU",
+ "authors": [
+ "Marcin Spoczynski",
+ "Daniel Fleischer",
+ "Moshe Berchansky",
+ "Gabriela Ben-Melech Stan",
+ "Shira Guskin",
+ "Weilin Xu",
+ "Adam Siemieniuk",
+ "Alexander Heinecke"
+ ],
+ "url": "https://arxiv.org/html/2605.26118v1",
+ "license": "CC-BY-4.0",
+ "retained_format": "HTML",
+ "sha256": "37178e7c0d8831d5ba31ac7db2b35c471f5b6386d2bdde28786cb96b4c7a6121",
+ "bytes": 346924,
+ "abstract_page": {
+ "url": "https://arxiv.org/abs/2605.26118v1",
+ "sha256": "b0da56776af1ee739e462f0d8d35b406d4bd767715ac7d5a7299c9bd4c646d76",
+ "bytes": 43183
+ },
+ "inspected_sections": [
+ "Complete HTML body: abstract, Sections I-VIII, References, Appendix A",
+ "Tables 1-3, Algorithm 1, Listing 1, captions of Figures 1-15"
+ ],
+ "graphic_scope": "Figure 1 SVG bytes retained; Figure 2 SVG acquisition failed with a TLS connection reset, and Figures 3-15 were not attempted afterward. Their graphical values are unverified and unused. All captions were read.",
+ "redistributed": false
+ },
+ "retention": {
+ "archive_url": "https://codeload.github.com/IntelLabs/Xe-Forge/zip/6cd3ee98dfe32746b345a6abe521fa4cb9bdc187",
+ "archive_sha256": "32fd487f263f28a59077f25a296ec8d9dc1c0d3c5868c562b515c5921d5519b9",
+ "archive_bytes": 1726733,
+ "complete_tree_entries": 268,
+ "complete_tree_blobs": 224,
+ "blob_check": "Every retained archive blob matches the pinned complete Git tree SHA and size. Symlinks are retained as Git link-text bytes without following them.",
+ "read_boundary": "Only the 18 selected files and listed line ranges support this procedure; retaining the full tree does not mean every body was inspected."
+ },
+ "rights_dispositions": [
+ "The complete pinned root LICENSE is Apache-2.0; README lines 775-777 declare it. The selected files contain no narrower code-license header found by the full-tree text/notice scan.",
+ "No repository NOTICE or THIRD_PARTY_NOTICES file is present in the pinned tree. CONTRIBUTING embeds the Linux Foundation DCO 1.1 with its verbatim-copy condition; that text is not adapted or redistributed.",
+ "The paper HTML and abstract page declare CC BY 4.0. This reference attributes the authors and adapts methodology through original interpretation without copying paper prose or figures. The paper retains its Intel trademark footnote; no trademark asset is redistributed.",
+ "README line 735 attributes curated examples to KernelBench and Intel XPU Triton benchmarks. No transitive rights conclusion is made for those kernels, and none are redistributed.",
+ "Source snapshots remain construction evidence outside the packaged library. The contribution contains original analysis, identities, hashes and links; no upstream code, kernels, datasets, plots, SVG, paper prose, DCO or raw benchmark output is copied."
+ ],
+ "source_observations": [
+ {
+ "scope": "trial_manager.py 19-72, 140-225, 286-378, 466-587; benchmark.py 344-405",
+ "observation": "Saved source bytes, tool-origin versus reported records, supplied comparator map, first correctness-pass pin, selection keys and measured-only candidate filtering are distinct contracts."
+ },
+ {
+ "scope": "external.py 69-188; benchmark.py 45-116, 318-341",
+ "observation": "ExternalResult.measured means ratio presence; the trial source marker means tool origin. Final stdout DONE framing, parsed host fields and retained return code do not establish a calibrated independent evaluator."
+ },
+ {
+ "scope": "skills/trial.py 43-100; skills/__init__.py 105-141; engines/claude_engine.py 69-140; cli.py 707-740; skills/upstream.py 69-161",
+ "observation": "Manual finalize defaults to no measured-only requirement; the inspected Claude result consumer uses best_measured and keepable. Named-gate parity can be retained without a numeric gain; top-level success and patch output have narrower meanings than performance or integration acceptance."
+ },
+ {
+ "scope": "docs/CORRECTNESS.md; docs/KERNEL_REPO.md; cli.py 630-665; claude/generator.py 87-115; skills/benchmark.py 216-229",
+ "observation": "Host, explicit/sibling reference and baseline-only oracle paths differ; input suffix routing and generated benchmark options determine which one is selected."
+ }
+ ],
+ "deductions": [
+ {
+ "scope": "trial_manager.py 361-365; benchmark.py 338-340",
+ "deduction": "Named-verdict remeasurement without a ratio clears an earlier ratio. Ratio omission alone can leave it because UNSPECIFIED is discarded before persistence. This was not executed as a failure."
+ },
+ {
+ "scope": "benchmark.py 372-381; trial_manager.py 324-340",
+ "deduction": "The comparison map does not cover device, toolchain, host command or timer identity, and its first-pass predicate is not a complete successful-timing gate."
+ },
+ {
+ "scope": "docs/CORRECTNESS.md 42-49",
+ "deduction": "Baseline agreement, including a reference derived from that baseline, cannot independently detect an existing semantic bug or promote whole-model correctness."
+ }
+ ],
+ "author_reports": "The paired paper supplies historical CoVeR/staged-pipeline, Intel GPU evaluation and limitation context. It does not establish that the inspected later host/trial path produced those results. Its measurements, README kernel-family reports and architectural containment statements are not locally reproduced observations.",
+ "native_candidates": {
+ "execution": "not_run",
+ "tests/test_trial_manager_ranking.py": [
+ "test_gated_trial_outranks_a_measured_regression",
+ "test_a_gated_trial_records_no_speedup",
+ "test_finalize_keeps_parity",
+ "test_the_claude_engine_returns_no_reported_win_baseline_copy_or_edited_trial",
+ "test_a_gated_re_measurement_clears_the_earlier_ratio"
+ ],
+ "tests/test_benchmark_gate.py": [
+ "test_a_speedup_without_both_times_is_refused"
+ ],
+ "scope": "Source definition inventory and selected assertion reads only; no native test, fake host acceptance or backend result was executed or synthesized."
+ },
+ "excluded_areas": [
+ {
+ "paths": [
+ "assets/",
+ "plots/"
+ ],
+ "reason": "Logos, trademarks and performance graphics are retained source assets, not redistributed or used to reconstruct gains."
+ },
+ {
+ "paths": [
+ "examples/",
+ "test_kernels/",
+ "templates/",
+ "knowledge_base/"
+ ],
+ "reason": "Curated kernel implementations, examples, tuning patterns and their transitive rights/runtime behavior are outside the interpretation procedure; no code is copied."
+ },
+ {
+ "paths": [
+ "src/xe_forge/agents/",
+ "src/xe_forge/planner.py",
+ "src/xe_forge/pipeline.py",
+ "src/xe_forge/engines/agent_engine.py",
+ "src/xe_forge/engines/dspy_engine.py"
+ ],
+ "reason": "Other engine, planner and optimization algorithms are not claimed to implement the inspected Claude/manual measured-only contract."
+ },
+ {
+ "paths": [
+ "src/xe_forge/core/executor.py",
+ "src/xe_forge/core/sycl_executor.py",
+ "src/xe_forge/core/profiler.py",
+ "src/xe_forge/core/tile_search/",
+ "external AI Bench implementation"
+ ],
+ "reason": "Numerical execution, build/profiler and hardware behavior are not audited or executed. The selected caller checks are source observations only."
+ },
+ {
+ "paths": [
+ "remaining CLI/template regions",
+ "remaining tests",
+ "scripts/",
+ ".github/",
+ ".env.example"
+ ],
+ "reason": "Only declared inspected regions support claims; no broader runtime, packaging, security or source-test audit is implied."
+ }
+ ],
+ "verification_boundaries": {
+ "source_blob_integrity": "pinned retained-byte equality",
+ "source_tests": "not_run",
+ "upstream_install": "not_run",
+ "backend_device_model": "not_run",
+ "numerical_quality": "not_run",
+ "performance_service": "not_run",
+ "agent_efficacy": "not_evaluated",
+ "promotion": "Candidate; no runtime integration or InferRSI PASS. Paper future work and referenced draft extensions are not delivered capabilities."
+ }
+}
diff --git a/src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/xeforge-trial-evidence.md b/src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/xeforge-trial-evidence.md
new file mode 100644
index 000000000..44fcd5d94
--- /dev/null
+++ b/src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/xeforge-trial-evidence.md
@@ -0,0 +1,159 @@
+# Xe-Forge: trial identity, evaluator evidence and candidate selection
+
+Status: source-derived candidate; empirical validation not_run. The ordinary
+[source record](xeforge-source.json) retains the paired repository/paper,
+inspected regions, hashes, rights and exclusions. This reference interprets
+supplied records; it adds no optimizer, evaluator or runtime integration.
+
+Use it when a kernel-agent report identifies a best trial, delegates measurement
+to a host command, or treats a retained candidate as a measured improvement.
+Keep the parent benchmark method's workload, independent acceptance, timing and
+RunSpec controls. The source-specific record below does not replace them.
+
+## Bind the saved artifact and comparison
+
+Recover the complete saved candidate, its trial ID/parent, result origin and
+measurement record. A source directory is one trial: retain all its files and
+relative paths, rather than an entry point combined with baseline companions.
+Xe-Forge hashes these bytes and checks that the benchmark's candidate matches
+the saved trial.
+
+Recover the recorder's `baseline_sha256`, `spec_sha256`, `reference_sha256` and
+`variant` map. On the benchmark caller path, the first tool-recorded outcome
+whose correctness is `pass` pins this map; an initial failed outcome does not.
+Later incompatible maps are refused. This predicate does not require a complete
+timing or a zero exit status. The API accepts a supplied map without checking
+that its caller selected `source="measured"`; the ordinary `trial result` CLI
+supplies no map and uses the default `reported` origin.
+
+The map does not include the device, compiler/toolchain, host command or timer.
+Retain those identities under the campaign's existing comparison contract.
+Equal source hashes alone do not establish an equivalent measurement environment.
+
+Sources: [saved bytes and digest](https://github.com/IntelLabs/Xe-Forge/blob/6cd3ee98dfe32746b345a6abe521fa4cb9bdc187/src/xe_forge/core/trial_manager.py#L19),
+[record persistence](https://github.com/IntelLabs/Xe-Forge/blob/6cd3ee98dfe32746b345a6abe521fa4cb9bdc187/src/xe_forge/core/trial_manager.py#L286),
+[benchmark caller and comparison map](https://github.com/IntelLabs/Xe-Forge/blob/6cd3ee98dfe32746b345a6abe521fa4cb9bdc187/src/xe_forge/skills/benchmark.py#L344).
+
+## Separate result origin, correctness and resolution
+
+| Source field or observation | What it means | What it does not establish |
+| --- | --- | --- |
+| Trial `source="measured"` | The benchmark tool recorded the outcome it printed. A later `trial result` write marks the record `reported` again. | A resolved ratio, independent oracle or calibrated timer. |
+| `ExternalResult.measured` | The external result contains a non-None `speedup`. This is a different meaning of measured. | Tool-origin qualification of a saved trial or a complete accepted measurement. |
+| `correctness="pass"` | A recorded pass assertion for the supplied workload. A reported write can supply it without invoking an oracle; establish oracle acceptance from the actual result origin and evaluator receipt. | Independent oracle validation, correctness of a baseline-only oracle or all valid inputs. |
+| Trial `status="completed"` | The record can be ranked, including a pass-marked outcome with both times and no ratio. | A performance win or an InferRSI PASS. |
+
+The host protocol supplies correctness, baseline/trial times, an optional
+speedup, timer description and named verdict, ending with `DONE`. The adapter
+requires `DONE` as the last nonempty stdout line. It parses the combined stdout
+and stderr and retains the process return code. This framing does not validate
+the host's input domain, numerical oracle, calibration or exit success.
+
+The benchmark wrapper rejects missing correctness and rejects a supplied ratio
+without both times. Preserve the raw host output, return code, timer and gate
+with the persisted record. A successful parse or a tool-origin marker cannot
+substitute for the actual evaluator contract.
+
+Sources: [host protocol, result fields and parser](https://github.com/IntelLabs/Xe-Forge/blob/6cd3ee98dfe32746b345a6abe521fa4cb9bdc187/src/xe_forge/external.py#L21),
+[wrapper checks and reporting](https://github.com/IntelLabs/Xe-Forge/blob/6cd3ee98dfe32746b345a6abe521fa4cb9bdc187/src/xe_forge/skills/benchmark.py#L45).
+
+## Keep selection parity separate from a measured gain
+
+Xe-Forge excludes a record from ranking when correctness is not `pass` or
+validation is `fail`. A missing validation result is not rejected by that
+predicate; rankability alone does not prove static validation ran.
+
+For a rankable record, its resolved ratio determines order when present.
+When both times are present and the ratio is absent, the source ranks it at
+parity. This keeps an unresolved comparison above a measured regression. A
+resolved parity result wins a tie against unresolved parity; time breaks further
+ties. The parity ordering key is not a measured `speedup=1.0` to publish.
+
+Inspect remeasurement updates before interpreting an absent ratio. When a named
+verdict arrives without a new ratio, `record_result` clears the previous ratio.
+However, `parse_outcome` discards `UNSPECIFIED`, and ratio omission without a
+named verdict does not trigger that clearing branch. Thus a previously stored
+ratio can remain. This is a deduction from the update predicates, not an
+executed failure. Check the actual stored gate/ratio together; do not assume
+that a new output line with no speedup removed an old one.
+
+The ranker uses field shape rather than a closed gate vocabulary. Do not infer
+that every named host verdict means a calibrated, harmless timing floor. Keep
+the host's actual decision and any execution failure separate from selection.
+
+Sources: [ordering](https://github.com/IntelLabs/Xe-Forge/blob/6cd3ee98dfe32746b345a6abe521fa4cb9bdc187/src/xe_forge/core/trial_manager.py#L31),
+[conditional ratio clearing](https://github.com/IntelLabs/Xe-Forge/blob/6cd3ee98dfe32746b345a6abe521fa4cb9bdc187/src/xe_forge/core/trial_manager.py#L361),
+[printed-outcome parsing](https://github.com/IntelLabs/Xe-Forge/blob/6cd3ee98dfe32746b345a6abe521fa4cb9bdc187/src/xe_forge/skills/benchmark.py#L318).
+
+## Follow the actual winner through delivery and reporting
+
+Check which consumer selected the winner. Ordinary `best` uses the stored best
+record, and manual `trial finalize` defaults to `require_measured=False`.
+Measured-only selection additionally rejects reported records, baseline copies
+and candidate bytes changed after measurement. Generated workspace instructions
+request `finalize --require-measured`; the inspected Claude engine independently
+uses `best_measured` and the same keepability predicate. Do not apply that
+restriction to every engine or manual invocation.
+
+Finalization refuses a measured regression but allows parity, including a gated
+comparison. A multi-file winner is copied as a whole directory. For a fresh
+named-gate record, the inspected trial/finalization output says none, a gate or
+parity; Claude's result passes through the absent ratio, and the main CLI prints
+a numeric total only when that field is present/truthy. These observations do
+not remove the stale-ratio update limitation above.
+
+Retain the record when reading a summary: parity can return `success=True`,
+workspace generation without launching an optimizer also returns success, and
+the top-level result does not carry the stored gate verdict. Operation success
+does not establish a gain. An upstream patch/`PORT.txt` records a measured winner
+and checks touched Python bytecode, while other touched files are reported
+unbuilt; that output is not whole-repository or serving acceptance.
+
+Sources: [eligible candidates and finalize](https://github.com/IntelLabs/Xe-Forge/blob/6cd3ee98dfe32746b345a6abe521fa4cb9bdc187/src/xe_forge/core/trial_manager.py#L466),
+[manual CLI default](https://github.com/IntelLabs/Xe-Forge/blob/6cd3ee98dfe32746b345a6abe521fa4cb9bdc187/src/xe_forge/skills/trial.py#L77),
+[workspace's requested mode](https://github.com/IntelLabs/Xe-Forge/blob/6cd3ee98dfe32746b345a6abe521fa4cb9bdc187/src/xe_forge/claude/templates/CLAUDE.md.j2#L434),
+[Claude result consumer](https://github.com/IntelLabs/Xe-Forge/blob/6cd3ee98dfe32746b345a6abe521fa4cb9bdc187/src/xe_forge/engines/claude_engine.py#L69),
+[main result output](https://github.com/IntelLabs/Xe-Forge/blob/6cd3ee98dfe32746b345a6abe521fa4cb9bdc187/src/xe_forge/cli.py#L707),
+[port output](https://github.com/IntelLabs/Xe-Forge/blob/6cd3ee98dfe32746b345a6abe521fa4cb9bdc187/src/xe_forge/skills/upstream.py#L69).
+
+## Identify the oracle before promoting correctness
+
+| Oracle path | Interpretation |
+| --- | --- |
+| Host command | Recover the host evaluator's actual inputs, reference, numerical criteria, timer and revision. Packet fields delegate the decision; they do not independently verify it. |
+| Explicit or sibling PyTorch reference | The inspected built-in benchmark path checks baseline and trial against the supplied reference. Preserve its independent identity and workload coverage. |
+| Input/repository kernel without an independent reference | Agreement preserves baseline behavior and can preserve its existing bug. A reference derived from that same kernel does not supply independent semantics. |
+
+Trace argument routing rather than guessing from a filename's intent: a target
+DSL suffix makes `-i` the baseline, so a `.py` file supplied for Triton can be
+the baseline even when its contents are PyTorch. `--reference` overrides the
+sibling `_pytorch.py` lookup. Read the resulting reference/benchmark options
+and comparison record before assigning oracle authority.
+
+Return the eligible artifact/cohort, result origin, actual oracle, named gate
+and ratio state, and selected-versus-delivered identity. Withhold a gain when
+performance is unresolved or the comparison is unbound. Identify the missing
+independent semantic evidence when only baseline agreement is available. Whole
+model outputs, integration and service performance retain the parent method's
+separate acceptance requirements; a kernel result cannot promote them.
+
+Sources: [oracle modes and baseline limitation](https://github.com/IntelLabs/Xe-Forge/blob/6cd3ee98dfe32746b345a6abe521fa4cb9bdc187/docs/CORRECTNESS.md#L8),
+[input/reference routing](https://github.com/IntelLabs/Xe-Forge/blob/6cd3ee98dfe32746b345a6abe521fa4cb9bdc187/src/xe_forge/cli.py#L630),
+[generated benchmark options](https://github.com/IntelLabs/Xe-Forge/blob/6cd3ee98dfe32746b345a6abe521fa4cb9bdc187/src/xe_forge/claude/generator.py#L87).
+
+## Attribution and evidence limits
+
+This is original analysis of IntelLabs/Xe-Forge and Marcin Spoczynski et al.,
+*Xe-Forge: Multi-Stage LLM-Powered Kernel Optimization for Intel GPU*,
+[arXiv:2605.26118v1](https://arxiv.org/html/2605.26118v1). The repository declares
+Apache-2.0; the paper declares [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/).
+No source code, kernels, datasets, paper prose or figures are redistributed.
+Selected rights, attribution and exclusions remain in the source record.
+
+The paper's staged pipeline and evaluation are historical author reports, not
+proof that this pinned host/trial path produced those results. Its cross-kernel
+limitations and proposed model-graph extensions do not establish whole-model
+support; referenced draft extensions are not delivered capabilities. Unverified
+graphic values are unused here. Source tests, backend/device/model execution,
+quality, performance and service behavior were not run locally; agent efficacy
+was not evaluated. Source and package-reader checks do not establish those effects.