Proof, not popularity: find out whether your agent's skills, docs and AGENTS.md actually work.
Documentation: https://intel.github.io/dokimi/ — the full tour, with every figure.
Skills, instructions, docs, MCP servers and a repository's AGENTS.md are cheap
to write and easy to over-claim. Dokimi runs the same questions or coding tasks
with and without one change, grades both the same way, and reports the
difference with its p-value, per model. Then it shows which parts of a skill
the model already knew, which it added and which it broke, and proposes a
shorter version that keeps what matters.
dokimi — Greek δοκιμή, "test, proof". An artifact gets trusted because it passed a test that could have failed, not because it is popular.
Which parts help: novelty. Dokimi asks the model about each claim in a skill twice, without the skill and with it, and a different model grades both answers. Every claim lands in one of four outcomes (more):
What measuring shows so far (evidence): under lenient grading, 70% of what a skill says a frontier model already produces unprompted; under strict grading, which also checks exact values, 38% is still missing even with the skill in context; a plausible wrong value planted in a skill is repeated in 85–94% of cases in a small study; and what a small model needs, a large one may not, so every verdict is per model.
cd dokimi && pip install -e . # installs the `dokimi` command| You want to… | Start with | Then read |
|---|---|---|
| Check a skill | dokimi catalog scan --root <catalog> --kind skills (free) |
Reviewing a skill |
| Check a repository's agent setup | dokimi repo scan <repo> (free) |
Reviewing a repository |
| See which parts of a skill help | dokimi novelty analyze --artifact skill:<dir> --tier triage --estimate-only (free estimate) |
Content novelty |
| Compare with and without a change | dokimi arms run --arms baseline,skill:<dir> … |
Evaluating treatments |
| Write evals you can trust | the dokimi-design-evals skill |
External content |
Every step lists its cost; the free ones come first.
Coding agents. Asked to "use dokimi to review this skill" or "this
repository's agent setup"? Follow reviewing.md step
by step: it says which command to run, what each costs, and how to read the
result. dokimi --help lists every command. To change dokimi itself, read
AGENTS.md.
More: what Dokimi measures · why it exists · contributing · CLI reference
Licensed under the Apache License, Version 2.0; see NOTICE for attribution.