Skill2

Skills for your skills.
Full-lifecycle management for Agent Skill libraries.

Test and audit Agent Skills before shipping. Catch bad triggers, weak evidence, and packaging defects—locally.
Visualize usage and test status across your library, then surface evidence-backed cleanup candidates.

中文

Why Skill2

Writing one Agent Skill is easy. Maintaining twenty is harder.

As your library grows, three questions matter:

• Does it trigger when it should—and stay quiet when it should not?
• Does it improve the outcome?
• Should it stay, be revised, or enter cleanup review?

Skill2 treats Agent Skills as testable, auditable software units. Five focused Skills help agents create, test, audit, package, and visualize a library—while deterministic scripts keep evidence reproducible and local.

Install

Claude Code

/plugin marketplace add MisterBrookT/skill2
/plugin install skill2@skill2-marketplace

Installs five self-contained Skills.

Codex

npx skills add MisterBrookT/skill2 -g -a codex -y

Copies the five self-contained Skills for Codex.

Manual fallback

git clone https://github.com/MisterBrookT/skill2.git ~/.skill2 && ~/.skill2/install.sh

Copies Skills only (install.sh supports --dry-run and conflict-gated --force from a checkout). Requires Git. uv is needed only when a Skill runs its deterministic script. Skill scripts use uv run --script; first run may fetch declared dependencies into the uv cache; offline use requires a warm cache. Data stays local; no hosted service, telemetry, or PyPI install for users.

Five focused Skills

Skill	Agent uses it when
skill2-create	Creating, updating, or restructuring a skill.
skill2-test	Testing activation and outcome in isolation.
skill2-package	Packaging, documenting, and optionally publishing a Skill repository.
skill2-audit	Finding contract, safety, and behavior gaps.
skill2-visualize	Viewing inventory, direct calls, zero-use candidates, test status, and conservative lifecycle review candidates.

Try it

Ask the agent directly:

Create a project-level skill for this workflow.
Audit this skill library and show only evidence-backed findings.
Visualize which skills are called directly and which have zero direct calls.

Local-first evidence

Skill2 visualizes skill inventory and usage from local agent session logs. Data stays on your machine; prompts and transcripts are never included.

Design

Skills are the product; deterministic scripts support them. The repository dogfoods every rule it teaches. Package defaults to native distribution and adds artifact or release work only when requested. Visualize never changes a library.

Area	Prior art	Adopted
Skill format	Agent Skills spec, Anthropic Skills	Portable SKILL.md, progressive disclosure, owned resources.
Authoring	Superpowers, writing-skills	Skills-first structure, trigger-first descriptions, dogfood.
Evaluation	Superpowers evals, Tripwire, Waza, skill-eval, agent-skills-eval, skillci, skill-distill	Isolated runs, positive/negative routing, baseline, deterministic assertions.
Packaging	agent-scripts, awesome-copilot, scientific-agent-skills, superpowers-marketplace, Caveman, OpenAI Plugins	Idempotent installs, conflict gates, marketplace manifests, CI.

Skill2 thanks these projects and their maintainers. Their work shaped this repository's architecture and design principles.

See design and prior art.

Development

Contributor and CI use the checkout CLI. This is not a user install step:

uv sync
PYTHONPATH=src uv run python -m unittest discover -s tests
uv run ruff check .
uv run skill2 lint skills
uv run skill2 package-check .

MIT