Seth Hobson
91fe43e152
- Create CLAUDE.md with project conventions and PluginEval quick reference - Add docs/plugin-eval.md with complete framework documentation (layers, dimensions, scoring, anti-patterns, statistical methods, project structure) - Add PluginEval section to main README under What's New - Expand plugin-eval/README.md with quick start and command table
1.3 KiB
1.3 KiB
plugin-eval
Three-layer quality evaluation framework for Claude Code plugins.
Quick Start
cd plugins/plugin-eval
uv sync
# Evaluate a skill (static only, instant)
uv run plugin-eval score path/to/skill --depth quick
# Evaluate with LLM judge (~30s)
uv run plugin-eval score path/to/skill --depth standard
# Full certification (all layers, ~5 min)
uv run plugin-eval certify path/to/skill
Layers
- Static Analysis — Structural checks, anti-pattern detection. Instant, free.
- LLM Judge — Semantic evaluation (triggering, orchestration, output, scope). ~30s, 4 calls.
- Monte Carlo — Statistical reliability via 50–100 simulated runs. ~2–5 min.
Commands
| CLI | Claude Code | Description |
|---|---|---|
plugin-eval score |
/eval |
Score a plugin or skill |
plugin-eval certify |
/certify |
Full certification with badge |
plugin-eval compare |
/compare |
Head-to-head comparison |
plugin-eval init |
— | Build corpus for Elo ranking |
Documentation
See docs/plugin-eval.md for the full reference: layers, dimensions, scoring formula, anti-patterns, statistical methods, and project structure.