skill-quality-eval
skill-quality-eval is a meta-plugin for Claude Code that objectively measures skill quality through a fork + JSON-schema + snapshot-directory model, running N-repeat evaluations against ground-truth baselines and proposing SKILL.md improvements when regressions are detected. It provides four commands (baseline/run/compare/promote) that enforce JSON output validation, perform semantic matching on natural language fields via Haiku, track accuracy and stability metrics, and auto-generate improvement suggestions via Opus when quality drops.
Install
Source: https://github.com/1989v/ai/tree/HEAD/plugins/skill-quality-eval
What it's made of
4 commands · 1 skill
- Commands
- 4
- Agents
- 0
- Skills
- 1
- MCP servers
- 0
- Hooks
- 0
What it needs & plugs into
- API keys
- none
- Paid services
- none detected
- External tools
- none
- Talks to
- nothing external detected
Facts extracted from the plugin's files. Prose generated by claude-haiku-4-5-20251001.
Is this your plugin?
Claim it to keep the card accurate and enter the weekly contest. Requires signing in as the GitHub owner (1989v).