hqhq1025/skill-optimizer

Diagnose and optimize your Agent Skills (SKILL.md) with real session data + research-backed static analysis. Works with Claude Code, Codex, and any Agent Skills-compatible agent.

37
/ 100
Emerging

This tool helps AI agent developers improve how well their custom "skills" perform. It takes your skill definition files and your agent's actual conversation history as input. You get a prioritized report detailing how often skills are used, user satisfaction, and missed opportunities, so you can make your AI agent more effective. This is for anyone who builds or maintains custom capabilities for AI agents like Claude Code or Codex.

Use this if you develop custom skills for AI agents and want to systematically diagnose and fix performance issues based on real user interactions and best practices.

Not ideal if you are looking for a tool to develop the core AI agent itself, or if your agent does not use the Agent Skills open standard.

AI-agent-development prompt-engineering AI-workflow-optimization skill-auditing developer-productivity
No Package No Dependents
Maintenance 13 / 25
Adoption 7 / 25
Maturity 9 / 25
Community 8 / 25

How are scores calculated?

Stars

38

Forks

3

Language

License

MIT

Category

optimization

Last pushed

Mar 30, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/hqhq1025/skill-optimizer"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.