/ Directory / Playground / skill-optimizer
← All servers ↗ GitHub
● Community hqhq1025 ⚡ Instant

skill-optimizer

by hqhq1025 · hqhq1025/skill-optimizer

Audit a single SKILL.md using real session data plus static analysis — tells you exactly what to change.

skill-optimizer looks at a SKILL.md through two lenses: (1) session logs — did it activate when expected, was the output useful — and (2) static analysis — is the frontmatter clean, is the description properly intent-scoped, are examples calibrated. It outputs concrete edits you can apply. Pairs well with SkillCompass (which does bundle-level ranking).

▶ Watch demo 📦 Install 💡 Use Cases

Why use it

Key features

Live Demo

What it looks like in practice

skill-optimizer-skill.replay ▶ ready
0/0

Install

Author repository · Claude Skills documentation

Use Cases

Real-world ways to use skill-optimizer

How to diagnose and fix one underperforming skill

👤 Skill authors iterating on a specific skill ⏱ ~30 min intermediate

When to use: You notice one skill never activates, or activates wrongly.

Flow
  1. Review the patch
    Show me the proposed SKILL.md diff.✓ Copied
    → Minimal, reviewable diff
  2. Apply and validate
    Apply the patch and tell me what to watch for this week.✓ Copied
    → Validation checklist

Outcome: A targeted improvement with an accountability plan.

Pitfalls
  • Optimizing for activation rate but breaking scope — Include a 'false positive rate' acceptance metric
Combine with: skillcompass-skill

Polish your first SKILL.md before publishing

👤 First-time skill authors ⏱ ~20 min beginner

When to use: You wrote a SKILL.md and want expert review before shipping.

Flow
  1. Ask for a review
    Review my SKILL.md against skill-optimizer's static checks.✓ Copied
    → Checklist with pass/fail + rationale
  2. Fix issues
    Apply the fixes and show me the final version.✓ Copied
    → Clean SKILL.md

Outcome: A ship-ready SKILL.md.

Pitfalls
  • Over-promising in the description — Be specific about what the skill does; Claude uses it to decide activation

Combinations

Pair with other MCPs for X10 leverage

skill-optimizer-skill + skillcompass-skill

SkillCompass ranks the bundle; skill-optimizer dives into the worst offender

Use SkillCompass to pick the weakest skill, then optimize its SKILL.md.✓ Copied
skill-optimizer-skill + filesystem

Apply SKILL.md patches directly

Apply the proposed diff to ~/.claude/skills/my-skill/SKILL.md.✓ Copied

Tools

What this MCP exposes

ToolInputsWhen to callCost
static-analysis SKILL.md path Before publishing or during iteration 0
log-based-analysis logs + skill path Post-use tuning 0
patch-generation findings After analysis 0

Cost & Limits

What this costs to run

API quota
none beyond LLM
Tokens per call
2–10k per skill analysis
Monetary
free
Tip
Static analysis is nearly free; log analysis costs more — run it only when iterating

Security

Permissions, secrets, blast radius

Credential storage: none; logs may contain sensitive prompts — treat their path carefully
Data egress: none

Troubleshooting

Common errors and fixes

No logs found

Confirm Claude Code trace path; pass the path explicitly if non-default.

Suggestions conflict with intended scope

Tell the optimizer your scope constraints; it can respect non-goals

Alternatives

skill-optimizer vs others

AlternativeWhen to use it insteadTradeoff
skillcompass-skillYou need bundle-level ranking, not single-skill depthBreadth over depth

More

Resources

📖 Read the official README on GitHub

🐙 Browse open issues

🔍 Browse all 400+ MCP servers and Skills

Continue exploring

Related tools and workflows

Choose another guide for your workflow, or explore a collection.

Browse all topic collections → · See 29 new official additions →