Skip to content
Skill

skill-optimizer

by hqhq1025

AI Summary

Analyze skills using historical session data + static quality checks, output a diagnostic report with P0/P1/P2 prioritized fixes. Scores each skill on a 5-point composite scale across 8 dimensions. CSO (Claude/Agent Search Optimization) = writing skill descriptions so agents select the right skill a

Install

Copy this and paste it into Claude Code, Cursor, or any AI assistant:

I want to install the "skill-optimizer" skill in my project.

Please run this command in my terminal:
# Install skill into your project
mkdir -p .claude/skills/skill-optimizer && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/skill-optimizer/SKILL.md "https://raw.githubusercontent.com/hqhq1025/skill-optimizer/main/skills/skill-optimizer/SKILL.md"

Then restart Claude Code (or reload the window in Cursor) so the skill is picked up.

Description

Use when the user wants to analyze, audit, or improve their Agent Skills (SKILL.md files). Triggers on /optimize-skill, /skill-audit, 'optimize skills', 'analyze skills', 'check my skills', 'skill quality'. Also use proactively when the user mentions skills aren't triggering, skills feel broken, or asks why a skill didn't fire.

Overview

Analyze skills using historical session data + static quality checks, output a diagnostic report with P0/P1/P2 prioritized fixes. Scores each skill on a 5-point composite scale across 8 dimensions. CSO (Claude/Agent Search Optimization) = writing skill descriptions so agents select the right skill at the right time. This skill checks for CSO violations.

Usage

• /optimize-skill → scan all skills • /optimize-skill my-skill → single skill • /optimize-skill skill-a skill-b → multiple specified skills

Rules

• Read-only: never modify skill files. Only output report. • All 8 dimensions: do not skip any. If data is insufficient, report "N/A — insufficient session data" rather than omitting. • Quantify: "you had 12 research tasks last week but the skill never triggered" beats "you often do research". • Suggest, don't prescribe: give specific wording suggestions for description improvements, but frame as suggestions. • Show evidence: for undertrigger claims, quote the actual user message that should have triggered the skill. • Evidence-based suggestions: when suggesting description rewrites, cite the specific research finding that motivates the change (e.g., "front-load trigger keywords — MCP study shows 3.6x selection rate improvement").

Data Sources

Auto-detect the current agent platform and scan the corresponding paths: | Source | Claude Code | Codex | Shared | |--------|------------|-------|--------| | Session transcripts | ~/.claude/projects//.jsonl | ~/.codex/sessions//.jsonl | — | | Skill files | ~/.claude/skills//SKILL.md | ~/.codex/skills//SKILL.md | ~/.agents/skills/*/SKILL.md | Platform detection: Check which directories exist. Scan all available sources — a user may have both Claude Code and Codex installed.

Discussion

0/2000
Loading comments...

Health Signals

MaintenanceCommitted 5d ago
Active
AdoptionUnder 100 stars
38 ★ · Niche
DocsREADME + description
Well-documented

GitHub Signals

Stars38
Forks3
Issues1
Updated5d ago
View on GitHub
MIT License

My Fox Den

Community Rating

Sign in to rate this booster

Works With

Claude Code