Agent skill
skill-manager
Manage, audit, and maintain your skill ecosystem. Use when the user asks to "check my skills", "audit skills", "find duplicate skills", "which skills am I using", "prune unused skills", "are my skills synced", "check for skill updates", "skill report", "skill health", or mentions skill maintenance, cleanup, or organization.
Install this agent skill to your Project
npx add-skill https://github.com/petekp/claude-code-setup/tree/main/skills/skill-manager
SKILL.md
Skill Manager
Unified tool for managing your skill ecosystem across Claude, Codex, and Agents runtimes.
Available Commands
Run these via the skill-manager.sh script in the repo's scripts/ directory:
# Full audit — runs all checks in one pass
~/.claude/scripts/skill-manager.sh report
# Individual commands
~/.claude/scripts/skill-manager.sh usage # Show skill usage frequency
~/.claude/scripts/skill-manager.sh usage --top 10 # Top 10 most-used skills
~/.claude/scripts/skill-manager.sh dupes # Detect redundant/duplicate skills
~/.claude/scripts/skill-manager.sh check # Verify availability for Claude/Codex/Agents
~/.claude/scripts/skill-manager.sh sync # Validate repo sync status
~/.claude/scripts/skill-manager.sh update # Check for npx skill updates
~/.claude/scripts/skill-manager.sh prune # List candidates for removal
When to Run Each Command
| Command | When to Use |
|---|---|
report |
Periodic full health check (weekly or monthly) |
usage |
Before pruning — see which skills are actually used |
dupes |
After installing new skills — check for overlap |
check |
After setup.sh or when skills seem missing |
sync |
After editing skills — verify everything is linked |
update |
Periodically — check if npx-installed skills have newer versions |
prune |
When the skill list feels bloated — find removal candidates |
How Usage Tracking Works
A PostToolUse hook in settings.json fires every time the Skill tool is used. It logs:
- Skill name
- Timestamp (UTC)
- Project directory
Data is stored in ~/.claude/skill-usage.jsonl (one JSON object per line). The usage and prune commands read this data to generate reports.
How to Use This Skill
When the user asks about skill management, run the appropriate command and present the results. For general questions, run report for a full picture.
Interpreting Results
- Check: Green means properly linked. Yellow means something unexpected. Red means broken.
- Sync: Verifies all three runtimes (Claude, Codex, Agents) point to the repo's skills directory.
- Dupes: Groups skills by prefix and checks keyword overlap in descriptions. High overlap (>40%) suggests consolidation.
- Usage: Shows invocation counts and last-used dates. "Never used" skills are prune candidates.
- Prune: Combines usage data with overlap analysis to suggest removals.
Archiving Skills
To archive a skill (remove from active use but keep for reference):
mv skills/<name> ~/.claude/skills-archive/
This removes it from all three runtimes (since they symlink to the repo's skills/).
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
ubiquitous-language
Extract a DDD-style ubiquitous language glossary from the current conversation, flagging ambiguities and proposing canonical terms. Saves to UBIQUITOUS_LANGUAGE.md. Use when user wants to define domain terms, build a glossary, harden terminology, create a ubiquitous language, or mentions "domain model" or "DDD".
every-style-editor
This skill should be used when reviewing or editing copy to ensure adherence to Every's style guide. It provides a systematic line-by-line review process for grammar, punctuation, mechanics, and style guide compliance.
manage-codex
Autonomous Codex batch orchestrator. Use for "/manage-codex", "manage codex", "use codex", "dispatch to codex", or long-running Codex work.
seo-audit
When the user wants to audit, review, or diagnose SEO issues on their site. Also use when the user mentions "SEO audit," "technical SEO," "why am I not ranking," "SEO issues," "on-page SEO," "meta tags review," "SEO health check," "my traffic dropped," "lost rankings," "not showing up in Google," "site isn't ranking," "Google update hit me," "page speed," "core web vitals," "crawl errors," or "indexing issues." Use this even if the user just says something vague like "my SEO is bad" or "help with SEO" — start with an audit. For building pages at scale to target keywords, see programmatic-seo. For adding structured data, see schema-markup. For AI search optimization, see ai-seo.
capture-learning
Analyze recent conversation context and capture learnings to project knowledge files (for project-specific insights) or skills/commands/subagents (for cross-project patterns). Use when the user asks to "capture this learning", "update the docs with this", "remember this for next time", "document this issue", "add this to CLAUDE.md", "save this knowledge", or "update project knowledge". Also triggers after resolving build/setup issues, discovering non-obvious patterns, or completing debugging sessions with valuable insights.
agent-changelog
Compile an agent-optimized changelog by cross-referencing git history with plans and documentation. Use when asked to "update changelog", "compile history", "document project evolution", or proactively after major milestones, architectural changes, or when stale/deprecated information is detected that could confuse coding agents.
Didn't find tool you were looking for?