Claude commands
Handy Claude commands, kept current by the community. Add one you rely on.
/validate-hook
validate-hook
Validate hooks for security, performance, and SDK compliance
/test-skill
test-skill
Test Claude Code skills using RED/GREEN/REFACTOR TDD phases in fresh subagents to prevent priming bias.
/skills-eval
skills-eval
Audit skill quality, frontmatter compliance, token efficiency, and activation reliability. Recommends improvements.
/rules-eval
rules-eval
Evaluate Claude Code rules in .claude/rules/ directories for quality
/promote-discussions
promote-discussions
Check GitHub Discussions for highly voted learnings and promote them to Issues.
/plugin-review
plugin-review
"Tiered plugin quality review: branch (quick gates),
/make-dogfood
make-dogfood
Analyze and enhance Makefiles for complete functionality coverage with auto-generation capability
/improve-skills
improve-skills
Identify and implement skill improvements from execution logs and user evaluations.
/hooks-eval
hooks-eval
Evaluate all hooks in a plugin for quality and compliance
/evaluate-skill
evaluate-skill
Manually evaluate a recent skill execution to record qualitative feedback.
/create-skill
create-skill
Scaffold new Claude Code skills with brainstorming, TDD methodology, and proper frontmatter and module structure.
/create-hook
create-hook
Create hooks with brainstorming and security-first design
/create-command
create-command
Create slash commands with brainstorming and best practices
/context-report
context-report
Generate context optimization report for skill directories
/analyze-skill
analyze-skill
Analyze skill file complexity metrics and generate modularization recommendations for splitting or progressive loading.
/aggregate-logs
aggregate-logs
Generate LEARNINGS.md from skill execution logs over a configurable time window.
/token-optimizer
token-optimizer
Route broad repository discovery to a cheaper worker model using each client's native subagents, keeping the main agent for decisions and targeted verification. Use when asked to "reduce token usage", "delegate bulk reading", "set up a cheap reader agent", or "why is my context filling up".
/context-update
Context update
Save a review-gated Context OS checkpoint
/context-start
Context start
Start a read-only Context OS continuity review
/context-setup
Context setup
Set up Context OS through its review-gated lifecycle workflow
/context-end
Context end
Close a Context OS session through its review-gated workflow
/svg-create
svg-create
Author or clean up an SVG asset — icon, illustration, mascot pose, logo mark — so it scales from viewBox, recolors from tokens, animates without a rewrite, is optimized, and has an accessible name.
/svg-animate
svg-animate
Animate an SVG — icon, logo reveal, stroke draw, morph, mascot loop — or turn a frame sequence / flat clip into one editable animated SVG, with the engine chosen for where the file lives.
/sound-pass
sound-pass
Decide which moments earn a sound, design one material family, generate the files (ElevenLabs if keyed, synth or CC0 if not), and wire them in — returns a sound map table.
Create a command
Please sign in to add a command.