Claude Skills

Use when creating new skills, modifying existing skills, or improving skill quality. Use when user says "create a skill", "write a skill", "add capability". Use when a repeated pattern should become reusable.

Knowledge flywheel health monitoring. Checks velocity, pool depths, staleness. Triggers: "flywheel status", "knowledge health", "is knowledge compounding".

Spawn Agent Farm for parallel issue execution. Mayor orchestrates crew via tmux + MCP Agent Mail. Replaces /crank for multi-agent work. Triggers: "farm", "spawn agents", "parallel work", "multi-agent".

Meta skill explaining the AgentOps workflow. Auto-injected on session start. Covers RPI workflow, Knowledge Flywheel, and skill catalog.

This skill should be used when the user asks to "generate documentation", "validate docs", "check doc coverage", "find missing docs", "create code-map", "sync documentation", "update docs", or needs guidance on documentation generation and validation for any repository type. Triggers: doc, documentation, code-map, doc coverage, validate docs.

Deep codebase exploration. Triggers: research, explore, investigate, understand, deep dive, current state.

Language-specific coding standards and validation rules. Provides Python, Go, TypeScript, Shell, YAML, JSON, and Markdown standards. Auto-loaded by /vibe, /implement, /doc, /bug-hunt, /complexity based on file types.

Setup the Ralph autonomous AI coding loop - ships features while you sleep

Fetch PR review comments and implement all requested changes

Fix grammar and spelling errors in one or multiple files while preserving formatting

Comprehensive post-implementation validation. Combines retro (learnings), vibe (code validation), security scanning (Talos), and knowledge extraction into a single unified workflow. Triggers: "post-mortem", "validate completion", "final check", "wrap up epic", "close out", "what did we learn".

Process GitHub PR review comments by fetching them to local JSON, implementing fixes, and tracking progress. Use when user invokes /gh-process-review command. Fetches reviews to file to avoid context pollution, uses jq for parsing, commits after each fix. Supports optional "continue" argument to skip fetching and resume with existing reviews file.

Quick commit and push with minimal, clean messages

Vérifie la conformité du code PHP aux principes Elegant Objects de Yegor Bugayenko. Analyse un fichier spécifique ou tous les fichiers modifiés dans la branche.

Charge la documentation d'un framework depuis son site web dans des fichiers markdown locaux. Supporte Symfony, API Platform, Meilisearch, atournayre-framework et Claude Code.

Trace knowledge artifact lineage and sources. Find orphans, stale citations. Triggers: "where did this come from", "trace this learning", "knowledge lineage".

Pre-mortem simulation for specs and designs. Simulates N iterations of implementation to identify failure modes before they happen. Triggers: "pre-mortem", "simulate spec", "stress test spec", "find spec gaps", "simulate implementation", "what could go wrong", "anticipate failures".

Expert guidance for creating, building, and using Claude Code subagents and the Task tool. Use when working with subagents, setting up agent configurations, understanding how agents work, or using the Task tool to launch specialized agents.

Epic decomposition into trackable issues. Triggers: "create a plan", "plan implementation", "break down into tasks", "decompose into features", "create beads issues from research", "what issues should we create", "plan out the work".