Produces a complete health report on a skill library: per-skill structural validation followed by cross-skill analysis covering trigger conflicts, redundancy, workflow coverage gaps, and composition chains. Auto-fixes unambiguous minor structural issues (whitespace, missing optional metadata) and formats all other findings with format-review-comments. TRIGGER when: user asks to audit skills, check skill coverage, validate all skills, find gaps in skills, check for trigger conflicts, or health-check the skill library. DO NOT TRIGGER when: user asks to create, update, rename, or delete a skill (use upsert-skill instead); or to evaluate a single skill for quality (use review-skill instead).
Audits AGENTS.md files and equivalent agent instruction files (CLAUDE.md, CURSOR.md, Copilot instructions) for completeness, accuracy, and agent-friendliness, producing structured, actionable feedback. Cross-references file paths, scripts, and branch names against the actual repository to catch stale or incorrect guidance. Formats every finding with format-review-comments and runs a refine-prose pass before presenting results. TRIGGER when: user asks to review, audit, check, inspect, analyze, or evaluate an AGENTS.md, CLAUDE.md, or agent instruction file. DO NOT TRIGGER when: user asks to review a pull request (use review-pr instead) or to evaluate a skill file (use review-skill instead).
Creates or updates agent instruction files (AGENTS.md, CLAUDE.md) by surveying the repository and generating accurate, current, agent-friendly guidance. Use when the user wants to generate, create, write, update, refresh, or regenerate an AGENTS.md or CLAUDE.md for a repository. TRIGGER when: user asks to create, generate, write, update, or refresh an AGENTS.md, CLAUDE.md, or agent instruction file. DO NOT TRIGGER when: user asks to review, audit, check, or evaluate an existing agent instruction file (use review-agents-md instead).
Reads a structured plan from a GitHub issue and orchestrates the full delivery workflow: parses unchecked tasks in dependency order, steps through them one at a time, commits via create-commit, reviews via review-pr, and opens a PR linked back to the plan issue. Use when the user says "implement #N", "implement this plan", "execute plan #N", "work through issue #N", "implement the plan in #N", or "carry out the tasks in #N". TRIGGER when: user wants to execute or implement a plan stored as a GitHub issue. DO NOT TRIGGER when: user wants to create or update a plan (use upsert-plan instead).
Stages changes safely, generates a conventional-commit message from the diff, and blocks secrets or debug artifacts from being committed. TRIGGER when: user asks to commit, save changes, stage files, write a commit message, run git commit, check in my changes, or commit my work. DO NOT TRIGGER when: user asks to push, open a PR, or create a branch.
Creates and updates detailed, structured work plans as GitHub issues. Use when the user wants to plan a feature, bug fix, project, or any body of work — also triggered by "make a plan", "scope out this work", "break down this task", "help me plan", or "create a GitHub issue for this". In update mode (triggered by an issue number or URL), edits the issue in place and posts a change-summary comment. DO NOT TRIGGER when: user asks to create, update, or delete a skill (use upsert-skill instead).
Evaluates structured work plans across six quality dimensions — objective clarity, task actionability, dependency correctness, acceptance criteria completeness, scope appropriateness, and structural completeness. Formats all findings with format-review-comments. Use when the user asks to review, audit, or evaluate a work plan. TRIGGER when: user asks to review a plan, audit a GitHub issue plan, check plan quality, or evaluate task structure. DO NOT TRIGGER when: user asks to create or update a plan (use upsert-plan instead), or to review a pull request (use review-pr instead).
Conducts systematic pull request reviews across logic, security, performance, test coverage, and documentation. Uses the format-review-comments skill to format all feedback. Use when the user asks to review a pull request, audit a diff, or give structured feedback on proposed code changes — also triggered by "look at this PR", "check PR #N", "can you review this", or "give feedback on this diff". TRIGGER when: user asks to review a pull request, audit a diff, or give feedback on proposed code changes. DO NOT TRIGGER when: user asks to review, evaluate, or audit a skill file (use review-skill instead).