hax-yax

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).

Evaluates whether a skill is effective — covering instruction clarity, trigger discoverability, example completeness, composability, and scope coherence. Reads the full skill directory including supporting files (scripts, references, assets) before reviewing. Formats every finding with format-review-comments and suggests inline fixes for unambiguous issues. Use when the user asks to review, audit, or evaluate a skill. TRIGGER when: user asks to review a skill, audit a skill, evaluate skill quality, or check if a skill is well-written. DO NOT TRIGGER when: user asks to create, update, rename, or delete a skill (use upsert-skill instead), or to review a pull request (use review-pr instead).

Manages the lifecycle of reusable agent skills stored under .agents/skills/. Use when the user wants to add, modify, rename, delete, or audit skills in this repository — also triggered by "create a new skill", "set up a skill", "list my skills", "what skills do I have", or "remove a skill". DO NOT TRIGGER when: the user asks to review, evaluate, or critique a skill for quality (use review-skill instead); or asks for a full library health report, trigger conflict analysis, or workflow coverage audit (use audit-skills instead).

Formats code review and PR feedback using the Conventional Comments standard (label [decorations]: subject). Apply proactively whenever posting review comments or any critique of code or pull requests. Invoke directly when the user asks to format feedback, use conventional comments style, or label a review comment as blocking, suggestion, or nitpick.

Polishes drafted prose for clarity, conciseness, and consistent voice before it is posted or presented. Apply after drafting any plan, review summary, or written output to catch filler phrases, passive constructions, and inconsistent terminology. Use when the user asks to polish, clean up, improve, edit, or tighten writing — also triggered by "refine this draft", "make this clearer", or "improve my writing". Also composable: other skills invoke it as a late-stage refinement step. TRIGGER when: user asks to polish, edit, or improve prose. DO NOT TRIGGER when: user asks to format or lint code (use language-specific tools instead), or when this skill is already running as a composable step within another skill.