.claude_code

Audit a repo's agent-facing documentation layer and dispatch the right fix — instruction-file topology (AGENTS.md canonical? CLAUDE.md/GEMINI.md @import it?), always-loaded token cost, CodeMap freshness and line-number accuracy, broken pointers, changelog-vs-code version drift. Read-only; reports first, then offers remediation in dependency order. Use when asked to "check this repo", "audit the agent docs", "is my CLAUDE.md/AGENTS.md set up right", "are the docs stale", "check the code map", "health check this project", or when onboarding an unfamiliar repo and you want to know whether its docs can be trusted. Also on /repo-doctor. NOT for code review, tests, dependency or security audits.

Audit and rightsize CLAUDE.md / AGENTS.md and skills per Anthropic's Claude 5 context-engineering guidance (Thariq, 2026-07-24) — cut rules the model can judge, extract detail to on-demand files/skills, dedupe layers, and verify. Use when users mention slow /resume, CLAUDE.md being too long, reducing token usage, context optimization, rightsizing instructions, auditing CLAUDE.md, or following up on /doctor output. Triggers on "optimize CLAUDE.md", "rightsize my instructions", "my resume is slow", "CLAUDE.md is too big", "audit my CLAUDE.md", "apply the context-engineering rules", "slim down my instructions".

Sync Claude Code config (CLAUDE.md, agents, skills, commands, instructions, settings, statusline, guard hooks, plugins, MCP servers, CC version) AND the shared cross-CLI house-rules — canonical ~/.config/agents/AGENTS.md plus the per-CLI instruction files that @import it (CLAUDE.md, GEMINI.md) and Codex/Copilot/agy/Pi wiring — from THIS machine to any SSH-reachable host so every AI coding CLI works the same there. Discovers targets from ~/.ssh/config. Use on /sync-claude-config [host], or when asked to "sync claude config to <host>", "mirror my agents/skills to <machine>", "make Claude Code (or my agents) work the same on <host>". Push-only (local → remote); never copies credentials or machine state.

Restructure a project's (or the whole machine's) AI-agent instruction files so AGENTS.md is the single canonical guide that every coding CLI follows — Claude Code, Codex, Copilot, Antigravity/agy, Gemini, Pi — with CLAUDE.md and GEMINI.md reduced to thin @import pointers plus tool-specific extras. Use this whenever the user wants non-Claude agents to behave the same as Claude, mentions consolidating or unifying AGENTS.md / CLAUDE.md / GEMINI.md, says things like "make all my agents follow the same rules", "share my house rules across CLIs", "make Codex/Copilot/Gemini work like Claude", or wants to clean up duplicated/​drifting instruction files. Works on the LOCAL project by default, then asks whether to also do the GLOBAL ~/.claude machine-wide setup. Trigger it even if the user doesn't name the skill.

Use when bumping a version, cutting a release, or when a CHANGELOG is stale, missing versions, or disagrees with the code — and before opening any PR, per the versioning rule in AGENTS.md. Also on /version-manager [check|backfill|release], or when the user says "bump the version", "cut a release", "the changelog is old". Auto-detects version locations in any stack (pyproject, package.json, VERSION file, module constants, README display) — no per-repo config.

Create a Discord post (announcement, release recap, changelog summary, community update) for the current project and save it as a markdown file under a Discord/ directory in the project root. Use this whenever the user asks to "create a Discord post", "write a Discord announcement", "make a Discord update", "post this to Discord", "draft a Discord message", or wants a community-facing summary of changes, a release, or news for a project — even if they don't say the word "skill". This skill only drafts and saves the post to a file; it never sends anything to Discord.

Use when the user asks for "an HTML" — an HTML document, page, report, explainer, announcement, week-in-review, summary, comparison, or any standalone HTML deliverable. Also use when converting a markdown report/notes into a shareable page. NOT for app UI components or pages inside a codebase (that's normal frontend work).

Use when generating, editing, batching, or scripting images, videos, or page layouts with the ImageAI CLI (`python main.py ...`) from inside the ImageAI repo, across any provider — Google Gemini / Nano Banana, OpenAI (gpt-image-2/1.5/1, DALL·E), Stability AI, or local Stable Diffusion. Covers model selection, sizing/aspect, references & masks, streaming, Batch API, lyrics-to-prompts, gcloud auth, key management, video generation (Gemini Omni + Veo: refs, extend, frame interpolation, conversational refine, edit-your-own-video, --json output contract), and the publication layout engine (--layout-design/--layout-fill/--layout-export for comics, magazines, PDFs). Trigger whenever the user wants to make or edit an image, video, or layout (or set up/test a provider key) from the command line in this working directory.

Use when a project hardcodes LLM model IDs (claude-*, gpt-*, gemini-*) that go stale, when the user wants current model IDs resolved at runtime, or on /model-registry [install|migrate|status|refresh-fallback]. Works in TypeScript/Next.js, Python, and any project that can fetch JSON.

Install this repo's Claude Code configuration into a user's ~/.claude/ directory. Merges agents, skills, output styles, instructions, settings, MCP servers, and supporting files using a diff-and-ask approach so users keep their existing customizations. Use when the user asks to install, deploy, apply, or set up the config from this repo. Triggers on requests like "install this config", "set up my claude config", "apply these settings", "deploy to my ~/.claude", or "merge this into my config".

Use when users ask to update or create the code map / CodeMap.md, refresh documentation line numbers, document new files, or when Docs/CodeMap.md is missing or older than 7 days. Triggers on "update the code map", "refresh CodeMap", "the code map is outdated", "update line numbers in documentation".

Safely update the Hermes Agent install on this machine (hermes CLI + ~/.hermes/hermes-agent source repo). Use on /update-hermes, or when asked to "update hermes", "upgrade the hermes agent", or "pull the latest hermes". Always backs up first — full ~/.hermes backup via `hermes update --backup` PLUS a separate patch/tarball backup of local source customizations, because the built-in backup intentionally excludes the hermes-agent/ source repo. Never runs a bare `hermes update`.

Generate user-facing feature documentation, Google sitemap, and navigational site map for any project. Writes markdown docs to the project's docs directory, generates sitemap.xml for SEO, and updates .raginclude for RAG indexing. Uses parallel agents to document multiple feature areas simultaneously. For developer/technical docs (API endpoints, data models, error handling), use the technical-documenter skill instead. Triggers on: 'document this project', 'generate feature docs', 'write support documentation', 'create product docs', 'document all features', 'update project documentation', 'generate sitemap'.

Use when the user wants to free up disk space or check install hygiene on their machine — "clean up my disk", "my drive is full", "find junk files", "did I install something in the wrong place", "make a cleanup runbook". Scans home + dev/cache locations, proposes a plain-English plan, then either cleans up (recoverable Trash with one-command undo) or writes a runbook. Never touches system files; deletes only via the audited safe-trash helper.

Download a YouTube video's transcript to the yt-transcript project's Notes directory. Use whenever the user provides a YouTube URL (youtube.com/watch, youtu.be, shorts, embed) or a bare 11-character video ID and asks to fetch, save, download, grab, or transcribe the transcript/captions/subtitles — even if they don't explicitly name this skill. Also trigger on phrases like "get the transcript of this video", "save the captions", or "transcribe https://youtu.be/...".

Initialize a new company project from scratch. Use when creating any new project for YourCompany — SaaS web apps (Next.js), Python scripts/tools, or standalone libraries. Sets up directory structure, CLAUDE.md, .gitignore, .env.example, JetBrains IDE support, brand conventions, and gets you coding immediately. Triggers on "start a new project", "create a new CL project", "initialize a project", "new SaaS app", "set up a Python tool for CL", "scaffold a project".

Sweep all registered projects and regenerate their user-facing feature documentation if stale. Reads ~/.claude/my-projects.yaml, dispatches one parallel agent per project to run the project-documenter skill, commits results, writes per-project reports to Notes/, and displays a sorted summary. Use when you want to refresh docs across all your projects at once.

Analyzes a codebase and generates comprehensive user-facing feature documentation. Use this skill when users ask to document features, create a feature list, generate product documentation, or write a Features.md file. Triggers on requests like "document the features", "what does this project do", "create feature documentation", or "list all capabilities".

Generate a .raginclude file for any project to feed its RAG knowledge base. Use when the user asks to create, generate, or update a .raginclude file, set up RAG indexing for a project, configure which files should be indexed for AI chat support, or make a project's documentation available to a RAG pipeline. Triggers on: 'create raginclude', 'generate raginclude', 'set up RAG for this project', 'index this project for chat', 'update raginclude'.

Generate developer and support-staff documentation for any project. Covers API endpoints, data models, error handling, configuration, and architecture. Outputs to $DOCS_DIR/Developer/ and is NOT added to .raginclude. Uses parallel agents to document multiple feature areas simultaneously. For user-facing docs, use the project-documenter skill instead. Triggers on: 'generate technical docs', 'document the API', 'create developer docs', 'write technical documentation', 'document endpoints', 'generate dev docs'.

Full product management toolkit for advisory, artifact generation, and product analysis. Use when the user needs help with: (1) PM strategy and decisions — prioritization, roadmap planning, feature scoping, stakeholder alignment, (2) Creating PM artifacts — PRDs, user personas, roadmaps, competitive analyses, MVP definitions, GTM briefs, sprint plans, metrics specs, feedback summaries, (3) Product analysis — lifecycle stage assessment, metrics health checks, SWOT analysis, market positioning, (4) PM workflows — market research guidance, agile practices, cross-functional collaboration, user feedback loops. Triggers on requests involving product strategy, feature prioritization, go-to-market planning, user research, KPIs/metrics, MVP definition, or any product management task.