Skip to content

TsukiNi22/ai-utils / skills/routers/doc

Router for documentation tasks of the user - README and Markdown docs, GitHub wiki, CHANGELOG / release notes, HTML documentation (user guide, technical doc, project graph), explanation pages (simple + technical), protocol / wire format docs, HTML style, reports, code comments - loads readme-style, wiki-style, html-doc, better-html-doc, explain-doc, better-explain-doc, protocol-doc, better-protocol-doc, html-style, better-html-style, report, docs-update, git-conventions or cpp-comments depending on what is documented. Invoke manually with /doc.

Documentation router

Request given with /doc: $ARGUMENTS

Load the skills with the Skill tool (never the other routers: they are manual-only), then write. The request is the text given with /doc (or the latest request; if none, inspect README.md, CHANGELOG.md, docs/ and propose what is missing or outdated).

Context

  • Existing docs: README.md, CHANGELOG.md, docs/*.html, wiki (<repo>.wiki), Doxyfile.
  • What changed since the docs were written: git log --oneline -- . ':!docs' | head, version in CMakeLists.txt.
  • Audience: users (non-technical) or developers.

Skills

SituationSkills
README, Markdown guidereadme-style
GitHub wiki (<repo>.wiki: Home, sidebar, section pages)wiki-style (+ readme-style for the Markdown rules, libutils for a libutils based project)
HTML documentation, docs/ site, GitHub Pages, project graphhtml-doc (+ readme-style for the README link)
a documentation site with search, several pages / sections, EN / FR, "like the claude-cluster docs", "better" docsbetter-html-doc (+ better-html-style; explanations in it: better-explain-doc, protocol pages: better-protocol-doc)
explain how something works (concept, algorithm, protocol, math) with diagrams / animations / interactive examples, simple + technicalexplain-doc (+ html-style)
specify / document a protocol, a wire or message format, a handshake, the commands of a client / server, a storage format (the reference of the frames, codes and commands)protocol-doc (it asks the output: Markdown, PDF via report, HTML sections via html-doc)
any other HTML page, a palette / color / font / theme to definehtml-style (better-html-style for the claude-cluster docs look with search)
CHANGELOG, release notes, PR descriptiongit-conventions
comments / documentation inside the code (any language), file headerscomments (+ cpp-comments for C++, python-comments for Python)
a result / report / study delivered as PDFreport
doc of a libutils based projectalso libutils (exact APIs)
update all the docs after changes / a new version (README, CHANGELOG, HTML site, gh-pages, wiki, packages / manifests, install scripts, help texts)docs-update (it loads the others by surface: readme-style, wiki-style, html-doc, git-conventions)
full documentation passdocs-update

Always

  • An audit / summary of the docs is delivered through report (format asked once, English, audit/ at the repository root).
  • Check every name/command/API against the code before writing it; mark planned vs implemented.
  • Start the answer with one line listing the loaded skills.
rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization.Stars: 464kUpdated Claude CodeCodexVerifiedInstall
academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.Stars: 196kUpdated Claude CodeCodexVerifiedInstall
claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).Stars: 196kUpdated Claude CodeCodexUnverifiedInstall
doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.Stars: 196kUpdated Claude CodeCodexVerifiedInstall