Keeps durable project documentation aligned with implementation and operating reality. Use when a change affects product behavior, architecture, data, APIs, configuration, environments, release procedures, commands, or other facts future maintainers need.
Use when writing READMEs, architecture, changelogs, release notes, runbooks, notebook docs, install docs, or security articles; produces docs. Do not trigger for API docs, AGENTS.md, or diagrams.
Synchronize documentation with a confirmed code, configuration, API, or behavior change by updating only evidence-backed README, API, configuration, example, migration, and changelog content while preserving style and language. Use for documentation-only edits; do not modify production behavior, invent undocumented facts, or use as a general code fix. 根据已确认的代码、配置、API 或行为变更,只更新有证据支持的 README、API、配置、示例、迁移和 CHANGELOG 内容,并保留原有风格与语言。用于仅文档修改;不得改变生产行为、编造未证实内容,也不作为通用代码修复。
Writes or upgrades API docs (Javadoc, etc.) with minimal, usage-focused text. Use when the user asks to document code, add Javadoc, upgrade docs, or apply documentation standards.
Write or review a security case record so another analyst, auditor or court can reconstruct what was known, when, and why each decision was made. Use when closing a case, preparing a case for escalation or legal hold, or auditing case quality.
Write and maintain documentation that lives with code: comments that earn their place, docstrings and doc comments, READMEs, API reference, architecture and decision records, runbook-style operational notes, and changelogs — and keep them true as the code changes, in the project's existing voice and tooling. Use when adding or reviewing comments or docstrings, writing or fixing a README, documenting a module, public API, or design decision, updating a changelog, or when docs have drifted from the code. For a standalone docs website use documentation-site; for long-form prose guides use technical-writing.
Plan, build and maintain a documentation website for a product, API, library, platform or internal system: information architecture (tutorials, how-to guides, reference, explanation), choosing a static site generator or hosted docs platform, navigation and search, versioning for multiple releases, generated API reference, code samples that are tested and actually run, docs-as-code workflow with review, previews, link checking and CI, plus accessibility, internationalisation and analytics. Use when someone asks to create a docs site, developer portal, knowledge base, handbook site, migrate docs to a new generator, add versioning or search to docs, or fix docs that users cannot navigate or that have drifted from the product.
リポジトリの構造・技術スタック・機能一覧・セットアップ手順を動的に解析し、 包括的なドキュメントを自動生成するスキル。言語・フレームワーク問わず汎用的に動作する。 Use this skill whenever the user asks to: - Explain a repository / リポジトリの説明 / リポジトリの概要 - Generate a README / README生成 / README作成 - Understand project structure / プロジェクト構成を教えて / 構造を説明して - Learn how to run a project / 使い方を教えて / 動かし方 / セットアップ方法 - Get a repo overview / repo overview / explain this repo / what does this repo do - List features / 機能一覧 / このプロジェクトは何ができる? - Onboard to a new codebase / コードベースのキャッチアップ / 新しいリポジトリに入った - "このリポジトリ何?" "プロジェクトの全体像" "how to run this project" - "コードの全体を把握したい" "ドキュメントを整備して" "技術スタックを知りたい" This skill is especially useful when joining a new project, onboarding team members, or when a repository lacks proper documentation. It works with ANY repository regardless of programming language, framework, or project type.
Writes user-facing help-center articles - verb-first how-to guides, symptom-organized troubleshooting pages, and FAQs - with one task per article, exact UI labels, and a stated success result. Use when someone asks "write a help article for...", "document how users reset their password", "turn these support tickets into a troubleshooting page", or "our help center articles are confusing, rewrite this one". Do NOT use for internal team procedures and SOPs - use process-doc instead; for on-call operational runbooks, use runbook-writer; for internal knowledge-base articles aimed at support agents, use kb-article-writer.
Keep project documentation accurate as code changes. Use whenever you add or change a feature, public API, config, env var, setup step, or command — and when the user asks to document something or writes new code without touching docs. Ensures README, usage docs, and inline docs stay true.
Write or update docstrings, READMEs and API docs that match what the code actually does, verified by reading the implementation. Use when the user asks to document code, write a README, explain a module, or fix out-of-date docs.
Flag possible documentation duplication, misplacement, or verbosity. Use when drafting or reviewing docs, backlog items, ADRs, or explanatory text to steer toward a single source of truth. Trigger phrases: "check documentation", "review docs", "check docs", "review documentation", "check for doc duplication", "review for duplication", "check doc quality", "review doc quality", "documentation review", "docs review", "check doc structure".
Use before adding, moving or substantially changing a page in docs/ or README.md, or a DOMAIN block in a template docs page: decides whether the knowledge belongs to this project or to the template, which existing page or designated place takes it, and what the change must link to.
Research across Notion and synthesize into structured documentation; use when gathering info from multiple Notion sources to produce briefs, comparisons, or reports with citations.
7.4k6mo agoReviewMountCreate a free account to mount
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md or AGENTS.md?
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
What is a skill?
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.