Use when the user asks for a documentation review, doc audit, doc comment review, godoc review, proto comment review, OpenAPI or Swagger spec review, README review, example test review, "are the docs in sync with the code", "do the docs still match", "are these comments accurate", or "check the examples". Also use when another skill dispatches a documentation review.
Verifies documentation claims against codebase reality using two-pass extraction and pattern expansion. Use when auditing docs before releases, after major refactors, when users report docs don't match behavior, or for periodic doc hygiene; trigger phrases include "audit docs", "verify documentation", "docs accurate", "documentation drift", "docs don't match".
Audit Station documentation, READMEs, architecture diagrams, and code comments against implementation and behavior evidence; maintain the learning path when features change. Use for documentation audits or feature changes that alter a documented journey or contract.
Skill: Documentation
## Propósito
Generar documentación de calidad para el código: docstrings, JSDoc, README sections, comentarios técnicos y documentación de API.
## Cuándo activar este skill
- El usuario pide "documentar", "documentación", "docstrings
Write or review UDS Core documentation using the repository's style, voice, and document-type conventions. Use when creating, editing, or reviewing release notes, how-to guides, troubleshooting runbooks, or reference pages.
2014mo agoReviewMountCreate a free account to mount
Create, restructure, or maintain accurate developer documentation for software, tools, automations, packages, APIs, SDKs, CLIs, installations, migrations, operations, and troubleshooting. Use when the user asks for a README, overview, quickstart, tutorial, how-to guide, concept page, reference, API or CLI documentation, installation guide, runbook, migration guide, release notes, troubleshooting page, or a complete documentation set.
683mo agoReviewMountCreate a free account to mount
Build or refine visual documentation, system diagrams, and interactive worked examples from verified sources. Use when a reader needs to understand a mechanism, ownership boundary, calculation, or workflow comparison.
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.
010mo agoReviewMountCreate a free account to mount
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.
Documentation conventions for .NET (.csproj, C#) including XML docs, DebuggerDisplay attributes, and Mermaid diagrams for architecture documentation. Use when adding XML docs, DebuggerDisplay, or creating architecture diagrams in markdown. DO NOT use for web frameworks (Next.js, React, JavaScript, TypeScript, Node.js).
Use this skill when the user requests to generate, create, or improve documentation for code, APIs, libraries, repositories, or software projects. Supports README generation, API reference documentation, inline code comments, and architecture documentation. Trigger on requests like \"document this code\", \"create a README\", \"generate API docs\", \"document architecture\", or when analyzing codebases for documentation purposes.
Specialized documentation agent for generating, maintaining, and organizing technical documentation. Creates MCP tool docs, API references, session logs, and architecture documentation in Obsidian vault.
Use when writing a README, documenting an API with OpenAPI, drafting a runbook for on-call engineers, authoring a technical spec or ADR, or setting up docs-as-code with auto-deploy to GitHub Pages.
1907mo agoReviewMountCreate a free account to mount
Records decisions and documentation. Use when making architectural decisions, changing public APIs, shipping features, or when you need to record context that future engineers and agents will need to understand the codebase.
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.