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.
Keeps ingestion repository and published GPT-RAG documentation aligned with shipped formats, configuration, indexing, deployment, audit, and operator behavior.
Searches across your Notion workspace, synthesizes findings from multiple pages, and creates comprehensive research documentation saved as new Notion pages. Turns scattered information into structured reports with proper citations and actionable insights.
Reviews Lumpcode CLI documentation in packages/apps/cli/DOCS for concision, coverage gaps, and quality relative to sibling docs and product behavior. Use when improving CLI DOCS markdown, auditing a specific file in that folder, or when the user invokes documentation review for packages/apps/cli/DOCS.
Create, audit, or consolidate durable project documentation, including feature rules, contracts, workflows, and runbooks. Use when documentation is the main deliverable; routine code changes can update their owning docs directly.
Writing clear, discoverable software documentation following the Eight Rules and Diataxis framework. Use when creating README files, API docs, tutorials, how-to guides, or any project documentation. Automatically enforces docs/ location, linking requirements, and runnable examples.
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.
Write, revise, and review software documentation including READMEs, architecture docs, API docs, examples, troubleshooting guides, and release notes. Use when the user asks to create docs, update docs after code changes, improve documentation clarity, document project workflows, or invokes this skill by name; when invoked without a target, infer the documentation task from current repo context and start working.
Research across Notion and synthesize into structured documentation; use when gathering info from multiple Notion sources to produce briefs, comparisons, or reports with citations.
Documentation best practices including Markdown formatting, generated PNG diagrams, technical writing, ADRs, Docusaurus and MDX documentation sites, and open source standards. Use when writing documentation, README files, Markdown or MDX content, creating static diagrams for Markdown, configuring Docusaurus, or asking about documentation structure, technical writing, or open source project setup. For interactive React Flow canvases in a SPA, use the reactflow-architecture-diagrams skill instead.
Generate, update, and maintain per-module documentation under docs/modules/, keep docs/ARCHITECTURE.md and README.md current, and produce Mermaid diagrams for data-flow, block, and dependency views. USE FOR: documenting a package; updating architecture docs after structural changes; generating diagrams; auditing documentation freshness; first-time doc generation for the project. DO NOT USE FOR: writing implementation code; debugging runtime errors; updating AGENTS.md or .subagents/ guides (use agents-doc-lifecycle instead).
Use up-to-date library and framework docs via Context7 MCP instead of training data. Activates for setup questions, API references, code examples, or when the user names a framework (e.g. React, Next.js, Prisma).
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.