How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
triggerdotdevCLAUDE.mdtriggerdotdev/trigger.dev/docs/CLAUDE.md
Documentation Mintlify-based documentation site for Trigger.dev. ## Configuration - Main config: `docs.json` - defines navigation, theme, metadata - Navigation structure: `docs.json` -> `navigation.dropdowns` -> groups -> pages ## Writing Docs Pages are MDX files. Frontmatter format: ```yaml
ag-ui-protocolCLAUDE.mdag-ui-protocol/ag-ui/CLAUDE.md
including the AG-UI Dojo demo viewer - `/sdks/python/`: Python implementation of the protocol - `/docs/`: Documentation site content ### Integration Pattern Each framework integration follows a similar pattern: 1. Implements the AbstractAgent
img2threejsCLAUDE.mdimg2threejs/img2threejs/CLAUDE.md
packs. - Keep claims honest: distinguish implemented capability from roadmap or design-only documentation. - Treat `forge/` as deterministic tooling and `grimoire/` as routed reference material. - Keep backward compatibility for existing sculpt
chenhg5CLAUDE.mdchenhg5/cc-connect/CLAUDE.md
sync.Mutex` or `atomic` types - Use `context.Context` for cancellation propagation - Channels should have clear ownership; document who closes them - Prefer `sync.Once` for one-time teardown (`pendingPermission.resolve()`) ### 7. i18n All user-facing
MicrosoftCLAUDE.mdmicrosoft/playwright-python/CLAUDE.md
scripts/update_api.sh`) and abort if either side is out of sync. - `scripts/expected_api_mismatch.txt` — explicit allowlist of "documented in JS, not in Python" or "named differently in Python" gaps. Lines that no longer
yusufkaraaslanCLAUDE.mdyusufkaraaslan/Skill_Seekers/CLAUDE.md
claude.ai/code) when working with code in this repository. ## Project Overview **Skill Seekers** converts documentation from 18 source types into production-ready formats for 21+ AI platforms (LLM platforms
walkinglabsCLAUDE.mdwalkinglabs/learn-harness-engineering/CLAUDE.md
course on building reliable coding environments for AI agents. The repo contains a VitePress documentation site plus hands-on project code. ## Commands ```sh # Documentation site npm install npm run docs
coleam00CLAUDE.mdcoleam00/context-engineering-intro/claude-code-full-guide/CLAUDE.md
ready code - `develop` - Integration branch for features - `feature/*` - New features - `fix/*` - Bug fixes - `docs/*` - Documentation updates - `refactor/*` - Code refactoring - `test/*` - Test additions or fixes ### Commit Message Format Never include claude
coleam00CLAUDE.mdcoleam00/context-engineering-intro/CLAUDE.md
Google style: ```python def example(): """ Brief summary. Args: param1 (type): Description. Returns: type: Description. """ ``` ### 📚 Documentation & Explainability - **Update `README.md`** when new features are added, dependencies change, or setup steps are modified
nanobrowserCLAUDE.mdnanobrowser/nanobrowser/CLAUDE.md
Navigating to $URL$", "placeholders": { "url": { "content": "$1", "example": "https://example.com" } } } } ``` **Guidelines:** - Use descriptive, self-documenting key names - Separate user-facing strings from internal/log strings - Follow hierarchical naming for maintainability
Wei-ShawCLAUDE.mdWei-Shaw/claude-relay-service/CLAUDE.md
ALWAYS prefer editing an existing file to creating a new one. NEVER proactively create documentation files (\*.md) or README files. Only create documentation files if explicitly requested by the User
corsairdevCLAUDE.mdcorsairdev/corsair/CLAUDE.md
docs.corsair.dev/llm-gateway. ## Product note The hosted product moved from `corsairdev/hosted` to `corsairdev/hub`. `hosted` receives documentation updates only
Orchestra-ResearchCLAUDE.mdOrchestra-Research/AI-Research-SKILLs/CLAUDE.md
format: ``` skill-name/ ├── SKILL.md # Main guidance (200-600 lines with YAML frontmatter) ├── references/ # Deep documentation (300KB+ target) │ ├── README.md # From official docs │ ├── api.md # API reference │ ├── tutorials.md # Step-by-step guides │ ├── issues.md
0xJackyCLAUDE.md0xJacky/nginx-ui/CLAUDE.md
flaky failures - Keep files modular and well-organized by functionality - **All comments and documentation must be in English** ## Frontend (Vue.js) Development ### Technology Stack - **TypeScript** for all code - **Vue 3** with
humanlayerCLAUDE.mdhumanlayer/humanlayer/CLAUDE.md
tools - `humanlayer-ts-vercel-ai-sdk/` - Specialized integration for Vercel AI SDK - `docs/` - Mintlify documentation site ### Core Concepts - **Contact Channels**: Slack, Email, CLI, and web interfaces for human interaction - **Multi
JeffallanCLAUDE.mdJeffallan/claude-skills/CLAUDE.md
scope`: `implementation` | `review` | `design` | `system-design` | `testing` | `analysis` | `infrastructure` | `optimization` | `architecture` - `output-format`: `code` | `document` | `report` | `architecture` | `specification` | `schema` | `manifests` | `analysis` | `analysis-and-code` | `code+analysis` - `related-skills`: Comma-separated
zubair-trabzadaCLAUDE.mdzubair-trabzada/geo-seo-claude/CLAUDE.md
user's own working directory and deliverables land there — never in this repo. Deep documentation already lives in [`docs/`](docs/) — read it before large changes and keep it in sync
mcp-useCLAUDE.mdmcp-use/mcp-use/docs/CLAUDE.md
Documentation instructions ## TypeScript documentation - Make all TypeScript documentation changes under `docs/v2/typescript/`. - Add new TypeScript pages to the v2 TypeScript navigation in `docs/docs.json`. - Update existing v2 TypeScript pages instead of their
JetBrainsCLAUDE.mdJetBrains/ideavim/CLAUDE.md
CommandKeyConsumer after plugin disable/enable`). ## Additional Documentation - Changelog maintenance: Handled by the `changelog` skill (auto-detected when updating changelog) ## Active Technologies - Kotlin (JVM 21) + IntelliJ Platform SDK, IdeaVim vim-engine
MicrosoftCLAUDE.mdmicrosoft/UFO/documents/docs/configuration/models/claude.md
/system/agents_config.md) - Complete agent settings reference - [Model Configuration Overview](overview.md) - Compare different LLM providers - [Anthropic Documentation](https://docs.anthropic.com/) - Official Claude API docs ## Step 4: Start Using UFO After configuration
A file Claude Code reads at the start of every session. It holds the commands, conventions and warnings the agent needs for this project.
At the repository root. Claude Code also reads CLAUDE.md files in subdirectories when it works there.
Build and test commands, the project's layout, conventions that aren't obvious from the code, and mistakes to avoid. Short files tend to work better than long ones.
Claude Code reads CLAUDE.md; most other agents read AGENTS.md. Many projects keep one and point the other at it.
