CLAUDE.md examples from real projects

fathahCLAUDE.md

hermes-desktop

fathah/hermes-desktop/CLAUDE.md

essence is always captured. ```markdown # Good Section Brief overview of what this section documents and why it matters. More detail can go in subsequent paragraphs, code blocks, or lists. ## Child

semaphoreuiCLAUDE.md

semaphore

semaphoreui/semaphore/.claude/CLAUDE.md

Claude Code Instructions # Documentation The documentation stored in /docs directory. It is a submodule with official Semaphore UI documentation in on Docusaurus engine. You should actualize the documentation

No other project uses it yet

phpstanCLAUDE.md

phpstan

phpstan/phpstan/CLAUDE.md

infrastructure. The actual source code lives at [phpstan/phpstan-src](https://github.com/phpstan/phpstan-src). - **Website:** https://phpstan.org/ - **Documentation:** https://phpstan.org/user-guide/getting-started - **API Reference:** https://apiref.phpstan.org/ ## Repository Structure ``` ├── phpstan # CLI entry point (shell script

phpstanCLAUDE.md

phpstan / website

phpstan/phpstan/website/CLAUDE.md

global data files - `src/_posts/` — Blog posts (Markdown) - `src/js/` — TypeScript source files - `src/user-guide/` — User guide documentation (Markdown) - `src/developing-extensions/` — Extension development docs - `src/writing-php-code/` — PHP writing guide - `src/app.pcss` — Main stylesheet (Tailwind + custom

567-labsCLAUDE.md

instructor

567-labs/instructor/CLAUDE.md

coverage run -m pytest tests/ -k "not docs"` then `uv run coverage report` - Build documentation: `uv run mkdocs serve` (for local preview) or `./build_mkdocs.sh` (for production) - Waiting: use `sleep

No other project uses it yet

formkitReads credentialsCLAUDE.md

auto-animate

formkit/auto-animate/.dmux-hooks/CLAUDE.md

dmux Hooks System - Agent Reference **Auto-generated documentation for AI agents** This document contains everything an AI agent needs to create, modify, and understand dmux hooks. It is automatically generated

borgbackupCLAUDE.md

borg

borgbackup/borg/.claude/CLAUDE.md

Always write pytest-style tests unless unittest-style is explicitly required. ## Writing docstrings, comments, documentation The docs shall always be in sync with the current code, algorithms and data structures

No other project uses it yet

browserlessReads credentialsCLAUDE.md

browserless

browserless/browserless/CLAUDE.md

interfaces (`BodySchema`, `QuerySchema`, `ResponseSchema`) that are automatically converted to: - Runtime JSON Schema validation - OpenAPI documentation (served at `/docs`) ### Docker Images Located in `docker/` with browser-specific Dockerfiles: - `base/` - Base image

No other project uses it yet

coleam00Pipes a download into a shellCLAUDE.md

context-engineering-intro / claude-code-full-guide

coleam00/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.md

context-engineering-intro

coleam00/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

yichuan-wPipes a download into a shellCLAUDE.md

LEANN

yichuan-w/LEANN/CLAUDE.md

enables semantic search across various data sources (emails, browser history, chat history, code, documents) on a single laptop without cloud dependencies. ## Build & Development Commands ### Quick install (pip) ```bash pip install

Orchestra-ResearchReads credentialsCLAUDE.md

AI-research-SKILLs

Orchestra-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

rybbit-ioCLAUDE.md

rybbit

rybbit-io/rybbit/docs/CLAUDE.md

rules in `content/partials/guides/README.md`; copy `TEMPLATE.mdx` for a new guide) ## Project Overview This is the documentation and marketing website for Rybbit, built with Next.js 16 and Fumadocs. The site includes: - Documentation

No other project uses it yet

DuarteSantos8Reads credentialsCLAUDE.md

openGym

DuarteSantos8/openGym/CLAUDE.md

Node, no framework), deps: @simplewebauthn/server, web-push. coach/ is the optional AI coach; openapi.yaml documents every route. web/ multi-stage Dockerfile (builds frontend → nginx) + nginx.conf.template (serves app, proxies /api

No other project uses it yet

glzr-ioCLAUDE.md

glazewm

glzr-io/glazewm/CLAUDE.md

other crates. - For logging, use `tracing` macros (e.g. `tracing::info!("...")`). - Functions should always be documented. - Use punctuation mark at the end of all comments. - If using unsafe features, include

humanlayerReads credentialsCLAUDE.md

humanlayer

humanlayer/humanlayer/CLAUDE.md

ticket just picka branch name `./scripts/create_worktree.sh three-short-words three-short-words` ### Library documentation research If you need up-to-date information about a library or dependency, use the HumanLayer

No other project uses it yet

Wei-ShawReads credentialsCLAUDE.md

claude-relay-service

Wei-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

maxrave-devReads credentialsCLAUDE.md

SimpMusic

maxrave-dev/SimpMusic/CLAUDE.md

questions, the AI agent **MUST** follow this research workflow: #### Step 1: Look up official documentation - Use **MCP Context7** (`resolve-library-id` → `query-docs`) to fetch up-to-date documentation

redpanda-dataCLAUDE.md

redpanda

redpanda-data/redpanda/CLAUDE.md

Configuration files - `proto/`: Protobuf definitions for Redpanda services and APIs - `.github/`, `.buildkite/`: CI/workflow automation - **Documentation:** [Docs site](https://redpanda.com/documentation) and `docs/`. ## Build, Test, and Validation Instructions ### Prerequisites (Always Perform

Evan-lczReads credentialsCLAUDE.md

DeepResearch-RAG

Evan-lcz/DeepResearch-RAG/CLAUDE.md

with parallel processing and comprehensive report generation. ## Repository Structure ### Root Directory - `README.md` - Comprehensive project documentation with quickstart guide - `pyproject.toml` - Python project configuration and dependencies - `langgraph.json` - LangGraph configuration defining the main