How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
affaan-mCLAUDE.mdaffaan-m/ECC/CLAUDE.md
related files: | File(s) | Skill | |---------|-------| | `README.md` | `/readme` | | `.github/workflows/*.yml` | `/ci-workflow` | | `*.tsx`, `*.jsx`, `components/**` | `react-patterns`, `react-testing` — for React-specific work invoke `/react-review`, `/react-build`, `/react-test` | When spawning subagents, always pass
nextlevelbuilderCLAUDE.mdnextlevelbuilder/ui-ux-pro-max-skill/CLAUDE.md
Best practices and anti-patterns - `icons` - Icon recommendations with import code (Phosphor, Heroicons, Lucide) - `react` - React/Next.js performance patterns - `web` - App interface guidelines (iOS/Android/React Native) - `google-fonts` - Individual Google Fonts lookup
nextlevelbuilderCLAUDE.mdnextlevelbuilder/ui-ux-pro-max-skill/stack/CLAUDE.md
tells you the exact command form. - Optional: 21st.dev **Magic** MCP (`@21st-dev/magic`) generates React components from a prompt but needs an API key — see `docs/SETUP.md`. It is intentionally left
danny-avilaCLAUDE.mddanny-avila/LibreChat/CLAUDE.md
organized into three sections: 1. **Package imports** — sorted shortest to longest line length (`react` always first). 2. **`import type` imports** — sorted longest to shortest (package types first, then local types
alirezarezvaniCLAUDE.mdalirezarezvani/claude-skills/c-level-advisor/CLAUDE.md
advisor/` | Tree of Thought | strategy_analyzer, financial_scenario_analyzer | | **CTO** | `cto-advisor/` | ReAct | tech_debt_analyzer, team_scaling_calculator | | **COO** | `coo-advisor/` | Step by Step | ops_efficiency_analyzer, okr_tracker
alirezarezvaniCLAUDE.mdalirezarezvani/claude-skills/engineering-team/CLAUDE.md
/scripts/project_scaffolder.py`) **Purpose:** Production-ready project scaffolding for modern stacks **Supported Stacks:** - Next.js + GraphQL + PostgreSQL - React + REST + MongoDB - Vue + GraphQL + MySQL - Express + TypeScript + PostgreSQL **Features:** - Docker Compose configuration - CI/CD pipeline (GitHub
alirezarezvaniCLAUDE.mdalirezarezvani/claude-skills/markdown-html/CLAUDE.md
output (separate CSS / JS / image folders). Single file or nothing. - ❌ External JS framework runtimes (React, Vue, Svelte, Alpine). Vanilla JS + IntersectionObserver only. - ❌ Silently overwriting existing output files. `output_path_resolver.py` suffixes
getpaseoCLAUDE.mdgetpaseo/paseo/CLAUDE.md
terminology — UI label wins, no synonyms | | [docs/coding-standards.md](docs/coding-standards.md) | Type hygiene, error handling, state design, React patterns, file organization | | [docs/design.md](docs/design.md) | Design system — tokens, buttons, hierarchy, density, alignment rails, states, what
open-metadataCLAUDE.mdopen-metadata/OpenMetadata/CLAUDE.md
Docker infrastructure. ## Stack at a glance - **Backend**: Java 21 + Dropwizard, multi-module Maven. - **Frontend**: React + TypeScript, built with **Vite** (dev server on :3000); component library `openmetadata-ui-core-components
open-metadataCLAUDE.mdopen-metadata/OpenMetadata/openmetadata-ui-core-components/CLAUDE.md
openmetadata/ui-core-components Shared UI component library for OpenMetadata, built on UntitledUI design system patterns with React Aria Components as the accessibility foundation. ## Package Overview - **Package name**: `@openmetadata/ui-core-components` - **Source root**: `src/main/resources/ui/src/` - **Build
walkinglabsCLAUDE.mdwalkinglabs/learn-harness-engineering/CLAUDE.md
pack - `docs-readme/` — localized README translations (one directory per locale) - `projects/shared/` — Shared Electron + TypeScript + React foundation - `projects/project-NN/` — Per-project `starter/` and `solution/` directories (project-01 through project-06; project
humanlayerCLAUDE.mdhumanlayer/humanlayer/CLAUDE.md
Model Context Protocol) server for Claude integration - `humanlayer-wui/` - CodeLayer - Desktop/Web UI (Tauri + React) for graphical approval management - `claudecode-go/` - Go SDK for programmatically launching Claude Code sessions ### Architecture Flow
humanlayerCLAUDE.mdhumanlayer/humanlayer/humanlayer-wui/CLAUDE.md
responding to approval requests. It's built with Tauri for desktop packaging and React for the interface. When the WUI is running, logs are written to: - Development: `~/.humanlayer/logs/wui-{branch
JeffallanCLAUDE.mdJeffallan/claude-skills/CLAUDE.md
yaml # YAML checks only python scripts/validate-skills.py --check references # Reference checks only python scripts/validate-skills.py --skill react-expert # Single skill python scripts/validate-skills.py --format json # JSON output for CI python scripts/validate-skills.py --help # Full
jnMetaCodeCLAUDE.mdjnMetaCode/superpowers-zh/CLAUDE.md
没有它，skill 就是死重 —— 文件在磁盘上但永远不会被调用。 **验收测试。** 在新 harness 里开一个干净 session，发这条用户消息： > Let's make a react todo list 可工作的集成会在写任何代码之前自动触发 `brainstorming` skill。把完整 transcript 贴在 PR 里。 **以下情况不算真正集成，会被关闭：** - 手动把 skill 文件拷进
WenyuChiouCLAUDE.mdWenyuChiou/awesome-agentic-ai-zh/CLAUDE.md
runs on every 4 GB machine. | | **`qwen2.5:3b`** | Stages 3–6 (tool use / agent / ReAct) | 1.9 GB, **reliable tool-use support** (OpenAI function-calling format), default for the current function
airweave-aiCLAUDE.mdairweave-ai/airweave/CLAUDE.md
with four main components: - **Backend** (`backend/`): Python 3.13, FastAPI, SQLAlchemy async, PostgreSQL - **Frontend** (`frontend/`): React 18, TypeScript, Vite, ShadCN UI, TailwindCSS - **Workers**: Temporal for async sync orchestration, Redis for pub/sub
ChrisWilesCLAUDE.mdChrisWiles/claude-code-showcase/CLAUDE.md
CLAUDE.md file showing how to configure Claude Code for your project. ## Quick Facts - **Stack**: React, TypeScript, Node.js - **Test Command**: `npm test` - **Lint Command**: `npm run lint` - **Build Command
ZSeven-WCLAUDE.mdZSeven-W/openpencil/CLAUDE.md
viewer SDK (wraps the op-host-web wasm bundle) ├── op-web-sdk-react/ React 19 adapter for op-web-sdk └── op-web-sdk-vue/ Vue 3 adapter
ZSeven-WCLAUDE.mdZSeven-W/openpencil/packages/CLAUDE.md
engine, pen-renderer, pen-figma, pen-mcp, pen-ai-skills, pen-sdk, pen-react, pen-acp) and pen-codegen were **retired** along with `apps/*`. Their functionality now lives
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.
