How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
MicrosoftCLAUDE.mdmicrosoft/playwright-cli/CLAUDE.md
Commit Convention Semantic commit messages: `label(scope): description` Labels: `fix`, `feat`, `chore`, `docs`, `test`, `devops` ```bash git checkout -b fix-39562 # ... make changes ... git add git commit
Model Context ProtocolCLAUDE.mdmodelcontextprotocol/typescript-sdk/CLAUDE.md
guidance to Claude Code (claude.ai/code) when working with code in this repository. ## Build & Test Commands ```sh pnpm install # Install all workspace dependencies pnpm build:all # Build all packages pnpm
Model Context ProtocolCLAUDE.mdmodelcontextprotocol/typescript-sdk/test/e2e/CLAUDE.md
test suite Conformance-style tests for the SDK's public surface. `requirements.ts` is a pure-data manifest: every behavior the SDK must satisfy, with its spec/source link. Test files
EverMind-AICLAUDE.mdEverMind-AI/EverOS/CLAUDE.md
make lint # ruff (check + format-check) + import-linter make format # auto-fix formatting make test # pytest tests/unit make integration # pytest tests/integration make ci # full CI: lint + test + integration ``` ## Architecture
Wei-ShawCLAUDE.mdWei-Shaw/claude-relay-service/CLAUDE.md
格式化** → `npx prettier --write <修改的文件>` 4. **检查** → `npm run lint` 5. **测试** → `npm test` 6. **验证** → `npm run cli status` 确认服务正常 ### 测试规范 - 测试文件在 `tests/` 目录，命名 `*.test.js` 或 `*.spec.js` - 使用
corsairdevCLAUDE.mdcorsairdev/corsair/CLAUDE.md
docs/pr-review-bot.md`). ## Commands - `pnpm lint` / `pnpm lint:fix` (biome), `pnpm typecheck`, `pnpm build`, `pnpm test` - `pnpm generate:plugin` — scaffold a new plugin (correct footprint: its own package + one registration edit
zilliztechCLAUDE.mdzilliztech/claude-context/CLAUDE.md
package ``` Packages depend on `core` via `workspace:*`, so **rebuild core (`pnpm build:core`) before testing mcp/vscode against core changes** — they consume `core/dist`, not its source. ### Tests - **core** uses Jest
mrexodiaCLAUDE.mdmrexodia/ida-pro-mcp/CLAUDE.md
signature creation, scanning, xref signatures (uses sigmaker.py) - `api_debug.py`: debugger control, unsafe / low priority for tests - `api_python.py`: execute Python in IDA context - `api_resources.py`: `ida://` MCP resources ## Core implementation rules ### IDA thread
Orchestra-ResearchCLAUDE.mdOrchestra-Research/AI-Research-SKILLs/CLAUDE.md
level deep from SKILL.md - Check documentation size: `du -sh skill-name/references/` 6. **Test the skill** with real use cases before submitting ### Improving Existing Skills When updating skills: 1. **Maintain
BeehiveInnovationsCLAUDE.mdBeehiveInnovations/pal-mcp-server/CLAUDE.md
these instructions to efficiently run quality checks, manage the server, check logs, and run tests. ## Quick Reference Commands ### Code Quality Checks Before making any changes or submitting PRs, always
MemTensorCLAUDE.mdMemTensor/MemOS/CLAUDE.md
integration-tester` | Read-write | Author and run integration / end-to-end cases under `tests/` | The main repo has no frontend stack, so no `frontend-dev` is provided; TypeScript sub-projects
0xJackyCLAUDE.md0xJacky/nginx-ui/CLAUDE.md
database pagination for large datasets - Before committing backend changes, run the CI-equivalent unit test command: `GOWORK=off go test -tags=unembed -race -cover -count=1 ./...` - Keep `-count
humanlayerCLAUDE.mdhumanlayer/humanlayer/CLAUDE.md
Quick Actions - `make setup` - Resolve dependencies and installation issues across the monorepo - `make check-test` - Run all checks and tests - `make check` - Run linting and type checking - `make test
humanlayerCLAUDE.mdhumanlayer/humanlayer/hld/CLAUDE.md
ORDER BY created_at DESC LIMIT 5;" ``` To clone nightly database to dev for testing: ```bash make clone-nightly-db-to-dev-db # Backs up existing dev db and copies
humanlayerCLAUDE.mdhumanlayer/humanlayer/humanlayer-wui/CLAUDE.md
typecheck`. - DO provide a manual list of steps for a human to test new UI changes. ## Guidelines - In React 19, ref is now available as a standard prop for functional
humanlayerCLAUDE.mdhumanlayer/humanlayer/scripts/CLAUDE.md
instead of Node.js. - Use `bun ` instead of `node ` or `ts-node ` - Use `bun test` instead of `jest` or `vitest` - Use `bun build <file.html|file.ts|file.css>` instead of `webpack` or `esbuild
JeffallanCLAUDE.mdJeffallan/claude-skills/CLAUDE.md
description:** ```yaml description: Use for debugging. First investigate root cause, then analyze patterns, test hypotheses, and implement fixes with tests. ``` **GOOD - Capability + trigger:** ```yaml description: Diagnoses bugs through root cause
Hugging FaceCLAUDE.mdhuggingface/chat-ui/CLAUDE.md
formatting (Prettier) and linting (ESLint) npm run format # Auto-format with Prettier npm run test # Run all tests (Vitest) ``` ### Running a Single Test ```bash npx vitest run path/to/file.spec.ts # Run specific
zubair-trabzadaCLAUDE.mdzubair-trabzada/geo-seo-claude/CLAUDE.md
documentation (keep in sync with code) | | `examples/` | Sample audit outputs, proposals, demo CRM data | | `tests/` | Test suite (see [Testing](#testing)) | | `white-label/` | Agency rebranding config (`brand_config.py`, `brand.example.json`) | | `install.sh` / `install-win.sh` / `uninstall.sh
JetBrainsCLAUDE.mdJetBrains/ideavim/CLAUDE.md
with IdeaVim. ## Quick Reference Essential commands: - `./gradlew runIde` - Start dev IntelliJ with IdeaVim - `./gradlew test -x :tests:property-tests:test -x :tests:long-running-tests:test` - Run standard tests Avoid
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.
