How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
phurynCLAUDE.mdphuryn/pm-skills/CLAUDE.md
Claude agents) ├── CONTRIBUTING.md <- contributor guidelines ├── README.md <- public documentation (GitHub) ├── LICENSE <- MIT ├── validate_plugins.py <- plugin validator ├── tests/ <- unit + docs-consistency tests (unittest) └── pm-{name}/ <- 9 plugin directories ├── .claude-plugin/plugin.json <- per-plugin
DonchitosCLAUDE.mdDonchitos/Claude-Code-Game-Studios/CCGS Skill Testing Framework/CLAUDE.md
CCGS Skill Testing Framework — Claude Instructions This folder is the quality assurance layer for the Claude Code Game Studios skill/agent framework. It is self-contained and separate from any game
DonchitosCLAUDE.mdDonchitos/Claude-Code-Game-Studios/src/CLAUDE.md
File Extension Routing. When in doubt, use the primary engine specialist configured in `CLAUDE.md`. ## Tests Tests live in `tests/` — not in `src/`. Run `/test-setup` to scaffold the test framework
alirezarezvaniCLAUDE.mdalirezarezvani/claude-skills/agents/CLAUDE.md
Agile product ownership and backlog management | | [cs-ux-researcher](product/cs-ux-researcher.md) | Product | UX research, usability testing, design insights | | [cs-product-analyst](product/cs-product-analyst.md) | Product | Product analytics, KPI design, experiment design | | [cs-engineering
alirezarezvaniCLAUDE.mdalirezarezvani/claude-skills/CLAUDE.md
coverage expansion** — public audit record `audit/productivity-2026-07/` (all 7 legacy skills scored, 24/24 scripts smoke-tested, coverage map vs the personal-productivity canon) + 3 gap-filling plugins, each with
alirezarezvaniCLAUDE.mdalirezarezvani/claude-skills/c-level-advisor/CLAUDE.md
board-prep` | Board meeting preparation | | `/em:hard-call` | Framework for hard decisions | | `/em:stress-test` | Stress-test any assumption | | `/em:postmortem` | Honest retrospective | ## Key Design Decisions - **Two-layer memory
alirezarezvaniCLAUDE.mdalirezarezvani/claude-skills/engineering-team/CLAUDE.md
zones - **gcp-cloud-architect** — GCP infrastructure design, Terraform modules, cloud-native patterns - **security-pen-testing** — Penetration testing methodology, vulnerability assessment, exploit analysis - **snowflake-development** — Snowflake data warehouse development, SQL optimization
alirezarezvaniCLAUDE.mdalirezarezvani/claude-skills/product-team/CLAUDE.md
Sample Size Calculator (`experiment-designer/scripts/sample_size_calculator.py`) **Purpose:** Statistical sample size planning for A/B tests and experiments **Features:** - Minimum detectable effect (MDE) calculation - Absolute and relative effect size modes - Power analysis
alirezarezvaniCLAUDE.mdalirezarezvani/claude-skills/standards/CLAUDE.md
standards/` **Available Standards:** 1. **communication/** - Communication principles and response protocols 2. **quality/** - Code quality, testing, and validation standards 3. **git/** - Git workflow, conventional commits, branching strategy 4. **documentation/** - Markdown quality
alirezarezvaniCLAUDE.mdalirezarezvani/claude-skills/templates/CLAUDE.md
agents/domain/cs-new-agent.md # 2. Customize for your agent vim agents/domain/cs-new-agent.md # 3. Follow template structure exactly # 4. Test relative paths and integrations # 5. Commit with conventional commit git commit -m "feat(agents): implement
VoltAgentCLAUDE.mdVoltAgent/awesome-claude-code-subagents/CLAUDE.md
Language/framework experts (TypeScript, Python, etc.) 03-infrastructure/ # DevOps, cloud, Kubernetes, etc. 04-quality-security/ # Testing, security auditing, code review 05-data-ai/ # ML, data engineering, AI specialists 06-developer-experience
activepiecesCLAUDE.mdactivepieces/activepieces/CLAUDE.md
isNil()`, `spreadIfDefined()`, `spreadIfNotUndefined()`, `ActivepiecesError({ code, params })`, `SeekPage `, `formErrors`, `BaseModelSchema`, `chunk()`, `partition()`, `unique()`, `omit()`, `sanitizeObjectForPostgresql()` ## Testing ```bash npm run test-unit # Vitest: engine + shared npm run test-api # API integration
mksgluCLAUDE.mdmksglu/context-mode/CLAUDE.md
I/O-bound work (network calls, API queries). **Keep concurrency 1** for CPU-bound (npm test, build, lint) or commands sharing state (ports, lock files, same-repo writes). GitHub API rate-limit
SuperClaude-OrgCLAUDE.mdSuperClaude-Org/SuperClaude_Framework/CLAUDE.md
directly. ### Required Commands ```bash # All Python operations must use UV uv run pytest # Run tests uv run pytest tests/pm_agent/ # Run specific tests uv pip install package # Install dependencies
microCLAUDE.mdmicro/go-micro/CLAUDE.md
microservice is automatically accessible to AI agents via the Model Context Protocol (MCP). ## Build & Test ```bash # Run all tests make test # Run tests for a specific package go test ./gateway/mcp
czlonkowskiCLAUDE.mdczlonkowski/n8n-mcp/CLAUDE.md
validate # Validate node data in database npm run dev # build + rebuild + validate # Testing npm test # Run all tests (vitest) npm run test:unit # Unit tests only npm run test:integration
claude-code-bestCLAUDE.mdclaude-code-best/claude-code/CLAUDE.md
TypeScript strict mode is enforced — **`bun run precheck` 必须零错误通过**（包含 typecheck + lint fix + test）。 ## Git Commit Message Convention 使用 **Conventional Commits** 规范： ``` : <描述> ``` 常见 type：`feat`、`fix`、`docs`、`chore`、`refactor
vxcontrolCLAUDE.mdvxcontrol/pentagi/CLAUDE.md
number, and 1 special character from `!@#$&*`. ## Project Overview **PentAGI** is an automated security testing platform powered by AI agents. It runs autonomous penetration testing workflows using a multi-agent system
teng-linCLAUDE.mdteng-lin/notebooklm-py/CLAUDE.md
Commands See [docs/installation.md](docs/installation.md) for the full installation guide. ```bash # Contributor install (matches CI test jobs): uv sync --frozen --extra browser --extra dev --extra markdown \ --extra mcp --extra server --extra
getpaseoCLAUDE.mdgetpaseo/paseo/CLAUDE.md
teardown invariants, and Parcel comparison | | [docs/testing.md](docs/testing.md) | TDD workflow, determinism, real dependencies over mocks, test organization | | [docs/qa.md](docs/qa.md) | QA evidence bar for pull requests — platform matrix, version drift, performance
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.
