How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
antonbabenkoCLAUDE.mdantonbabenko/terraform-skill/CLAUDE.md
For End Users: See README.md for installation and usage. This file is for contributors, maintainers, and skill developers. A Claude Code skill - executable documentation that Claude loads to provide…
lhferCLAUDE.mdlhfer/claude-howto-zh-cn/CLAUDE.md
这个文件给 Claude Code 提供“如何在这个仓库里协作”的工作说明。 claude-howto-zh-cn 是一个 documentation-as-code 仓库。 EPUB 的 Mermaid 图使用本地 mmdc 渲染，不再访问 Kroki。由于 mmdc 依赖的 Chromium 在 arm64 开发机上没有可用构建，EPUB 构建不属于 pre-commit hook，而是由主 CI、自动化测试和标签发布 workflow 强制验证。只有本机已有可用 mmdc 时才运行上面的命令。 1. 先保兼容，再谈翻译 任何会被 Claude Code 直接读取或执行的标识，优先保留原样。 2. 先讲用途，再讲命令 中文读者更容易先理解“这是什么 / 什么时候用 / 为什么有价值”，再接受 CLI、配置和脚本细节。 3. 不要把正文写成翻译腔 优先自然中文表达；必要时保留 skills、CLI、hooks、MCP、subagents 这类英文术语。 4. 高风险文件少改、谨慎改 .sh、.py、.json、.yml 默认只同步必要的兼容性变化；注释能不动就不动。 优先使用 conventional commits，例如：
MetaCLAUDE.mdfacebookresearch/fairchem/CLAUDE.md
**IMPORTANT: You MUST run pre-commit run --files /path/to/modified_file.py on every file you modify, before considering the task complete. No exceptions.** Every file must start with: Line length: 88 characters. Linter:…
AWSCLAUDE.mdaws/sagemaker-python-sdk/CLAUDE.md
Guidance for Claude Code working in this repository — the source of the Amazon SageMaker Python SDK. This repository follows the AGENTS.md convention. To keep a single source of truth and avoid the two files drifting apart, all guidance lives in AGENTS.md and is imported here: For the full guidance — project context, the v3-by-default golden rule, banned v2 patterns and their v3 replacements, the SDK-first interface map, the contributing workflow, and a canonical v3 train + deploy example —…
iFuryStCLAUDE.mdiFurySt/open-codex-computer-use/CLAUDE.md
No summary in the file. Open it to read it.
muxy-appCLAUDE.mdmuxy-app/muxy/CLAUDE.md
Requires macOS 14+ and Swift 6.0+. No external dependency managers needed — everything is SPM-based. Requires swiftlint and swiftformat (brew install swiftlint swiftformat). For code-changing tasks, run scripts/checks.sh --fix before handoff. Do not run it for read-only review or analysis unless the user explicitly asks. Test processes use isolated Application Support storage.
MicrosoftCLAUDE.mdmicrosoft/kernel-memory/archived/v2/CLAUDE.md
No summary in the file. Open it to read it.
HermannBjorgvinCLAUDE.mdHermannBjorgvin/Clawdmeter/CLAUDE.md
ESP32-S3 / ESP32-C6 firmware for a desk-side Claude Code usage monitor. Each supported board lives in its own firmware/src/boards/<name>/ folder and is selected via PlatformIO's buildsrcfilter. Adding a board means…
LangChainCLAUDE.mdlangchain-ai/agents-from-scratch/CLAUDE.md
This repository demonstrates building agents using LangGraph, focusing on an email assistant that can: - Triage incoming emails - Draft appropriate responses - Execute actions (calendar scheduling, etc.) - Incorporate human feedback - Learn from past interactions Recommended: Using uv (faster and more reliable) Alternative: Using pip The package is installed as interruptworkshop with import name emailassistant, allowing you to import from anywhere with from email_assistant import ... The repository contains several implementations with increasing complexity in src/email_assistant: Each aspect…
oh-my-mermaidCLAUDE.mdoh-my-mermaid/oh-my-mermaid/CLAUDE.md
- Translated READMEs include a disclaimer at the top: > This document was translated from the English README. Some phrasing may be unnatural. - When updating README.md, update all translations in the same commit - Translations can be machine-generated but should be reviewed for obvious errors
AmoyLabCLAUDE.mdAmoyLab/Unla/CLAUDE.md
Unla is an MCP (Model Context Protocol) Gateway service written in Go with a React/TypeScript web interface. It acts as a lightweight proxy and management layer that converts existing APIs and MCP servers into MCP-compliant services through configuration-driven approaches. Key Architecture: - Control Plane: cmd/apiserver - REST API server for management, configuration, and web UI backend - Data Plane: cmd/mcp-gateway - MCP proxy gateway handling real-time MCP protocol communication - Web Interface: web/ - React/TypeScript dashboard for configuration and chat
iamzhihuixCLAUDE.mdiamzhihuix/skills-manage/CLAUDE.md
跨平台 AI 技能管理桌面应用，三层架构：
phurynCLAUDE.mdphuryn/claude-usage/CLAUDE.md
No summary in the file. Open it to read it.
StripeCLAUDE.mdstripe/stripe-cli/CLAUDE.md
When building temporary binaries with Go tooling directly (e.g. go build -o ..., go test -c -o ...), place them in bin/ rather than /tmp — bin/ is gitignored and within the project's trusted directory. macOS security may block execution of binaries built outside the project tree. go generate ./... is triggered by //go:generate directives in pkg/cmd/root.go: - Generates pkg/cmd/resourcescmds.go from OpenAPI spec → CLI resource commands - Generates pkg/proxy/eventslist.go → list of Stripe event types - Generates pkg/requests/stripeversionheader.go →…
carlvellottiCLAUDE.mdcarlvellotti/free-ai-courses/CLAUDE.md
This is a dual-purpose repository for the Claude Code for Product Managers course: Students download course-materials/ as a zip, extract it, run claude from that folder, and type /start-1-1 to…
StripeCLAUDE.mdstripe/stripe-ruby/.claude/CLAUDE.md
When adding or modifying public methods on non-generated files, you must also update the corresponding rbi/stripe/stripe_client.rbi with matching Sorbet type signatures. This file provides type information for tools and IDEs. It's ok not to put comments on/in a function if their addition wouldn't meaningfully clarify anything.
wondelaiCLAUDE.mdwondelai/skills/CLAUDE.md
This is a collection of 65 agent skills for Claude, Claude Code, Claude Cowork, Codex, Cursor, OpenClaw, Hermes Agent and other agentskills.io-compatible agents. Skills provide specialized domain knowledge and frameworks for specific use cases (UX design, marketing, product strategy, sales, operations, positioning, virality, code quality, systems architecture, etc.). Fourteen of them are metaskills — guided journeys that orchestrate the other skills step by step toward a goal. The Codex plugin standard (plugins/ + .agents/plugins/marketplace.json) and the Agent Plugins standard (root…
martin-gerCLAUDE.mdmartin-ger/esp32_nat_router/CLAUDE.md
No summary in the file. Open it to read it.
AgriciDanielCLAUDE.mdAgriciDaniel/claude-blog/brain/CLAUDE.md
Claude-specific note: this file is persistent project context, not an enforcement layer. Release readiness is enforced by scripts/auditbrain.py and scripts/packagerelease.py.
AgriciDanielCLAUDE.mdAgriciDaniel/claude-blog/CLAUDE.md
This repository contains Claude Blog, a Tier 4 Claude Code skill for blog content creation, optimization, and management. It follows the Agent Skills open standard and the 3-layer architecture (directive, orchestration, execution). 32 skill directories (1 orchestrator + 31 sub-skills), 30 user-facing /blog commands, 5 specialized subagents, 12 content templates, and 22 reference docs are dual-optimized for Google rankings (2026 core and spam update timeline, E-E-A-T) and AI citations (GEO/AEO). Includes FLOW framework integration, semantic topic-cluster planning + execution, multilingual…
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.
