How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
SupabaseCLAUDE.mdsupabase/wrappers/CLAUDE.md
they were regular PostgreSQL tables. The project is maintained by [Supabase](https://supabase.com). **Documentation**: https://fdw.dev/ | **API Docs**: https://docs.rs/supabase-wrappers ## Repository Structure ``` wrappers/ ├── supabase-wrappers/ # Core FDW framework library
pocketpawCLAUDE.mdpocketpaw/pocketpaw/docs/CLAUDE.md
/code) when working with code in this repository. ## What This Is This is the documentation site for PocketPaw, a self-hosted AI agent. The docs are 120+ MDX files consumed
ferdinandobonsCLAUDE.mdferdinandobons/startup-skill/CLAUDE.md
SKILL.md # Main skill file (~476 lines, 8 phases + pre-flight & customer discovery) │ └── references/ # Supporting documents loaded on demand │ ├── research-principles.md │ ├── research-scaling.md │ ├── research-wave-1-market.md │ ├── research-wave-2-competitors.md │ ├── research-wave-3-customers.md │ ├── research-wave-4-distribution.md │ ├── research-synthesis.md │ ├── verification-agent.md │ ├── customer-interview.md │ ├── intake-questions.md │ ├── output-specs.md │ ├── frameworks.md
SentryCLAUDE.mdgetsentry/sentry-mcp/packages/mcp-core/src/internal/agents/tools/data/CLAUDE.md
files for namespaces that exist in the OpenTelemetry repository ## File Organization ``` data/ ├── CLAUDE.md # This documentation ├── gen_ai.json # Generative AI attributes ├── db.json # Database attributes ├── http.json # HTTP attributes ├── rpc.json # RPC attributes ├── messaging.json # Messaging
jdevalkCLAUDE.mdjdevalk/specification.website/CLAUDE.md
# CLAUDE.md — repo guidance for AI agents (and humans skimming) This file is read by
LeslieLeungCLAUDE.mdLeslieLeung/glean/CLAUDE.md
monorepo structure - always check your current working directory - You don't have to create documentation unless explicitly asked - Never run `make db-reset` without explicit user consent - Always write code
LeslieLeungCLAUDE.mdLeslieLeung/glean/frontend/CLAUDE.md
monorepo structure - always check your current working directory - You don't have to create documentation unless explicitly asked - Always write code comments in English - DO NOT modify anything within `frontend/packages/ui/src/components
wecode-aiCLAUDE.mdwecode-ai/Wegent/tests/CLAUDE.md
Wegent E2E Testing Guidelines This document contains guidelines for writing and maintaining E2E tests for the Wegent project. --- ## Rules ### Rule 1: Use data-testid for Element Selection **When locating page
alirezarezvaniCLAUDE.mdalirezarezvani/claude-code-skill-factory/CLAUDE.md
installing generated skills | | **[documentation/CLAUDE.md](documentation/CLAUDE.md)** | Templates and references structure | Working with templates or documentation | **How It Works**: Claude loads the most relevant CLAUDE.md based on your current task context, giving
alirezarezvaniCLAUDE.mdalirezarezvani/claude-code-skill-factory/claude-skills-examples/CLAUDE.md
definition with brand standards - `apply_brand.py` - Brand application module **Purpose**: Apply consistent corporate branding to documents (colors, fonts, layouts) **Key Class**: `BrandFormatter` - applies Acme Corporation brand standards **Pattern**: Brand definition (colors
alirezarezvaniCLAUDE.mdalirezarezvani/claude-code-skill-factory/documentation/CLAUDE.md
documentation/CLAUDE.md This file provides guidance for working with documentation, references, and factory templates in this repository. --- ## Documentation Structure The `documentation/` folder contains two main subdirectories: ### references/ Official documentation and reference
alirezarezvaniCLAUDE.mdalirezarezvani/claude-code-skill-factory/generated-skills/CLAUDE.md
declaring complete."** When generating skills in this folder: 1. Compare output against official Anthropic documentation 2. Check reference examples in `../documentation/references/` 3. Verify all required sections/fields are present (e.g., project
alirezarezvaniCLAUDE.mdalirezarezvani/claude-code-skill-factory/.github/CLAUDE.md
subtask issues 6. Begin implementation ``` **❌ WRONG - Too Many Tasks**: ``` User: "Create comprehensive Wiki documentation" DON'T DO THIS: - Create issue with 40+ tasks in checkboxes - Results in 40+ GitHub issues
borgheiCLAUDE.mdborghei/Claude-Skills/agents/CLAUDE.md
customer discovery | product-manager-toolkit | 407 | **Total**: 1,795 lines of comprehensive agent documentation **Template Available**: [templates/agent-template.md](../templates/agent-template.md) (318 lines) - Use this to create new agents ### Agent vs Skill | Aspect
borgheiCLAUDE.mdborghei/Claude-Skills/business-operations/CLAUDE.md
health: information architecture, doc ownership and freshness SLAs, duplication and orphan detection, and a documentation-debt backlog. Use when the wiki has decayed, docs are stale, or nobody can find
borgheiCLAUDE.mdborghei/Claude-Skills/CLAUDE.md
deployed by users into their AI coding workflows. ## Navigation Map This repository uses **modular documentation**. For domain-specific guidance, see: | Domain | CLAUDE.md Location | Focus | |--------|-------------------|-------| | **Agent Development** | [agents/CLAUDE.md](agents/CLAUDE.md) | cs-* agent
borgheiCLAUDE.mdborghei/Claude-Skills/c-level-advisor/CLAUDE.md
Resources - **CEO Advisor Skill:** `ceo-advisor/SKILL.md` - **CTO Advisor Skill:** `cto-advisor/SKILL.md` - **Main Documentation:** `../CLAUDE.md` --- **Last Updated:** November 5, 2025 **Skills Deployed:** 2/2 C-level skills production-ready **Focus
borgheiCLAUDE.mdborghei/Claude-Skills/data-analytics/CLAUDE.md
reporting 4. **analytics-engineer/** - Data pipeline design, dbt modeling, data warehouse architecture, testing, and documentation 5. **ml-ops-engineer/** - Model deployment, ML pipelines, model monitoring, feature stores, and infrastructure automation
borgheiCLAUDE.mdborghei/Claude-Skills/documents/CLAUDE.md
Documents Domain Production-grade document automation skills for the four Office formats Anthropic ships official skills for. Each toolkit reads OOXML or PDF directly using the Python standard library only
borgheiCLAUDE.mdborghei/Claude-Skills/hr-operations/CLAUDE.md
help` support - Handle sensitive data assumptions (tools process anonymized or aggregated data only) **Skill documentation must:** - Reference established HR methodologies (SHRM, Bersin, Mercer frameworks) - Include compliance considerations (EEOC, GDPR, local
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.
