Authoring CLAUDE.md Project Instructions

Automate Git worktree management for parallel SPEC development.

1.2k|214|Updated Sep 16, 2025
One-click install
npx skills add https://github.com/modu-ai/moai-adk --skill authoring-claude-md-project-instructions
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Authoring CLAUDE.md Project Instructions
Source: https://github.com/modu-ai/moai-adk/tree/main/.claude/skills/moai-cc-claude-md
Command: npx skills add https://github.com/modu-ai/moai-adk --skill authoring-claude-md-project-instructions

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes templates (resource) components.

What problem does it solve?

Effectively guiding an AI agent requires clear, structured instructions and consistent project context. This Skill helps you design and maintain CLAUDE.md files, which serve as living documents for AI collaboration, ensuring Claude understands your project's overview, workflows, standards, and architectural decisions.

Core Features & Use Cases

  • Project Context Definition: Structure CLAUDE.md with sections for project overview, tech stack, and team details.
  • Workflow Documentation: Define development phases (Plan, Implement, Sync) and AI collaboration patterns.
  • Code Standards Enforcement: Document TRUST 5 principles (Test First, Readable, Unified, Secured, Trackable) and other non-negotiable rules.
  • Architectural Guidance: Describe directory structure, key design decisions, and rationale behind architectural choices.
  • Use Case: When onboarding a new AI agent or team member, a well-structured CLAUDE.md created with this Skill can instantly provide all necessary project context, accelerating their productivity and ensuring alignment with project standards.

Quick Start

Example: Basic CLAUDE.md structure

(This is a Markdown snippet, not a command)

# Project Name

# Description: What does this project do?

# ## Development Workflow

# ### Phase 1: Planning

# - Use /alfred:1-plan for SPEC creation

# ## Code Standards (TRUST 5 Principles)

# ### T - Test First

# - Target coverage: ≥ 85%

# Claude can help fill in these sections based on your project.

Frequently Asked Questions about Authoring CLAUDE.md Project Instructions

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create a CLAUDE.md file to document project context for AI collaboration?

CLAUDE.md is a structured markdown file that documents your project overview, tech stack, development workflows, code standards, and architectural decisions. Create sections for project description, the Plan-Implement-Sync workflow phases, TRUST 5 principles (Test First, Readable, Unified, Secured, Trackable), and directory structure to give Claude immediate context when onboarding.

What should I include in CLAUDE.md to ensure an AI agent understands my project standards?

Include project overview and description, development workflow phases, code standards like TRUST 5 principles with specific metrics (e.g., ≥85% test coverage), architectural decisions and rationale, directory structure, tech stack details, and team collaboration patterns. This ensures Claude aligns with your non-negotiable rules and project governance from the start.

When do I need to update CLAUDE.md as my project evolves?

Update CLAUDE.md whenever your development workflow changes, architectural decisions shift, code standards are revised, or new team practices emerge. Keeping it current ensures new AI agents and team members receive accurate project context and reduces onboarding friction and misalignment.

Can I use CLAUDE.md with multiple team members and AI agents simultaneously?

Yes. CLAUDE.md serves as a living document shared across your team and AI collaborators. It acts as a single source of truth for project context, workflow expectations, and standards, enabling consistent collaboration patterns and reducing context-switching overhead.

How does CLAUDE.md improve AI collaboration compared to verbal or scattered documentation?

CLAUDE.md provides structured, searchable project context in a single file. AI agents consume it on every interaction, eliminating repeated context clarification, ensuring consistent interpretation of standards, and accelerating productivity by giving Claude complete architectural and workflow understanding upfront.