skills.rest
Simon-YHKim
Simon-YHKimCOMMUNITY
Explore all skills by this author →
GitHub

project-context-md

Creates or updates the project-root CLAUDE.md file with verification tools and project conventions.

Updated Apr 5, 2026
Search Tags:#git#claude code#claude.md#project onboarding#codebase context#developer documentation#verification tools
One-click install
npx skills add https://github.com/Simon-YHKim/eject-button --skill project-context-md-simon-yhkim
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: project-context-md
Source: https://github.com/Simon-YHKim/eject-button/tree/main/.claude/skills/project-context-md
Command: npx skills add https://github.com/Simon-YHKim/eject-button --skill project-context-md-simon-yhkim

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? New Claude Code sessions start with zero project context, forcing users to repeatedly explain build commands, test workflows, and directory conventions. This Skill generates a CLAUDE.md file that Claude Code reads automatically at session start, listing the verification tools (dev server, tests, lint, typecheck) Claude can run autonomously. ## Core Features & Use Cases - CLAUDE.md Generation: Creates a structured project context file covering stack, verification commands, key paths, environment variables, and taboo paths. - Merge-Aware Updates: Detects an existing CLAUDE.md and merges section-by-section so teammate-written context is preserved. - Verification Loop Enablement: Implements the Boris Cherny principle of giving Claude self-verification commands (dev server, test, lint, build, DB access) so it can check its own work. - Use Case: You clone a repo with no Claude Code setup. Run this Skill to scan package.json, directory structure, and git history, then produce a reviewed CLAUDE.md committed to git for the whole team. ## Quick Start Ask Claude to create a CLAUDE.md for this project listing the dev server, test, and lint commands it can use to verify its own work.

Frequently Asked Questions about project-context-md

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

FAQPage Schema
How do I create a CLAUDE.md file for Claude Code?▼

Run this Skill in the project root and it scans package.json, directory structure, and git history to draft a CLAUDE.md. It lists your stack, verification commands, key paths, and conventions, then you review and commit it to git.

What should a CLAUDE.md file contain for Claude Code?▼

A CLAUDE.md should contain the project summary, tech stack, verification tools (dev server, test, lint, typecheck, build commands), key URL paths, directory structure, required environment variables, taboo paths that must not be modified, and team conventions.

Does this Skill overwrite an existing CLAUDE.md?▼

No. It first checks whether CLAUDE.md exists and merges section by section, preserving content teammates already wrote. Only missing or outdated sections are added or refreshed.

Should CLAUDE.md be committed to git or gitignored?▼

Commit it to git. The Skill explicitly warns against gitignoring CLAUDE.md because the file is meant to be shared with the whole team so every Claude session and teammate benefits from the same project context.

Why does Claude Code need verification commands in CLAUDE.md?▼

Listing dev server, test, and lint commands lets Claude run them autonomously to verify its own changes instead of guessing. This realizes the verification loop principle and is often the highest-impact file for Claude Code productivity.

Related Skills

Explore More Software Engineering Skills→
goodraingoodrain
7

rainbond-project-init

Initializes local projects for Rainbond by generating manifests and app bindings.

Official
Advanced
kv0906kv0906
14

ralph

Automate long-running coding tasks through iterative PRD-driven development cycles.

Community
Advanced
3D-Stories3D-Stories
2

rawgentic:add-exception

Add WAL and security guard exceptions to `.rawgentic.json` with validation.

Official
Intermediate
m2ai-portfoliom2ai-portfolio
4

agentify-docs

Convert internal documentation into agent-ready instructions with explicit boundaries.

Official
Intermediate