amnafarzy/ravie/project-control-plane
Claude Code and agent skill by amnafarzy/ravie
- community
Checking that the SKILL.md file is still in the repository.
Use this whenever setting up Claude Code in a repo — the user says "onboard this project", "set up CLAUDE.md", "install the skills or hooks" — or when CLAUDE.md is missing, stale, or broken. NOT for feature work inside an already-onboarded repo.
Install
npx vskill@latest install amnafarzy/ravie/project-control-planeSKILL.md
The same SKILL.md was published earlier as amnafarzy/ravie/project-control-plane.
project-control-plane
Onboard a new repo to Claude Code. Creates the CLAUDE.md, copies skills, configures hooks, and verifies the setup works.
Purpose
When starting a new project or adding Ravie to an existing repo, this skill walks through the full setup: create the context file, install skills, configure enforcement, and verify with a test task.
Process
1. Gather project context
Read the repo to understand:
2. Create CLAUDE.md from template
Copy CLAUDE-TEMPLATE.md or quickstart/CLAUDE.md to the project root. Fill in:
- What the project is (1-2 sentences)
- Stack (from package.json + repo structure)
- Commands (from package.json scripts)
- Connected systems (GitHub URL, Linear workspace, Notion space, etc.)
- Active priorities (from Linear or current work)
3. Install skills
4. Configure hooks
Review the project's settings (hooks/hooks.json for plugin installs, .claude/settings.json for direct-copy) — adjust allow/deny lists for this project's specific commands.
5. Create CLAUDE.local.md
This is for personal WIP notes that shouldn't be committed.
6. Verify setup
Open Claude Code in the project and test:
If it summarizes your stack correctly, the setup works.
Then test a real skill:
Output format
Hard rules
- Never create CLAUDE.md without reading the project first — it should reflect the real stack, not a template
- Always add CLAUDE.local.md to .gitignore
- Always verify the setup with a real test, not just file creation
- Keep CLAUDE.md under 100 lines — move domain-specific rules to
rules/
Connects to
decision-log-adr— decisions made during setup should be loggednotion-brain— for linking the project's Notion workspacelinear-operator— for linking the Linear workspace
Common failure modes
CLAUDE.md too long — 200+ lines of context. Agent spends tokens reading it every turn. Keep it under 100 lines, move the rest to rules files.
Copy instead of symlink — Skills get out of sync with the master repo. Symlink is better unless you need project-specific skill modifications.
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/project-control-plane/SKILL.md
Popularity
- Repository stars
- 3
- 7-day trend score
- 7
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/amnafarzy/ravie/project-control-plane)