Code, review & ship faster
Manage your GitHub workflow, delegate coding tasks to AI agents, run scheduled Routines in the cloud, and use worktree parallelism to ship multiple features at once — all from your agent, with no context switching.
Expert Install
Copy this to your agent — it will install, configure, and verify everything.
Works on OpenClaw, Claude Code, Telegram, Feishu, and any agent interface. Your agent reads dev-expert.md and follows the setup steps inside.
Talk and handle it
After setup, say these to your agent:
Review open PRs, triage issues, check… Official
- › "Review my open PRs for anything blocking"
- › "Create an issue: login page crashes on Safari"
- › "What's the CI status on my current branch?"
- › "List all open issues assigned to me"
Delegate a refactor, background task, or… Official
- › "Delegate this refactor to a coding agent"
- › "Have Codex review this function for edge cases"
- › "Run this migration script in a background agent"
Schedule CI checks, auto-review routines, and… Official
- › "Set up a routine that runs tests when a PR is opened"
- › "Schedule a nightly build and deploy routine"
- › "Auto-assign reviewers via a cloud routine"
▶ View setup file dev-expert.md
Ship Expert
Agentic setup file — share this URL with your agent and it will set everything up for you:
https://clawhub.md/expert/dev-expert.md
Goal: Code, review & ship faster
What you'll have: Manage your GitHub workflow, delegate coding tasks to AI agents, run scheduled Routines in the cloud, and use worktree parallelism to ship multiple features at once — all from your agent, with no context switching.
Step 1: Install
clawhub install openclaw/github openclaw/coding-agent openclaw/cloud-routines
Step 2: Configure
Each skill may need credentials or auth before it can act on your behalf.
openclaw/github
Review open PRs, triage issues, check CI status, and create new issues — all via the gh CLI without opening a browser.
- Authenticate with the GitHub CLI: run
gh auth loginand follow the prompts - Choose HTTPS or SSH, then log in via browser — no extra tokens needed
- The skill uses
ghunder the hood, so all your existing GitHub access applies
openclaw/coding-agent
Delegate a refactor, background task, or code review to Claude Code or Codex while you stay focused on the bigger picture.
- Ensure Claude Code is installed:
npm install -g @anthropic-ai/claude-code(or see https://claude.ai/code) - Optional — for Codex delegation:
npm install -g @openai/codexthencodex login - No extra environment variables needed if Claude Code is already working in your session
openclaw/cloud-routines
Schedule CI checks, auto-review routines, and nightly test runs on Anthropic infrastructure — your agent ships even when you're offline.
- Ensure Claude Code is installed and authenticated:
claude auth login - Enable Routines:
claude routines enable(requires Max subscription) - For webhook triggers, configure your incoming webhook URL in Claude settings
Step 3: Try it
After setup, say these to your agent to verify everything works:
openclaw/github
- "Review my open PRs for anything blocking"
- "Create an issue: login page crashes on Safari"
- "What's the CI status on my current branch?"
openclaw/coding-agent
- "Delegate this refactor to a coding agent"
- "Have Codex review this function for edge cases"
- "Run this migration script in a background agent"
openclaw/cloud-routines
- "Set up a routine that runs tests when a PR is opened"
- "Schedule a nightly build and deploy routine"
- "Auto-assign reviewers via a cloud routine"
Ship Expert · clawhub.md/expert/dev-expert