From oh-my-claudecode
Takes a brief product idea and autonomously handles specification, planning, implementation, testing, and validation. Useful for rapid prototyping or building features hands-off.
How this skill is triggered — by the user, by Claude, or both
Slash command
/oh-my-claudecode:autopilotThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Full autonomous execution from idea to working code.
Full autonomous execution from idea to working code.
Autopilot is the ultimate hands-off mode. Give it a brief product idea (2-3 lines) and it handles everything:
/autopilot <your idea>
/ap "A CLI tool that tracks daily habits"
/autopilot Add dark mode to the app
These phrases auto-activate autopilot:
Goal: Turn vague idea into detailed spec
Agents:
Output: .omc/autopilot/spec.md
Goal: Create implementation plan from spec
Agents:
Output: .omc/plans/autopilot-impl.md
Goal: Implement the plan
Mode: Ralph + Ultrawork (persistence + parallelism)
Agents:
Goal: All tests pass
Mode: UltraQA
Cycle:
Goal: Multi-perspective approval
Agents (parallel):
Rule: All must APPROVE or issues get fixed and re-validated.
Optional settings in .claude/settings.json:
{
"omc": {
"autopilot": {
"maxIterations": 10,
"maxQaCycles": 5,
"maxValidationRounds": 3,
"pauseAfterExpansion": false,
"pauseAfterPlanning": false,
"skipQa": false,
"skipValidation": false
}
}
}
/cancel-autopilot
Or say: "stop", "cancel", "abort"
Progress is preserved for resume.
If autopilot was cancelled or failed, just run /autopilot again to resume from where it stopped.
New Project:
/autopilot A REST API for a bookstore inventory with CRUD operations
Feature Addition:
/autopilot Add user authentication with JWT tokens
Enhancement:
/ap Add dark mode support with system preference detection
Stuck in a phase?
.omc/autopilot-state.json for stateValidation keeps failing?
QA cycles exhausted?
npx claudepluginhub mazenyassergithub/oh-my-claudecode --plugin oh-my-claudecodeCreates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.