# Oh My Pi

> Multi-agent orchestration for PI: team coordination, autonomous execution, persistence loops, and requirements gathering. USE FOR: multi-agent development, parallel execution, code implementation, architecture design, security review, test automation, project planning. Commands: /skill:team, /skill:autopilot, /skill:ralph, /skill:deep-interview, /skill:plan, /skill:verify

- Skill: `changhochien/oh-my-pi` (Agent Skill, multi-file: 12 files)
- Install (CLI): `npx skillmds@latest add changhochien/oh-my-pi`
- Raw SKILL.md: https://api.skillmd.com/api/skills/changhochien/oh-my-pi/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: changhochien (https://skillmd.com/u/changhochien)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/changhochien/oh-my-pi

---


# oh-my-pi

Multi-agent orchestration for PI coding agent.

<operating_principles>
- Delegate specialized work to the most appropriate agent.
- Prefer evidence over assumptions: verify outcomes before final claims.
- Choose the lightest-weight path that preserves quality.
- Keep users informed with concise progress updates.
- Verify completion before declaring done.
</operating_principles>

<agent_catalog>
Prefix: `oh-my-pi:`. See `agents/*.md` for full prompts.

explorer (haiku), executor (sonnet), architect (opus), debugger (sonnet),
code-reviewer (opus), security-reviewer (sonnet), tester (sonnet),
planner (sonnet), verifier (sonnet), critic (opus), git-master (sonnet),
analyst (sonnet), writer (sonnet), scientist (sonnet), designer (sonnet),
code-simplifier (sonnet)
</agent_catalog>

<skills>
Invoke via `/skill:<name>` or use natural language triggers.

Workflows:
- `autopilot`: Full autonomous execution from idea to working code
- `ralph`: Persistence loop until all acceptance criteria pass
- `team`: N coordinated agents on shared task list (in-session)
- `pi-team`: tmux-based multi-agent orchestration (multi-provider CLI workers)
- `deep-interview`: Socratic requirements gathering
- `plan`: Strategic planning
- `verify`: Multi-perspective validation

Utilities:
- `cancel`: Cancel active execution modes
- `status`: Show current mode status
</skills>

<state_paths>
State: `.omp/state/`, `.omp/plans/`, `.omp/prd.json`, `.omp/notepad.md`
</state_paths>

<team_pipeline>
Stages: `plan` → `execute` → `verify` → `fix` (loop)
</team_pipeline>

---

## Quick Commands

```bash
/skill:team 3:executor "implement user authentication"
/skill:autopilot "build a REST API for task management"
/skill:ralph "fix all TypeScript errors"
/skill:deep-interview "I want to build something cool"
/skill:plan "migrate to microservices"
/skill:verify "review the changes"
```

## Agent Delegation

Use `oh-my-pi:<agent>` prefix for specialized agents:

```
Task(subagent_type="oh-my-pi:executor", model="sonnet", prompt="...")
Task(subagent_type="oh-my-pi:architect", model="opus", prompt="...")
Task(subagent_type="oh-my-pi:debugger", model="sonnet", prompt="...")
```

## Keyword Triggers

| Keyword | Skill |
|---------|-------|
| "autopilot", "build me", "I want a" | `autopilot` |
| "ralph", "don't stop", "must complete" | `ralph` |
| "team", "parallel", "coordinated" | `team` |
| "interview", "requirements", "clarify" | `deep-interview` |
| "plan this", "let's plan" | `plan` |
| "cancel", "stop" | `cancel` |