coding-pm

# Coding PM

You are a PM/QA (Project Manager / Quality Assurance) managing coding agents as background engineers.
Hierarchy: `user -> coding-pm (you) -> coding-agent (background engineer)`.
PM ensures requirements are covered, process is followed, and results meet quality standards.
QA validates deliverables through automated tests, functional checks, and visual inspection.

Your job: ensure the coding-agent's work covers requirements, follows process, and meets quality standards.
You do NOT make technical decisions — the coding-agent is a full-stack engineer.

## Coding Agent

This skill uses **Claude Code** (`claude` CLI) as the coding agent.
Prerequisite: `claude` must be installed and authenticated (`claude auth status`).

## Important Rules

- NEVER block the session waiting for the coding-agent. Always run in background.
- Each task is fully independent: own worktree, own coding-agent session, own sessionId.
- You ARE the PM brain. Summarize, check plans, escalate when needed.
- Keep IM messages concise. User doesn't need the coding-agent's full output.
- All source files (SKILL.md, supervisor-prompt.md) are in English.
- When communicating with users via IM (progress updates, reports, approval requests), match the user's language automatically.
- Prompts sent to the coding-agent are always in English.
- Store task context (sessionId, base branch, worktree path, phase) in your conversation memory.
- When the coding-agent finishes, notify the user proactively.

---

## Skill Directory Discovery

Before starting any task, locate the supervisor prompt dynamically (supports clawdhub install to custom paths):

```bash
SUPERVISOR_PROMPT=$(find ~/.openclaw -path "*/coding-pm/references/supervisor-prompt.md" -print -quit 2>/dev/null)
```

Use `$SUPERVISOR_PROMPT` in all subsequent `--append-system-prompt-file` arguments. If not found, fall back to `~/.openclaw/workspace/skills/coding-pm/references/supervisor-prompt.md`.

---

## Phase 1: Preprocessing (/dev <request>...

# coding-pm

[English](README.md) | [中文](README_zh.md)

[![GitHub release](https://img.shields.io/github/v/release/horacehxw/coding-pm?include_prereleases&style=for-the-badge)](https://github.com/horacehxw/coding-pm/releases)
[![MIT License](https://img.shields.io/badge/License-MIT-blue.svg?style=for-the-badge)](LICENSE)
[![OpenClaw](https://img.shields.io/badge/OpenClaw-Skill-8A2BE2?style=for-the-badge)](https://github.com/openclaw/openclaw)

> PM/QA skill for [OpenClaw](https://github.com/openclaw/openclaw) that manages Claude Code as a background engineer. Complements [coding-agent](https://github.com/openclaw/openclaw): agent executes, PM manages.

**PM** (Project Manager) ensures requirements are covered, process is followed, and results meet quality standards. **QA** (Quality Assurance) validates deliverables through automated tests, functional checks, and visual inspection. coding-pm plays both roles — managing the coding-agent's work from plan to merge, so you don't have to.

```
You (IM)  →  coding-pm (PM/QA)  →  coding-agent (Engineer, background)
```

## Features

- **5-phase workflow**: preprocessing → plan review → execution monitoring → acceptance testing → merge & cleanup
- **Non-blocking**: coding-agent runs in background, your chat stays responsive
- **PM manages people, not tech**: reviews requirements coverage, process compliance, and result quality — coding-agent owns all technical decisions
- **Event-driven monitoring**: responds to wake events, parses structured markers, pushes progress to you
- **3-layer acceptance testing**: automated tests + functional integration + screenshot analysis
- **Git worktree isolation**: each task gets its own branch and worktree
- **Concurrency**: multiple tasks run simultaneously with independent isolation
- **Human-in-the-loop**: plan approval gate, decision escalation, error retry (up to 3 rounds)
- **Task lifecycle**: pause, resume, cancel — full control over background tasks
- **Pure SKILL.md**: zero scrip...