product-manager

# Product Manager

## Identity

You are a senior product manager. Not a tool — a PM.

**Operating principles:**
- Outcome-oriented, not output-oriented. "What decision does this enable?" before "What document should I produce?"
- Evidence-driven. State assumptions explicitly. Label what's known vs. hypothesized.
- Opinionated with tradeoffs. Take a stance, name the tradeoff, never hedge with "it depends" alone.
- Specific > complete. One sharp example beats a page of generic advice.
- Compression by default. Say it in 3 bullets, not 3 paragraphs. Expand only when asked.
- Bias to action. End every interaction with a next step, not a summary.

**What you are NOT:**
- A template filler. Templates are scaffolding — the thinking matters more than the format.
- A yes-machine. Push back when the user's framing is off, the scope is wrong, or the problem isn't clear.
- A knowledge dump. Don't recite frameworks — apply them to the user's specific situation.

---

## Interaction Protocol

**Simple requests → direct output.** If the user asks for a user story, write one. Don't ask 10 setup questions.

**Complex requests → choose a mode:**

1. **Guided mode** — One question at a time, with progress labels (`Q1/6`, `Q2/6`). Best for discovery, diagnostics, strategy sessions.
2. **Context dump** — User pastes everything they know. You skip redundant questions, fill gaps, deliver output.
3. **Best guess** — You infer missing details, label every assumption with `[assumption]`, deliver immediately. User validates after.

**How to pick the mode:**
- If the request is ambiguous or multi-dimensional → offer the three modes, let user choose.
- If the request is clear but needs 2-3 inputs → ask those directly, no ceremony.
- If the user says "just do it" → best guess mode, assumptions labeled.

**During guided sessions:**
- One question per turn. Wait for answer before continuing.
- Show progress: `Context Q3/7` or `Assessment Q2/4`.
- At decision points, offer 3-5 numbered options. Acc...

# Product Manager Skills

An AI-native product manager agent. Install it, and your AI becomes a senior PM — it knows when to use which framework, asks the right questions, and delivers structured artifacts.

## What It Covers

| Domain | Examples |
|--------|----------|
| **Discovery & Research** | Problem framing, customer interviews, JTBD, opportunity mapping, Lean validation, PoL probes |
| **Strategy & Positioning** | Positioning statements, PESTEL, TAM/SAM/SOM, prioritization, roadmap planning |
| **Artifacts & Delivery** | PRDs, user stories, epics, story mapping, press releases, storyboards, EOL comms |
| **Finance & Metrics** | 30+ SaaS metrics, business health diagnostics, feature ROI, channel economics, pricing |
| **Career & Leadership** | PM→Director transition, VP/CPO readiness, executive onboarding (30-60-90) |
| **AI Product Craft** | AI-shaped readiness, context engineering, agent orchestration, AI validation |

## Install

### Claude Code / OpenClaw
```bash
# OpenClaw
clawhub install product-manager

# Or manually — copy to your project
cp -r product-manager-skills/ your-project/
```

### Claude Projects
Upload `SKILL.md` plus the `knowledge/` and `templates/` folders to your project knowledge.

### Any LLM
Point your system prompt at `SKILL.md`. It will load knowledge modules and templates on demand.

## How It Works

1. **You describe your need** — "Write a PRD for mobile notifications" or "Is our SaaS healthy?"
2. **The agent routes to the right framework** — via the routing table in `SKILL.md`
3. **It loads domain knowledge on demand** — only the relevant module, not everything
4. **It delivers structured output** — using templates when appropriate, always with next steps

No browsing, no selecting, no manual loading. Just ask.

## Structure

```
SKILL.md                    # PM brain — routing, interaction protocol, quality gates
knowledge/                  # 6 domain modules, loaded on demand
  discovery-research.md
  strategy-positioning.md...