# Pmx Metric Tree

> Build a metric tree showing how top-level outcomes are driven by sub-metrics.

- Skill: `giljae/pmx-metric-tree` (Agent Skill)
- Install (CLI): `npx skillmds@latest add giljae/pmx-metric-tree`
- Raw SKILL.md: https://api.skillmd.com/api/skills/giljae/pmx-metric-tree/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: giljae (https://skillmd.com/u/giljae)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/giljae/pmx-metric-tree

---


# Metric Tree

## When to use
- Use when the task clearly matches this PM activity.
- Use when a structured answer is more useful than a generic brainstorm.
- Use when the user needs explicit trade-offs, implications, or next steps.

## Instructions
1. Clarify the goal, user, or decision context.
2. Use the skill-specific lens below to structure the work.
3. Make assumptions explicit instead of hiding them.
4. End with a practical recommendation or next step.

### Skill-specific lens
1. Start from the top-level outcome metric.
2. Decompose into drivers and sub-drivers.
3. Identify leverage points and blind spots.
4. Use the tree to guide experimentation or prioritization.

## Output
- Top metric
- Drivers
- Sub-drivers
- Leverage points
- Blind spots