Skip to main content
command CX Codex

setup-metrics — Claude Code command for product metrics

setup-metrics is a Claude Code command that defines product metrics from a North Star to alert thresholds. It covers feature measurement planning and dashboard reviews.

MIT ★ 28,211 updated 2026-10-16

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add phuryn/pm-skills
/plugin install pm-product-discovery@pm-skills
Open on GitHub

What setup-metrics does

/setup-metrics asks about the product area, its stage, business goals, current metrics, and analytics tools. It then proposes a North Star metric with a formula and data source, plus actionable input metrics, health metrics, and counter-metrics. Each metric gets green, yellow, and red thresholds along with a check frequency.

The output is a Markdown dashboard spec with a metrics tree, targets, current values, data sources, refresh frequency, and a review schedule. The command saves the file to the workspace and can offer follow-up SQL queries, OKRs, or a weekly review template. For a pre-launch product, baseline values still need calibration after launch.

What it helps with

  • choose a North Star metric for a product or feature
  • connect input metrics to a business outcome
  • set alert thresholds for metric degradation
  • draft a dashboard spec and review schedule

Example prompts for the agent

  • Design metrics for a new checkout flow with /setup-metrics
  • Create a metrics dashboard for a SaaS project management tool with /setup-metrics
  • Plan metrics for a product before launch with /setup-metrics

How to install setup-metrics

1Plugin marketplace

/plugin marketplace add phuryn/pm-skills
/plugin install pm-product-discovery@pm-skills

2Manually: put the files in place

.claude/commands/setup-metrics.md

Call it with /setup-metrics. For all projects use ~/.claude/commands/

Questions about setup-metrics

How do I install setup-metrics in Claude Code?

Add the marketplace with /plugin marketplace add phuryn/pm-skills, then install the plugin with /plugin install pm-product-discovery@pm-skills.

What does setup-metrics do?

It helps define a North Star metric, input metrics, health metrics, and counter-metrics. It also sets alert thresholds and produces a Markdown dashboard specification.

Can setup-metrics help with a pre-launch product?

Yes. It can define metrics before launch, but their baselines need calibration once the product is live.

Source text

setup-metrics.md · MIT
---
description: Design a product metrics dashboard with North Star metric, input metrics, health metrics, and alert thresholds
argument-hint: "<product or feature area>"
---

# /setup-metrics -- Product Metrics Dashboard Design

Design a comprehensive metrics framework for your product or feature — from selecting the right North Star to defining alert thresholds that catch problems early.

## Invocation

```
/setup-metrics SaaS project management tool
/setup-metrics New checkout flow we just launched
/setup-metrics             # asks what you're measuring
```

## Workflow

### Step 1: Understand What to Measure

Ask the user:
- What product or feature area are you setting up metrics for?
- What stage is it in? (pre-launch, recently launched, mature)
- What are the current business goals or OKRs?
- Do you have existing metrics? What's missing or broken?
- What analytics tools are you using? (helps tailor implementation advice)

### Step 2: Define the Metrics Framework

Apply the **metrics-dashboard** skill:

**North Star Metric:**
- Identify the single metric that best captures the value your product delivers to users
- Validate against criteria: measures value delivery, is a leading indicator, is actionable
- Define the metric precisely (formula, data source, time window)

**Input Metrics (3-5):**
- Identify the levers that drive the North Star
- Each input metric should be directly actionable by a team
- Map the causal chain: Input → North Star → Business Outcome

**Health Metrics (3-5):**
- Metrics that should stay stable — if they degrade, something is wrong
- Examples: error rates, latency, support ticket volume, NPS, churn rate
- Define "healthy" ranges and degradation thresholds

**Counter-Metrics (1-2):**
- Metrics that could indicate you're optimizing the wrong way
- Example: if North Star is "daily active users", counter-metric is "session quality" to prevent empty engagement

### Step 3: Design Alert Thresholds

For each metric:

| Metric | Green | Yellow | Red | Check Frequency |
|--------|-------|--------|-----|----------------|
| [metric] | [healthy range] | [warning] | [critical] | [daily/weekly] |

- **Yellow**: Investigate — something may be off
- **Red**: Act immediately — page someone or escalate

### Step 4: Create Dashboard Spec

```
## Metrics Dashboard: [Product/Feature]

**North Star**: [metric name]
**Definition**: [precise formula]
**Current value**: [if known]
**Target**: [goal]

### Input Metrics
| Metric | Definition | Owner | Target | Current |
|--------|-----------|-------|--------|---------|

### Health Metrics
| Metric | Healthy Range | Yellow Threshold | Red Threshold |
|--------|-------------|-----------------|---------------|

### Counter-Metrics
| Metric | Why It Matters | Watch For |
|--------|---------------|-----------|

### Metrics Tree
North Star: [metric]
├── Input: [metric 1] → driven by [team/action]
├── Input: [metric 2] → driven by [team/action]
├── Input: [metric 3] → driven by [team/action]
└── Counter: [metric] → watch for [degradation signal]

### Implementation Notes
- Data sources: [where each metric comes from]
- Refresh frequency: [real-time / hourly / daily]
- Tool recommendations: [based on user's stack]

### Review Cadence
- **Daily**: Glance at North Star and health metrics
- **Weekly**: Review input metrics trends, discuss in team standup
- **Monthly**: Deep dive — are inputs driving the North Star as expected?
- **Quarterly**: Reassess the metrics framework itself
```

Save as a markdown file to the user's workspace.

### Step 5: Offer Next Steps

- "Want me to **write SQL queries** to compute these metrics?"
- "Should I **create OKRs** based on this metrics framework?"
- "Want me to **build a cohort analysis** to set realistic baselines?"
- "Should I **set up a weekly metrics review template**?"

## Notes

- A good North Star is rare — most teams pick vanity metrics. Push for a metric that captures *user value delivered*, not just engagement
- Input metrics should be MECE (mutually exclusive, collectively exhaustive) in explaining the North Star
- If the product is pre-launch, define metrics now but note that baselines will need calibration after launch
- Counter-metrics prevent Goodhart's Law — when a metric becomes a target, it ceases to be a good metric
- Recommend starting with fewer metrics, well-instrumented, over a sprawling dashboard nobody checks

© Paweł Huryn · MIT · phuryn/pm-skills

Similar slash commands

All slash commands for Data and databases →

From the same set120

The whole set →
north-star Identifies your North Star Metric, validates it against core criteria, and outlines actionable input metrics. CX Codex +1 ★ 28,211repo stars growth-strategy growth-strategy builds a growth plan from growth loops and GTM motions. Use it when product traction stalls or you need a structured experiment plan. CX Codex +1 ★ 28,211repo stars strategy The /strategy command builds a complete product strategy through a 9-section Canvas: vision, segments, value, trade-offs, metrics, growth, capabilities, and defensibility. CX Codex +1 ★ 28,211repo stars research-users research-users synthesizes research notes, survey exports, and tickets into user personas, behavioral segments, and journey maps. Helpful for PMs evaluating qualitative data. CX Codex +1 ★ 28,211repo stars triage-requests triage-requests takes a batch of feature requests in any format and organizes them into themed groups ranked by priority. Helps clarify what users actually need and where to focus next. CX Codex +1 ★ 28,211repo stars plan-launch plan-launch builds a full go-to-market launch plan: from beachhead market and ICP to messaging, channel priorities, and timeline saved to Markdown. CX Codex +1 ★ 28,211repo stars pricing Builds a pricing plan from product value, competitor data, willingness to pay, and pricing tests. Useful when launching or changing a product’s pricing. CX Codex +1 ★ 28,211repo stars market-scan market-scan — a command for strategic analysis of competitive landscape. Runs SWOT, PESTLE, Porter's Five Forces, and Ansoff Matrix together and delivers a unified report with cross-framework synthesis. CX Codex +1 ★ 28,211repo stars

Project sponsors

Companies that keep this analytics open