Use when setting product North Star metrics, decomposing high-level business metrics into actionable sub-metrics and leading indicators, mapping strategy to measurable outcomes, identifying which metrics to move through experimentation, understanding causal relationships between metrics (leading vs lagging), prioritizing metric improvement opportunities, or when user mentions metric tree, metric decomposition, North Star metric, leading indicators, KPI breakdown, metric drivers, or how metrics connect.
Decomposes North Star metrics into actionable sub-metrics and leading indicators to identify high-impact experiment opportunities. Use when setting product metrics, diagnosing metric changes, or prioritizing growth initiatives through causal analysis.
/plugin marketplace add lyndonkl/claude/plugin install lyndonkl-thinking-frameworks-skills@lyndonkl/claudeThis skill inherits all available tools. When active, it can use any tool Claude has access to.
resources/evaluators/rubric_metrics_tree.jsonresources/methodology.mdresources/template.mdDecompose high-level "North Star" metrics into actionable sub-metrics, identify leading indicators, understand causal relationships, and select high-impact experiments to move metrics.
Use metrics-tree when you need to:
Define Strategy:
Understand Metrics:
Prioritize Actions:
Diagnose Issues:
A metrics tree decomposes a North Star metric (the single most important product/business metric) into its component drivers, creating a hierarchy of related metrics with clear causal relationships.
Key Concepts:
North Star Metric: Single metric that best captures core value delivered to customers and predicts long-term business success. Examples:
Metric Levels:
Leading vs Lagging:
Quick Example:
North Star: Weekly Active Users (WAU)
Input Metrics (L2):
├─ New User Acquisition
├─ Retained Users (week-over-week)
└─ Resurrected Users (inactive → active)
Action Metrics (L3) for Retention:
├─ Users completing onboarding
├─ Users creating content
├─ Users engaging with others
└─ Users receiving notifications
Leading Indicators:
- Day 1 activation rate (predicts 7-day retention)
- 3 key actions in first session (predicts long-term engagement)
Copy this checklist and track your progress:
Metrics Tree Progress:
- [ ] Step 1: Define North Star metric
- [ ] Step 2: Identify input metrics (L2)
- [ ] Step 3: Map action metrics (L3)
- [ ] Step 4: Select leading indicators
- [ ] Step 5: Prioritize and experiment
- [ ] Step 6: Validate and refine
Step 1: Define North Star metric
Ask user for context if not provided:
Choose North Star using criteria:
See Common Patterns for North Star examples by type.
Step 2: Identify input metrics (L2)
Decompose North Star into 3-5 direct drivers:
See resources/template.md for decomposition frameworks.
Step 3: Map action metrics (L3)
For each input metric, identify specific user behaviors:
If complex, see resources/methodology.md for multi-level hierarchies.
Step 4: Select leading indicators
Identify early signals that predict North Star movement:
Step 5: Prioritize and experiment
Rank opportunities by:
Select 1-3 experiments to test highest-priority hypotheses.
See resources/evaluators/rubric_metrics_tree.json for quality criteria.
Step 6: Validate and refine
Verify metric relationships:
North Star Metrics by Business Model:
Subscription/SaaS:
Marketplace:
E-commerce:
Social/Content:
Decomposition Patterns:
Additive Decomposition:
North Star = Component A + Component B + Component C
Example: WAU = New Users + Retained Users + Resurrected Users
Multiplicative Decomposition:
North Star = Factor A × Factor B × Factor C
Example: Revenue = Users × Conversion Rate × Average Order Value
Funnel Decomposition:
North Star = Step 1 → Step 2 → Step 3 → Final Conversion
Example: Paid Users = Signups × Activation × Trial Start × Trial Convert
Cohort Decomposition:
North Star = Σ (Cohort Size × Retention Rate) across all cohorts
Example: MAU = Sum of retained users from each signup cohort
Avoid Vanity Metrics:
Ensure Causal Clarity:
Limit Tree Depth:
Balance Leading and Lagging:
Avoid Gaming:
Resources:
resources/template.md - Metrics tree structure with decomposition frameworksresources/methodology.md - Advanced techniques for complex metric systemsresources/evaluators/rubric_metrics_tree.json - Quality criteria for metric treesOutput:
metrics-tree.md in current directorySuccess Criteria:
Quick Decision Framework:
Common Mistakes:
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.