metric-diagnosis
Use when investigating unexpected metric changes - systematically narrows root cause through 4D segmentation, intrinsic vs extrinsic factor analysis, hypothesis testing, and North Star impact assessment
npx skills add majiayu000/claude-skill-registry --skill metric-diagnosis-jayhjenkins-productosv0-2 --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Metric Diagnosis Workflow ## Purpose Systematically investigate why a metric changed unexpectedly (dropped or spiked) by segmenting data, distinguishing internal vs. external factors, and testing hypotheses to identify root cause. Prevents rushing to wrong conclusions and ensures evidence-based responses. ## When to Use This Workflow Use this workflow when: - Key metrics drop or spike unexpectedly - Leadership asks "what happened to [metric]?" - Post-mortem analysis needed after incident - A/B test shows unexpected patterns - Need to validate suspected root cause - User behavior changed suddenly without obvious reason ## Skills Sequence This workflow applies the `root-cause-diagnosis` skill three times, then assesses North Star impact: ``` 1. Root Cause Diagnosis (Phase 1) ↓ (Segment across 4 dimensions: People, Geography, Technology, Time) 2. Root Cause Diagnosis (Phase 2) ↓ (Distinguish intrinsic vs extrinsic factors) 3. Root Cause Diagnosis (Phase 3) ↓ (Build hypothesis table and test against data) 4. North Star Alignment ↓ (Assess impact on top-line metrics) OUTPUT: Narrowed scope, tested hypotheses, identified root cause, recommended actions ``` ## Required Inputs Gather thi
- Purpose
- When to Use This Workflow
- Skills Sequence
- Required Inputs
- Metric Change Information
- Data Access
- Recent Activity Log
- Workflow Steps
- Phase 0: Data Quality Verification (5 minutes)
- Phase 1: Narrow the Scope (15-20 minutes)
- Phase 2: Generate Hypotheses (15-20 minutes)
- Phase 3: Test Hypotheses (20-30 minutes)
- Phase 4: Assess North Star Impact (10 minutes)
- Phase 5: Recommend Actions (10 minutes)
What does the metric-diagnosis skill do?
Use when investigating unexpected metric changes - systematically narrows root cause through 4D segmentation, intrinsic vs extrinsic factor analysis, hypothesis testing, and North Star impact assessment
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill metric-diagnosis-jayhjenkins-productosv0-2 --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.