root-cause-diagnosis
Use when metrics drop or spike unexpectedly - systematically investigates using 4-dimension segmentation (People, Geography, Technology, Time), intrinsic vs extrinsic factors, and hypothesis table method to identify root cause
Profile →npx skills add majiayu000/claude-skill-registry --skill root-cause-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.
# Root Cause Diagnosis ## Purpose Systematically narrow down the root cause of unexpected metric changes by segmenting data, distinguishing internal vs. external factors, and testing hypotheses against observed patterns. Prevents jumping to conclusions and ensures evidence-based decision-making. ## When to Use This Skill Activate automatically when: - Key metrics drop or spike unexpectedly - A/B test results show unexpected patterns - User behavior changes suddenly - Post-mortem analysis needed after incident - Leadership asks "what happened?" - `metric-diagnosis` workflow investigates metric changes - Need to validate suspected causes **When NOT to use:** - Change was expected (planned feature release, known seasonality) - Metric is within normal variance - Root cause is already confirmed - Data quality issue is obvious (reporting broken) ## The Iron Law **ASK CLARIFYING QUESTIONS FIRST - DON'T GUESS** Most metric problems are more narrow than initially stated. The problem might only affect: - Specific user segments - Certain geographies - Particular platforms - Limited time windows Narrow the scope before hypothesizing causes. ## The 4 Critical Dimensions Always segment data acro
- Purpose
- When to Use This Skill
- The Iron Law
- The 4 Critical Dimensions
- Dimension 1: People (User Segments)
- Dimension 2: Geography
- Dimension 3: Technology (Platform)
- Dimension 4: Time
- Intrinsic vs. Extrinsic Factors
- Intrinsic Factors (Internal)
- Extrinsic Factors (External)
- The Hypothesis Table Method
- Step 1: Create Table Structure
- Step 2: Fill in Predictions
What does the root-cause-diagnosis skill do?
Use when metrics drop or spike unexpectedly - systematically investigates using 4-dimension segmentation (People, Geography, Technology, Time), intrinsic vs extrinsic factors, and hypothesis table method to identify root cause
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill root-cause-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.