Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From ai-pm
Analyzes A/B test result CSV/table data and outputs PM-ready report with conclusion, results table, guardrail checks, bias/novelty warnings, and ship/iterate/kill recommendation. Always checks statistical significance vs. business meaning, guardrail violations, and p-hacking signals.
npx claudepluginhub kimsanguine/ai_pm --plugin ai-pmHow this skill is triggered — by the user, by Claude, or both
Slash command
/ai-pm:experiment-analyzerclaude-opus-4-8The summary Claude sees in its skill listing — used to decide when to auto-load this skill
실험 결과 데이터(CSV / 표)를 받아 **PM 보고 포맷** 으로 분석 결과 + ship/iterate/kill 권고를 출력한다.
Analyzes A/B test results for statistical significance, sample size validation, confidence intervals, guardrail metrics, and recommendations on launch, extension, or termination. Useful for evaluating experiments, interpreting split test data, or deciding variant rollouts.
Summarizes A/B test results, declares a winner or inconclusive, and drafts stakeholder recommendations. Use after experiments complete for analysis and ship/kill decisions.
Documents completed experiment or A/B test results: statistical analysis, learnings, and recommendations. Use after experiments to communicate findings, inform decisions, and build organizational knowledge.
Share bugs, ideas, or general feedback.
실험 결과 데이터(CSV / 표)를 받아 PM 보고 포맷 으로 분석 결과 + ship/iterate/kill 권고를 출력한다.
samples/ab-test-results.csv 또는 사용자 첨부.~/.claude/guides/evals.md 의 PM 보고 포맷 따름).## 결론 (한 줄)
주 메트릭 +X.X% (p=0.0XX, n=NNN per arm) — ship / iterate / kill / extend
## 무엇을 했나
- 변경: <한 줄>
- 기간: YYYY-MM-DD ~ YYYY-MM-DD
- 표본: control n=NNN / treatment n=NNN
- 가설: <한 줄>
## 결과 표
| 메트릭 | Control | Treatment | Δ | p-value |
|---|---|---|---|---|
## 가드레일
- 메트릭 X: 변화 없음 / 악화 -X.X%
- 메트릭 Y: ...
## 의심 신호 (있다면)
- 표본 균형 / novelty / segment 편향 / Simpson's paradox 검토 결과.
## 권고
ship / iterate / kill / extend
- 사유: <한 줄>
- 다음 step: <한 줄>
samples/ab-test-results.csv~/.claude/guides/evals.md7.1-growth-experiment-analysis.mdgood-examples/checkout-cta-test.mdbad-examples/p-only-recommend.md