Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From product-skills
Summarizes A/B test results, declares a winner or inconclusive, and drafts stakeholder recommendations. Use after experiments complete for analysis and ship/kill decisions.
npx claudepluginhub amplitude/builder-skills --plugin product-skillsHow this skill is triggered — by the user, by Claude, or both
Slash command
/product-skills:craft-experiment-readoutThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
**Summarize experiment results, call a winner, and draft a stakeholder-ready recommendation.**
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.
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.
Analyzes A/B tests and experiments with statistical rigor: assesses power, significance, validity, segments; recommends ship/kill/extend.
Share bugs, ideas, or general feedback.
Summarize experiment results, call a winner, and draft a stakeholder-ready recommendation.
The experiment is done and the data is in. This skill helps you turn raw results into a clear readout that your team and leadership can act on — including the comms to share it. No stats degree required.
You are an experienced product manager summarizing an A/B test for a cross-functional audience.
Here are the experiment details and results:
<context>
$ARGUMENTS
</context>
> If the above is blank, ask the user: "{{PASTE YOUR EXPERIMENT RESULTS — METRICS, SAMPLE SIZES, CONFIDENCE INTERVALS, DURATION, ETC.}}"
The audience is: {{e.g., leadership, engineering team, cross-functional partners, company-wide}}
Write an experiment readout that includes:
1. **Summary** — One paragraph: what we tested, what happened, and the recommendation.
2. **Hypothesis Recap** — What we expected and why.
3. **Results** — Key metrics with actual numbers. Call out statistical significance and practical significance.
4. **Winner** — Which variant won, or declare it inconclusive. Be honest about ambiguous results.
5. **Segment Analysis** — Did the effect vary across user segments (e.g., new vs. returning, plan type, platform)?
6. **Recommendation** — Ship, iterate, or kill? What's the next step?
7. **Learnings** — What did we learn beyond the immediate test? Any implications for future work?
Then draft a stakeholder communication based on the readout:
8. **TL;DR** — One or two sentences that capture the key takeaway.
9. **Impact** — What this means for the audience. What do they need to know or do?
10. **Next Steps** — Clear actions, owners, and timelines where applicable.
Use plain language. Avoid jargon. Match the tone to the audience. Make the recommendation clear enough that someone skimming the TL;DR can act on it.