Agent Skill · Amplitude

craft-experiment-readout

Summarize experiment results, call a winner, and draft a stakeholder-ready recommendation. Use when an A/B test is complete and you need to communicate results.

Provider: Amplitude Path in repo: product-skills/skills/craft-experiment-readout/SKILL.md

Skill body

Experiment Readout

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.


Prompt Template

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.

Tips

Skill frontmatter

suggest_when: User has experiment results, says "analyze this test", "did it win", "experiment readout", "share results with stakeholders", or needs to make a ship/kill/iterate decision on a completed A/B test.

Work with this as data

Every skill here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for agent skills

4 MCP tools reach this
  • find_skillsBrowse and filter every skill in the catalog.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This skill
curl "https://apis.io/api/v1/skills/craft-experiment-readout"
All agent skills
curl "https://apis.io/api/v1/skills?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

A second provider on the same verified email joins the account you already have.