Skip to content

Experiment Readout

Turns A/B and product experiment data into a ship, stop, extend or iterate decision report

Stars
9,376
Licence
Apache-2.0
Files
6 files

What it does

When installed, the agent turns raw experiment notes (A/B test results, growth experiments, onboarding changes, email tests) into a structured decision report rather than a plain data summary. The report covers the hypothesis, setup, primary and guardrail metrics, an interpretation separating signal from noise, a clear recommendation to ship, stop, extend or iterate, and follow-up experiments. It also flags uncertainty, such as small samples or missing significance data, and offers three HTML visual styles to choose from.

Great for

  • Product managers and growth teams reviewing an A/B test and deciding whether to launch a change
  • Leaders who need a concise, action-oriented readout of an experiment
  • Teams running early-stage or mixed qualitative and quantitative experiments that need caveats kept visible

Skip it if

  • Statistical validation: the skill does not calculate p-values or confidence intervals, and it is instructed to avoid inventing them, so a formal analysis still needs a statistician or analytics tool
  • Experiments with no real data provided, since the skill is designed to rely only on user-supplied numbers

Try asking

  • “Here is our onboarding checklist A/B test CSV. Write a decision readout with a ship, stop, extend or iterate recommendation.”
  • “Turn these experiment notes and metric tables into a product readout for leadership.”
  • “Summarise this pricing experiment as a lab notebook style report with caveats on sample size.”
  • “Create a growth console style readout of our activation funnel experiment with follow-up test ideas.”
Step-by-step guide: how to use Experiment ReadoutInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 6 original files, the Apache-2.0 licence and an attribution note.

    experiment-readout.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip experiment-readout.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip experiment-readout.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Provide the hypothesis, sample sizes, duration, and primary and guardrail metrics up front so the report can fill every section.
  • Say which style you want (product-readout for leadership, lab-notebook for exploratory work, growth-console for funnel and real-time metrics), or let the default apply.
  • Check the output for directional or inconclusive labels when your sample is small, and add significance data yourself if you need a firm conclusion.

What's inside

  • assets/growth-console.html
  • assets/lab-notebook.html
  • assets/product-readout.html
  • example.html
  • example.md
  • SKILL.md

Redistributed unmodified from nexu-io/html-anything under the Apache-2.0 licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.