doc-experiment-readout
100 / 100 · Low risk
Fine to try.
Writes an Experiment Readout with the hypothesis, design, sample and duration, the result with its interval, guardrail metrics, the decision and what we learned. Use for "run doc-experiment-readout", "experiment readout", "write up the A/B test", "did the test win", "the result is not significant", "read this experiment honestly", "test results doc", "ship or stop after the test", part of the Claude Docs for Product Managers Pack by 90n.
What this skill can do
We found nothing in the files we read that matches our rules. That does not prove the skill is safe: see the limits of static scanning.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'doc-experiment-readout' ] || [ -L ~/.agents/skills/'doc-experiment-readout' ]; then echo 'A skill folder named doc-experiment-readout already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/polar-bear-org/claude-skills' "$d" && git -C "$d" checkout --quiet '95f01806ca43f6ee788d0579743e35853b695930' -- 'packs/docs-for-product-managers-pack/skills/doc-experiment-readout' && mkdir -p ~/.agents/skills && cp -R "$d"/'packs/docs-for-product-managers-pack/skills/doc-experiment-readout' ~/.agents/skills/'doc-experiment-readout' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'doc-experiment-readout' ~/.claude/skills/'doc-experiment-readout' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
[](https://zalavijaysinh.github.io/skilltrust/repos/polar-bear-org/claude-skills/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-07 | 95f0180 | 100 |