← All skills

pm-experiment-design

100 / 100 · Low risk

Fine to try.

By polar-bear-org/claude-skills (GitHub) · design · 54 stars · scanned at commit 95f0180

Designs an online controlled experiment with a hypothesis, variants, one primary metric, guardrails, a sample and duration check and a decision rule written before launch. Use for "run pm-experiment-design", "design an A/B test", "experiment plan", "is my test big enough", "sample size for a test", "how long should the test run", "settle this with a test", "decision rule for an experiment", part of the AI for Product Management Pack by 90n.

Works with any agent that supports SKILL.md skills.

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/'pm-experiment-design' ] || [ -L ~/.agents/skills/'pm-experiment-design' ]; then echo 'A skill folder named pm-experiment-design 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 "$d" checkout --quiet '95f01806ca43f6ee788d0579743e35853b695930' -- 'packs/ai-for-product-management-pack/skills/pm-experiment-design' && mkdir -p ~/.agents/skills && cp -R "$d"/'packs/ai-for-product-management-pack/skills/pm-experiment-design' ~/.agents/skills/'pm-experiment-design' && 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/'pm-experiment-design' ~/.claude/skills/'pm-experiment-design' (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

The badge for polar-bear-org/claude-skills shows the score of its lowest-scoring skill.

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/polar-bear-org/claude-skills.svg)](https://zalavijaysinh.github.io/skilltrust/repos/polar-bear-org/claude-skills/)

Score history