brainstorm-experiments — Claude Code skill for experiment design
The brainstorm-experiments skill for Claude Code and Codex turns a product hypothesis into a low-cost experiment with a pass threshold set in advance. It selects a method for a new idea or an existing feature.
LicenseRef-MIT-Commons-Clause 104 installs ★ 1,183 updated 2026-11-08
npx skills add borghei/Claude-Skills --skill brainstorm-experiments -a claude-codeWhat brainstorm-experiments does
The skill frames a test as a measurable claim about what share of a target group will take an action, then suggests a method and a pass bar. For a new product, options include a landing page or pre-order; for an existing one, a fake door or A/B test.
The workflow covers the hypothesis, method, metric, timeboxed run, and result assessment. The experiment_designer.py script suggests up to three methods for each hypothesis. Each one needs hypothesis_text, target_segment, and product_type set to new or existing.
Set the threshold before the test and record a counter-metric in the experiment plan. If a hypothesis has no percentage bar, the script exits with code 1. That makes the pass/fail rule explicit before results come in.
What it helps with
- test demand before building a product
- measure willingness to pay
- choose a test for a new idea or an existing feature
- set a pass bar and track a counter-metric
Example prompts for the agent
- Design a test for the claim that at least 10% of the target segment will place a pre-order.
- Suggest an experiment for this new product idea and define its pass threshold.
- Compare ways to test interest in this feature and choose a method.
How to install brainstorm-experiments
1Skills CLI (Vercel)
npx skills add borghei/Claude-Skills --skill brainstorm-experiments -a claude-code2Manually: put the files in place
~/.claude/skills/brainstorm-experiments/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/brainstorm-experiments/
1Skills CLI (Vercel)
npx skills add borghei/Claude-Skills --skill brainstorm-experiments -a codex2Manually: put the files in place
.agents/skills/brainstorm-experiments/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add borghei/Claude-Skills --skill brainstorm-experiments -a cursor2Manually: put the files in place
.cursor/skills/brainstorm-experiments/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install borghei/Claude-Skills project-management/discovery/brainstorm-experiments2Manually: put the files in place
.github/skills/brainstorm-experiments/SKILL.md1Skills CLI (Vercel)
npx skills add borghei/Claude-Skills --skill brainstorm-experiments -a gemini-cli2Platform CLI
gemini skills install https://github.com/borghei/Claude-Skills --path project-management/discovery/brainstorm-experimentsManually: put the files in place
.devin/skills/brainstorm-experiments/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add borghei/Claude-Skills --skill brainstorm-experiments -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about brainstorm-experiments
How do I install brainstorm-experiments in Claude Code?
Run npx skills add borghei/Claude-Skills --skill brainstorm-experiments -a claude-code. The skill file is at ~/.claude/skills/brainstorm-experiments/SKILL.md.
What does brainstorm-experiments do?
It helps turn a product belief into a testable hypothesis, choose an experiment, and define a pass threshold before the test. Its script can suggest up to three methods for each hypothesis.
What fields does experiment_designer.py need?
Each hypothesis needs hypothesis_text, target_segment, and product_type, set to new or existing. The percentage in the hypothesis supplies the pass bar; without it, the script exits with code 1.