ClaudeSuperPower
SubmitLog in

experiment-design

Skill

Help the user design a well-formed GrowthBook experiment before it's launched. Use when the user asks to "design an A/B test", "set up an experiment", "test X vs Y", "configure an experiment", or "what should we measure". Produces a complete spec — hypothesis, variations, primary metric, guardrails,

0Security

Install

git clone https://github.com/growthbook/skills.git ~/.claude/skills/experiment-design

What is experiment-design?

Help the user design a well-formed GrowthBook experiment before it's launched. Use when the user asks to "design an A/B test", "set up an experiment", "test X vs Y", "configure an experiment", or "what should we measure". Produces a complete spec — hypothesis, variations, primary metric, guardrails, sample size — ready to hand off. Does not create the experiment in GrowthBook. For launching, use experiment-launch. For ideas grounded in past results, use experiment-brainstorm first.

What this can do

Capabilities declared in this component's own frontmatter — not inferred.

Run shell commands

Declares Bash

~122 tokens of context used while enabled, before you invoke anything

All declared tools (1)
Bash

Documentation

README · ~5 min read

experiment-design

Help the user produce an experiment spec that's actually launchable. Walk them through hypothesis, variations, metrics, and sample-size sanity. This skill does not write to GrowthBook — it ends with a ready-to-launch spec that experiment-launch consumes.

All API calls go through the bundled helper: ${CLAUDE_PLUGIN_ROOT}/scripts/gb-call. It needs GB_API_KEY — set in your shell, or written to ~/.config/growthbook/.env by /growthbook:gb-setup. If unset or invalid, gb-call's error message points back at /growthbook:gb-setup.

Workflow

  1. Frame the hypothesis. Falsifiable, if/then/because format:

    If we change X, then Y will improve, because Z.

    Push for specificity if the hypothesis is vague. "We think users will like it" doesn't say which metric — engagement could mean five different things. "If we move the CTA above the fold, then click-through will increase, because users decide whether to engage before they scroll" gives the prediction something concrete to land against.

  2. Define variations. Default to two: control (current state) and treatment (the change). Three or more variations are valid but cost statistical power; ask the user whether they really need a third. Number variations from 0 (control) to N.

  3. Pick goal metrics (ideally one, two max). List available templates and available metrics:

Reviews

Log in to leave a review.

No reviews yet — be the first.

Explore related

Other things in this space — across every part of the ecosystem, not just skills.

Skillssimilar to this one

All skills →

ECC

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

235.3K stars

claude-md-improver

Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintena

32.8K stars

Anthropic-Cybersecurity-Skills

817 structured cybersecurity skills for AI agents · Mapped to 6 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF & MITRE F3 (Fight Fraud) · agentskills.io standard · Works with Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI & 20+ platforms · 29 security domains · Apache 2.0

26.9K stars