ClaudeSuperPower

experiment-launch

Skill

Launch a GrowthBook A/B test end-to-end via the REST API — create the experiment, prep the feature flag, wire the experiment-ref rule, and start the experiment. Use when the user says "launch this experiment", "create the experiment", "wire up the A/B test", "kick off the test", "set up X as an expe

Install

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

What is experiment-launch?

Launch a GrowthBook A/B test end-to-end via the REST API — create the experiment, prep the feature flag, wire the experiment-ref rule, and start the experiment. Use when the user says "launch this experiment", "create the experiment", "wire up the A/B test", "kick off the test", "set up X as an experiment in GrowthBook", "start the experiment for flag Y", or "I already have a flag and want to run an experiment on it". Works for both experiment-first (creates the flag) and flag-first (detects the existing flag via the reuse path and wires the experiment to it). For designing the spec first, use experiment-design. For stopping a running experiment, use experiment-stop. For interpreting results, use experiment-analyze.

What this can do

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

Run shell commands

Declares Bash

~181 tokens of context used while enabled, before you invoke anything

All declared tools (1)
Bash

Documentation

README · ~12 min read

experiment-launch

Launch a GrowthBook A/B test end-to-end: create the experiment in draft, prep or reuse the feature flag, add the experiment-ref rule on a fresh draft revision, then call /start to publish the rule and flip the experiment to running. Handles the approval-required and pre-launch-checklist failure paths.

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 it's missing or invalid, gb-call's error message points back at /growthbook:gb-setup.

Required inputs

Collect from the user (or earlier skill output) before starting. Prompt for what's missing.

  • Feature flag name — kebab-case key, regex [a-zA-Z0-9_-]
  • Experiment name — human-readable
  • Variations — array of {name, value}, length ≥ 2. The first entry is the control. Values are serialized as strings on the rule (booleans → "false"/"true", numbers → "42", JSON → JSON-encoded string).
  • Project ID (optional) — pins the experiment and flag to a specific project

Optional inputs

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.