Growth experiments are the activity teams do most carelessly. Hypothesis is implicit; metric is improvised; kill conditions are not defined. The result is experiments that run forever waiting for significance and decisions made by intuition rather than data.
The /surge-experiment skill designs a single experiment with rigor: testable hypothesis, exact metric and measurement, baseline, MDE, required run time, explicit kill conditions. One unambiguous design per experiment.
Tonone's /surge-experiment skill designs single growth experiments with hypothesis, metric, baseline, MDE, run time, and kill conditions.
Related skills
Install
/surge-experiment ships with the Surge agent in Tonone for Claude Code.
1. Add to marketplace
2. Install Surge
Frequently asked questions
- What does /surge-experiment do?
- It designs a single growth experiment with hypothesis, metric, baseline, MDE, run time, and kill conditions.
- How do I install /surge-experiment?
- Install Tonone for Claude Code via tonone.ai/get-started.
Pairs well with
Growth systems that compound. Acquisition loops, activation funnels, and retention hooks that don't stop working.
The metrics that matter, the funnels that leak, and the cohorts no one noticed were churning.
What users actually want: not what they say, not what the team guesses. What the evidence shows.