skills.rest
marmikcfc
marmikcfcCOMMUNITY
Explore all skills by this author →
GitHub

experiment-design

Generate experiment specs with hypothesis, variants, metrics, and guardrails.

Updated Apr 19, 2026
Search Tags:#design#metrics#strategy#statistics#experiment#sample-size#bet
One-click install
npx skills add https://github.com/marmikcfc/pepper-skills --skill experiment-design-marmikcfc
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: experiment-design
Source: https://github.com/marmikcfc/pepper-skills/tree/main/skills/experiment-design
Command: npx skills add https://github.com/marmikcfc/pepper-skills --skill experiment-design-marmikcfc

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Turn strategic bets into rigorous, runnable experiments with clearly defined hypotheses, variants, success metrics, guardrails, and execution plans.

Core Features & Use Cases

  • Converts bets into complete experiment specs including hypothesis, control, variant, primary metric, sample size, duration, and guardrails
  • Auto-generates a unique Experiment ID, owner assignment, and a concise execution plan
  • Saves and tracks specs under experiments/active for weekly strategy reviews and audits

Quick Start

Provide a bet title or paste the bet row from bets/bets.md, and the tool will generate a complete experiment spec ready for execution.

Frequently Asked Questions about experiment-design

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I design an experiment from a strategic bet?▼

To design an experiment from a strategic bet, you provide the bet title or paste the bet row from your strategy file. The tool then generates a complete experiment card with hypothesis, variants, metrics, sample size, duration, and guardrails.

What components are needed for a rigorous experiment design?▼

A rigorous experiment design requires a defined hypothesis, control and variant groups, primary metrics, guardrails, and a calculated sample size. It also needs an execution plan, kill criteria, decision rules, and a realistic duration estimate based on weekly throughput.

How is sample size and experiment duration calculated from weekly throughput?▼

Sample size and experiment duration are calculated by evaluating your weekly throughput. The tool uses this data to produce a realistic duration estimate and determine the necessary sample size for achieving statistical significance.

Can I create an experiment specification without a pre-existing bets file?▼

Yes, you can create an experiment specification without a pre-existing bets file by providing an inline hypothesis. The tool will auto-increment a unique experiment ID, assign an owner, and save the active spec for tracking.

What is the best way to track active experiment specs for weekly strategy reviews?▼

The best way to track active experiment specs for weekly strategy reviews is to save them in a dedicated directory. The tool automatically saves generated specs under an active experiments folder for audits and continuous tracking.

Related Skills

Explore More Data & Analytics Skills→
marmikcfcmarmikcfc

bet-ledger

Log strategic bets to an append-only bets/bets.md ledger.

Community
Intermediate
StreamPilotOrgStreamPilotOrg
1

experiment-analyzer

Analyzes growth experiments and generates markdown reports with follow-up suggestions.

Official
Basic
shalevaminshalevamin

ab-test-analysis

Analyze A/B test results for statistical significance and rollout recommendations.

Community
Advanced
ryzamediaryzamedia
1

ab-testing

Design and evaluate statistically rigorous A/B and multivariate experiments.

Community
Advanced