clawpod-app/awesome-openclaw-agent-packs/experiment-design

Claude Code and agent skill by clawpod-app/awesome-openclaw-agent-packs

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Design structured growth experiments with hypotheses, ICE scoring, and success criteria. Trigger with "design an experiment", "growth experiment for [metric]", "how do we improve [metric]", or "test idea for [channel]".

Install

npx vskill@latest install clawpod-app/awesome-openclaw-agent-packs/experiment-design

SKILL.md

Experiment Design

Design a structured growth experiment.

When to Use

  • User wants to improve a specific metric
  • Testing a new growth channel or tactic
  • Optimizing an existing funnel step

Steps

  1. Define the growth lever (acquisition, activation, retention, revenue, referral)
  2. Identify the current metric and target improvement
  3. Generate 3-5 experiment ideas
  4. Score each with ICE (Impact 1-10, Confidence 1-10, Ease 1-10)
  5. Design the top experiment with full specification

Output Format

markdown
## Growth Experiment -- [Metric]
 
### Current State
-**Metric**: [current value]
-**Target**: [target value]
-**Lever**: [AARRR stage]
 
### Experiment Ideas (ICE Scored)
| # | Idea | Impact | Confidence | Ease | Score |
|---|------|--------|------------|------|-------|
| 1 | [idea] | [1-10] | [1-10] | [1-10] | [avg] |
 
### Top Experiment: [Name]
-**Hypothesis**: If we [change], then [metric] will [improve by X%] because [reasoning]
-**Control**: [Current state]
-**Variant**: [What changes]
-**Primary Metric**: [What to measure]
-**Sample Size**: [Minimum for significance]
-**Duration**: [Expected runtime]
-**Success Criteria**: [Threshold for declaring winner]

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

See the full security report

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

See evaluation results

Source

Popularity

7-day trend score
5

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/clawpod-app/awesome-openclaw-agent-packs/experiment-design/badge)](https://verified-skill.com/skills/clawpod-app/awesome-openclaw-agent-packs/experiment-design)

Something wrong with this skill or its page? Tell us.