Designs and manages growth experiments using ICE/RICE frameworks. Structures hypothesis-experiment-measure-learn cycles for systematic startup growth with weekly experiment cadence.
From forged-claude-codenpx claudepluginhub dokkabei97/forged-claude-code --plugin forged-claude-codeThis skill uses the workspace's default tool permissions.
Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.
Migrates code, prompts, and API calls from Claude Sonnet 4.0/4.5 or Opus 4.1 to Opus 4.5, updating model strings on Anthropic, AWS, GCP, Azure platforms.
Details PluginEval's skill quality evaluation: 3 layers (static, LLM judge), 10 dimensions, rubrics, formulas, anti-patterns, badges. Use to interpret scores, improve triggering, calibrate thresholds.
Turns growth from gut feeling into a repeatable process. Run 2-3 experiments per week, learn fast, double down on what works.
| Trigger | Behavior |
|---|---|
| Weekly growth meeting | Experiment pipeline review |
| "growth experiment" | New experiment design |
| Post-experiment | Result analysis and learnings |
# Experiment: [Name]
**ID**: GX-[NNN]
**Date**: YYYY-MM-DD
**Owner**: @name
**Status**: Idea / Designed / Running / Completed
## Hypothesis
> If we [specific change],
> then [expected outcome],
> measured by [metric] changing from [baseline] to [target],
> within [timeframe].
## ICE Score
| Factor | Score (1-10) | Reasoning |
|--------|-------------|-----------|
| **Impact** | [N] | [How much will this move the needle?] |
| **Confidence** | [N] | [How sure are we this will work?] |
| **Ease** | [N] | [How quickly can we test this?] |
| **ICE Score** | **[N]** | Impact × Confidence × Ease |
## Design
- **What**: [Specific change or test]
- **Where**: [Channel, page, or touchpoint]
- **Who**: [Target segment]
- **Duration**: [How long to run]
- **Sample**: [Expected sample size]
- **Success Criteria**: [What "winning" looks like]
## Results (post-experiment)
| Metric | Baseline | Result | Change | Significant? |
|--------|----------|--------|--------|-------------|
| [Metric] | [N] | [N] | [+/-]% | Yes/No |
## Decision: 🟢 Scale / 🟡 Iterate / 🔴 Kill
**Reasoning**: [Why this decision]
## Learnings
- [What we learned about our users]
- [Implications for future experiments]
| Channel | Experiment Ideas |
|---|---|
| Onboarding | Simplify signup, personalized first experience, progress bar |
| Subject line tests, send time optimization, drip sequence | |
| Landing Page | Headline variants, CTA placement, social proof |
| Pricing | Free tier limits, annual discount, feature gating |
| Referral | Double-sided incentive, share mechanics, invite timing |
| Content | Topic clusters, format tests, publishing frequency |
| Product | Feature discovery, empty states, notification triggers |
## Growth Meeting — YYYY-MM-DD (30 min)
### 1. Metrics Check (5 min)
- North Star: [value] ([trend])
- Key funnel metrics: [quick update]
### 2. Completed Experiments Review (10 min)
- GX-[N]: [Result] → [Decision]
- GX-[N]: [Result] → [Decision]
### 3. Running Experiments (5 min)
- GX-[N]: [Progress update]
### 4. New Experiment Pipeline (10 min)
| ID | Experiment | ICE | Status |
|----|-----------|-----|--------|
| GX-[N] | [Name] | [N] | Ready to launch |
| GX-[N] | [Name] | [N] | Needs design |
### 5. Launch Decisions
- Launch this week: GX-[N], GX-[N]
| Tool | Purpose |
|---|---|
| Write | Generate experiment docs, meeting agendas |
| Read | Reference previous experiment results |
Will:
Will Not: