borghei/Claude-Skills / project-management/discovery/brainstorm-experiments
brainstorm-experiments
VerifiedDesigns cheap experiments with a pre-set pass bar (at least X% of Y will do Z) and picks the method. Use when validating an idea before building, testing willingness to pay, or choosing between fake door, landing page and A/B test.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 8.5 KB |
| assets/experiment_plan_template.md | markdown | 2.5 KB |
| assets/sample_hypotheses.json | config | 441 B |
| assets/sample_hypotheses_flawed.json | config | 211 B |
| examples/ai-summarization-willingness-to-pay-experiment.md | markdown | 13.7 KB |
| references/experiment-methods.md | markdown | 8.0 KB |
| references/methodology-and-tools.md | markdown | 8.4 KB |
| references/red-flags.md | markdown | 12.7 KB |
| scripts/experiment_designer.py | script | 13.4 KB |
assets/experiment_plan_template.md
View on GitHub# Experiment Plan Template
## Experiment Overview
| Field | Value |
|-------|-------|
| **Experiment Name** | |
| **Owner** | |
| **Date Created** | YYYY-MM-DD |
| **Product** | New / Existing |
| **Status** | Planned / Running / Complete / Abandoned |
---
## Experiment Card
### Hypothesis (XYZ Format)
> At least **X%** of **Y** will **Z**.
| Component | Value |
|-----------|-------|
| **X% (threshold)** | |
| **Y (target segment)** | |
| **Z (measurable action)** | |
### Method
| Field | Value |
|-------|-------|
| **Experiment Type** | Landing Page / Explainer Video / Pre-Order / Concierge MVP / Fake Door / Feature Stub / A/B Test / Wizard of Oz / Survey |
| **Description** | Brief description of the experiment setup |
| **Audience** | Who will be exposed to the experiment? |
| **Sample Size Target** | Minimum number of participants / impressions |
| **Duration** | Start date to end date |
| **Effort Level** | Low / Medium / High |
### Metrics
| Metric Type | Metric Name | How Measured | Target |
|-------------|-------------|--------------|--------|
| **Primary** | | | |
| **Secondary** | | | |
| **Guardrail** | | Must not degrade | Current baseline: |
### Success Criteria
- **Pass:** Primary metric >= threshold (X%)
- **Fail:** Primary metric < threshold
- **Inconclusive:** Insufficient sample size or metric within margin of error
---
## Experiment Tracker
*Use this table to manage multiple concurrent experiments.*
| # | Experiment Name | Hypothesis | Method | Status | Start | End | Primary Metric | Result |
|---|----------------|-----------|--------|--------|-------|-----|----------------|--------|
| 1 | | | | Planned | | | | |
| 2 | | | | Planned | | | | |
| 3 | | | | Planned | | | | |
| 4 | | | | Planned | | | | |
| 5 | | | | Planned | | | | |
**Status values:** Planned | Running | Complete (Pass) | Complete (Fail) | Complete (Inconclusive) | Abandoned
---
## Results Documentation
*Complete this section when the experiment ends.*
### Raw Results
| Metric | Baseline | Result | Delta | Pass/Fail |
|--------|----------|--------|-------|-----------|
| Primary: | | | | |
| Secondary: | | | | |
| Guardrail: | | | N/A | |
### Analysis
**What happened?**
**Why do we think this happened?**
**Unexpected observations:**
### Decision
| Decision | Rationale |
|----------|-----------|
| **Proceed / Pivot / Abandon** | |
### Next Steps
| Action | Owner | Due Date |
|--------|-------|----------|
| | | |
| | | |
| | | |
---
## Notes
*Capture any context, anomalies, or learnings not covered above.*
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |