hypothesis-library
Curated repository of experiment hypotheses, assumptions, and historical learnings.
When & Why to Use This Skill
The Hypothesis Library skill is a structured repository designed to manage the full lifecycle of experiment hypotheses, assumptions, and historical insights. It enables teams to maintain a centralized knowledge base of past experiments, ensuring data-driven decision-making and preventing redundant testing by documenting wins, losses, and reusable learnings with consistent metadata.
Use Cases
- Experiment Prioritization: Reference past wins and losses to effectively rank the product backlog based on historical evidence and confidence ratings.
- Cross-Team Knowledge Sharing: Distribute documented learnings across different product pods and marketing channels to prevent redundant testing and scale successful strategies.
- Structured Idea Intake: Capture new experiment ideas using a consistent metadata schema, including target personas, funnel stages, and primary success metrics.
- Evidence-Based Decision Making: Utilize the assumptions matrix and belief statements to validate experiment logic and supporting data points before committing resources.
| name | hypothesis-library |
|---|---|
| description | Curated repository of experiment hypotheses, assumptions, and historical |
Hypothesis Library Skill
When to Use
- Capturing new experiment ideas with consistent metadata.
- Referencing past wins/losses before prioritizing the backlog.
- Sharing reusable learnings across pods and channels.
Framework
- Metadata Schema – hypothesis ID, theme, persona, funnel stage, metrics.
- Assumptions Matrix – belief statements, supporting evidence, confidence rating.
- Status Tracking – idea → scoped → running → decided → archived.
- Learning Tags – impact summary, guardrail notes, follow-up ideas.
- Governance Hooks – approvals, owners, review cadence.
Templates
- Intake form for new hypotheses.
- Learning card format (context, result, recommendation).
- Portfolio dashboard summarizing mix by theme/metric.
Tips
- Require at least one supporting data point before moving to prioritization.
- Use consistent tagging so search/filtering works across teams.
- Link to
synthesize-learningsoutputs to keep narratives fresh.