mirror of
https://github.com/magnus919/agent-skills.git
synced 2026-09-11 19:47:12 +03:00
Magnus HedemarkGitHubusername <username>factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>Add the product-experimentation skill (issue #190): end-to-end experiment workflow from assumption mapping through method selection, guardrail definition, and decision-readout that updates the roadmap. Includes: - SKILL.md with full 8-step workflow, method ladder (interviews through A/B tests), multi-criteria decision framework, and routing to data-scientist and release-engineering - README.md with 5 required human-facing sections - references/discovery-brief.md mapping existing experimentation guidance across product-methodology, data-scientist, release-engineering, product-design-and-ux, and financial-modeling - references/method-selection.md with decision tree and anti-patterns - references/guardrails-and-ethics.md with guardrail design, ethical boundaries, and stopping rules - references/experiment-readout.md with decision-impact field types - 4 templates: assumption-map, experiment-brief, guardrail-and-decision-rule, readout-learning-entry - evals/evals.json with 5 output-quality cases covering prototype test, feature-flag rollout, underpowered experiment, guardrail omission, and significant-but-no-ship boundary Shared updates: root README catalog entry, skill-triggers.md entry, regenerated marketplace/codex/llms catalogs. Co-authored-by: username <username> Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
1.6 KiB
1.6 KiB
Readout and Learning Entry
Document the outcome of a product experiment and what changed as a result. Every experiment must produce at least one concrete change — otherwise the experiment was not worth running.
Experiment Reference
- Experiment name:
- Experiment brief: (link)
- Date completed:
Hypothesis and Method
- Hypothesis tested:
- Method used:
Result Summary
- Primary metric outcome:
- Statistical evidence: (effect size, confidence interval — from data-scientist)
- Guardrail status: (all passed / failures listed below)
- Qualitative observations:
Decision
- Decision: (ship / no-ship / inconclusive)
- Decision owner:
- Rationale: (include which criteria were weighted and why)
Decision Impact
Record at least one concrete change. If nothing changed, state why and whether the experiment was worth running.
| Impact type | Description | Where recorded |
|---|---|---|
| (roadmap / backlog / decision log / lifecycle / adoption) |
Learning
- What we learned: (generalizable beyond this specific experiment)
- What we would do differently: (method, instrumentation, guardrails, timing)
- Open questions: (what remains unknown and worth testing later)
Routing
- Roadmap updates routed to product-roadmapping-and-portfolio
- Backlog changes routed to product-methodology
- Decision log entry created in product-methodology
- Adoption evidence routed to product-adoption
- Lifecycle learning routed to product-lifecycle-learning