About user-research-repository-review
A skill for product and research teams that turns repository-review questions into an operating model with governance, evidence handling, and decision links. It emphasizes consent, evidence quality, and review of stale insights.
Key features
- 01Classifies research and evidence sources
- 02Defines capture, redaction, and tagging
- 03Sets confidence and insight lifecycle
- 04Links insights to product decisions
- 05Specifies governance and review processes
Use cases
- 01Designing a research repository operating model
- 02Creating an evidence taxonomy and schema
- 03Reviewing consent, access, and retention risks
Install
Copy the command and run it in a terminal.
$
npx skills add https:/After installing, type/user-research-repository-reviewin Claude Code to confirm it loaded.
Bundled filesagents/openai.yamlreferences/user-research-repository-patterns.md
Details
From the project READMEUser Research Repository Review
Use this skill to convert user research repository, insight taxonomy, evidence tagging, consent, synthesis, and decision-linkage questions into a concrete artifact with owners, gates, metrics, and recovery paths.
Workflow
- Identify research sources, participant consent, data sensitivity, user segments, product decisions, taxonomy needs, repository owners, and current evidence failure modes.
- Read
references/user-research-repository-patterns.md. - Classify inputs as primary research, usability evidence, survey signal, support cluster, sales/CS note, churn reason, app review, analytics anomaly, or synthesized insight.
- Define capture workflow, redaction, tagging, confidence scoring, insight lifecycle, decision linkage, search/browse views, and stale-evidence review.
- Produce repository operating model, state machine, decision table, event schema, taxonomy checklist, and governance plan.
When not to use
- Do not use for generic advice the base model already handles without this skill's specific artifact contract.
Guardrails
- Do not store raw PII, recordings, or sensitive customer quotes without consent, access controls, and retention rules.
- Do not let loud anecdotes override sample quality, segment fit, recency, or contradictory evidence.
- Do not publish insights without separating observation, interpretation, confidence, and decision implication.
- Do not let research repositories become dead archives with no owner, decision link, or stale-evidence review.
Output format
Research repository context:
Audience / source of truth / risk boundary:
Repository operating model:
| Area | Decision | Evidence | Risk | Owner |
| --- | --- | --- | --- | --- |
Taxonomy, confidence, and decision linkage:
- <trigger> -> <policy, metric, edge case, support note>
Comments
Markdown supported