inspection-metrics-summarizer
Purpose
Summarize inspection and review metrics so teams can see defect density, issue mix, effort, outcomes, and improvement opportunities.
Trigger this skill when
- You need a focused code-review or inspection analysis or artifact rather than generic commentary.
- Review discipline, issue handling, or closure quality matters to the outcome.
- You need a reusable output another reviewer, developer, or agent can extend safely.
Expected inputs
- review logs or issue data
- artifact size or scope data
- timing or effort data if available
- desired reporting audience
Deliverables
- inspection metrics summary
- patterns and insights
- data quality caveats
- recommended next skill
Operating procedure
- Clarify the artifact, review objective, and what counts as a meaningful issue.
- Separate explicit evidence from assumptions, missing context, or inference.
- Apply the relevant review structure, checklist, or inspection framing consistently.
- Produce compact findings that support triage, rework, and decision-making.
- Recommend the next most useful review, remediation, readiness, or process step.
Quality gates
- Do not treat preference as defect unless the criterion is explicit.
- Make severity, uncertainty, and evidence quality explicit.
- Prefer actionable findings tied to consequence over vague style commentary.
- Keep the artifact compact, structured, and reusable.
Handoff targets
- defect-leakage-predictor
- process-review-gap-detector
- release-readiness-reviewer
Output style
- Be explicit about evidence quality and uncertainty.
- Prefer structured findings over narrative filler.
- Tie recommendations to risk, delivery consequence, or rework cost.
- Use severity, priority, or confidence labels when useful.
Failure modes to avoid
- Do not collapse all issues into one undifferentiated list.
- Do not hide missing evidence, unclear criteria, or reviewer uncertainty.
- Do not recommend vague actions with no owner or closure path.
- Do not ignore process defects when the artifact issues are symptoms of review failure.
Minimum output skeleton
## Summary
## Findings
## Structured outputs
## Evidence / confidence
## Assumptions
## Open questions
## Recommended next skill
1---2name: inspection-metrics-summarizer3description: inspection-metrics-summarizer4---5# inspection-metrics-summarizer67## Purpose8Summarize inspection and review metrics so teams can see defect density, issue mix, effort, outcomes, and improvement opportunities.910## Trigger this skill when11- You need a focused code-review or inspection analysis or artifact rather than generic commentary.12- Review discipline, issue handling, or closure quality matters to the outcome.13- You need a reusable output another reviewer, developer, or agent can extend safely.1415## Expected inputs16- review logs or issue data17- artifact size or scope data18- timing or effort data if available19- desired reporting audience2021## Deliverables22- inspection metrics summary23- patterns and insights24- data quality caveats25- recommended next skill2627## Operating procedure281. Clarify the artifact, review objective, and what counts as a meaningful issue.292. Separate explicit evidence from assumptions, missing context, or inference.303. Apply the relevant review structure, checklist, or inspection framing consistently.314. Produce compact findings that support triage, rework, and decision-making.325. Recommend the next most useful review, remediation, readiness, or process step.3334## Quality gates35- Do not treat preference as defect unless the criterion is explicit.36- Make severity, uncertainty, and evidence quality explicit.37- Prefer actionable findings tied to consequence over vague style commentary.38- Keep the artifact compact, structured, and reusable.3940## Handoff targets41- defect-leakage-predictor42- process-review-gap-detector43- release-readiness-reviewer4445## Output style46- Be explicit about evidence quality and uncertainty.47- Prefer structured findings over narrative filler.48- Tie recommendations to risk, delivery consequence, or rework cost.49- Use severity, priority, or confidence labels when useful.5051## Failure modes to avoid52- Do not collapse all issues into one undifferentiated list.53- Do not hide missing evidence, unclear criteria, or reviewer uncertainty.54- Do not recommend vague actions with no owner or closure path.55- Do not ignore process defects when the artifact issues are symptoms of review failure.5657## Minimum output skeleton58```md59## Summary60## Findings61## Structured outputs62## Evidence / confidence63## Assumptions64## Open questions65## Recommended next skill66```