Senior Code Review Skill
Use this skill before finalizing meaningful code changes.
Review the final diff for:
- unrelated changes
- accidental formatting churn
- generated, vendored, compiled, or package-owned files
- missing or weak validation
- unused imports, variables, types, functions, or files caused by the change
- naming clarity
- consistency with existing patterns
- incomplete fixes that minimize the diff while leaving required behavior unresolved
- abstractions without a demonstrated boundary, invariant, meaningful duplication, or variability
- unnecessary change amplification across unrelated components
- material technical debt without its scope, rationale, and follow-up condition
- speculative configurability
- behavior changes beyond the request
- API compatibility
- migration risk
- safety risk
- performance risk
- accessibility regressions
- subagent claims that were not independently verified
- finite-manifest nodes, root permits, or total-budget use that were not reconciled
- child execution that did not select a verified Luna/max profile or explicit
gpt-5.6-luna/max child-execution settings, or permissions, scope, authority, or workspace expansion beyond the parent assignment
- progress or task-reporting messages that set
model, reasoning_effort, thinking, or analogous destination-setting overrides, or altered a parent or peer task
- task-created auxiliary worktrees without integration evidence and a verified
removed or exact-blocker preserved disposition
Ask:
Would I approve this in code review?
If not, fix the issue or report the remaining risk clearly.
Final report format:
Summary:
- Changed X to do Y.
Verification:
- Ran: [command or check]
- Result: [passed/failed/not run, with reason]
Notes:
- [Assumptions, unrelated issues, subagent usage, follow-ups, or risk notes if any]
1---2name: senior-code-review-23description: Use before finalizing a meaningful code change. Reviews the final diff for correctness, scope control, maintainability, validation gaps, safety risk, performance risk, accessibility risk, and subagent claims that still need verification.4---56# Senior Code Review Skill78Use this skill before finalizing meaningful code changes.910Review the final diff for:1112- unrelated changes13- accidental formatting churn14- generated, vendored, compiled, or package-owned files15- missing or weak validation16- unused imports, variables, types, functions, or files caused by the change17- naming clarity18- consistency with existing patterns19- incomplete fixes that minimize the diff while leaving required behavior unresolved20- abstractions without a demonstrated boundary, invariant, meaningful duplication, or variability21- unnecessary change amplification across unrelated components22- material technical debt without its scope, rationale, and follow-up condition23- speculative configurability24- behavior changes beyond the request25- API compatibility26- migration risk27- safety risk28- performance risk29- accessibility regressions30- subagent claims that were not independently verified31- finite-manifest nodes, root permits, or total-budget use that were not reconciled32- child execution that did not select a verified Luna/max profile or explicit `gpt-5.6-luna`/`max` child-execution settings, or permissions, scope, authority, or workspace expansion beyond the parent assignment33- progress or task-reporting messages that set `model`, `reasoning_effort`, `thinking`, or analogous destination-setting overrides, or altered a parent or peer task34- task-created auxiliary worktrees without integration evidence and a verified `removed` or exact-blocker `preserved` disposition3536Ask:3738```text39Would I approve this in code review?40```4142If not, fix the issue or report the remaining risk clearly.4344Final report format:4546```text47Summary:48- Changed X to do Y.4950Verification:51- Ran: [command or check]52- Result: [passed/failed/not run, with reason]5354Notes:55- [Assumptions, unrelated issues, subagent usage, follow-ups, or risk notes if any]56```
ArcanEdge-AI