Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Systematically evaluate code changes for security, correctness, performance, and spec alignment. Use when reviewing PRs, assessing code quality, or verifying implementation against requirements.
.claude/skills/microck-reviewing-code/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | 30% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 25% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -13% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -34% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 10% | 0% |
Evaluate code changes across security, correctness, spec alignment, performance, and maintainability. Apply sequential or parallel review based on scope.
Sequential (small PRs, <5 files):
Parallel (large PRs, >5 files):
Read documentation:
docs/feature-spec/F-##-*.md — Technical design and requirementsdocs/user-stories/US-###-*.md — Acceptance criteriadocs/api-contracts.yaml — Expected API signaturesdocs/data-plan.md — Event tracking requirements (if applicable)docs/design-spec.md — UI/UX requirements (if applicable)docs/system-design.md — Architecture patterns (if available)docs/plans/<slug>/plan.md — Original implementation plan (if available)Determine scope:
Security (/25)
Correctness (/25)
Spec Alignment (/20)
docs/api-contracts.yamldocs/data-plan.mddocs/design-spec.mdPerformance (/15)
Maintainability (/15)
Total: /100
Format:
Location: file.ts:123
Problem: [Description]
Impact: [Risk/consequence]
Fix: [Specific change needed]
Spec reference: [docs/api-contracts.yaml line X]Highlight what was done well for learning
Best for <5 files, single concern:
Best for >5 files, multiple concerns:
senior-engineer for vulnerability assessmentExplore for pattern complianceprogrammer for endpoint validationprogrammer for UI/UX and accessibilitydocumentor for comment quality and docs# Code Review: [Feature/PR]
## Summary
**Quality Score:** [X/100]
**Issues:** Critical: [N], Important: [N], Nice-to-have: [N]
**Assessment:** [APPROVE / NEEDS REVISION / MAJOR REWORK]
## Spec Compliance
- [ ] APIs match `docs/api-contracts.yaml`
- [ ] Events match `docs/data-plan.md`
- [ ] UI matches `docs/design-spec.md`
- [ ] Logic satisfies story AC
## Findings
### Critical Issues
[Issues with fix recommendations]
### Important Issues
[Issues that should be addressed]
### Nice-to-Have Suggestions
[Optional improvements]
### Good Practices
[What worked well]
## Recommendations
[Next steps: approval, revision needed, etc.]Offer options:
Parallel fixes for large revisions:
Document format:
✅ FIXED: [Issue name]
File: [path:line]
Change: [what changed]
Verification: [how to test]Check if specs need updates:
Always flag for user approval before modifying specs.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-03 | fail→fail | 14,108 | 16,869 | +20% | 1 | 1 | 0% | 1,588 | 2,556 | +61% | 0 | 0 | — |
case-01 | fail→fail | 8,107 | 16,228 | +100% | 1 | 1 | 0% | 972 | 2,445 | +152% | 0 | 0 | — |
case-02 | fail→fail | 17,540 | 10,876 | -38% | 1 | 1 | 0% | 2,797 | 2,995 | +7% | 0 | 0 | — |
case-04 | pass→fail | 24,860 | 2,789 | -89% | 1 | 1 | 0% | 5,513 | 1,496 | -73% | 0 | 0 | — |
case-05 | pass→pass | 20,341 | 18,924 | -7% | 1 | 1 | 0% | 3,760 | 4,819 | +28% | 0 | 0 | — |
case-06 | pass→fail | 9,795 | 3,408 | -65% | 1 | 1 | 0% | 1,594 | 1,549 | -3% | 0 | 0 | — |
case-07 | fail→pass | 11,123 | 6,805 | -39% | 1 | 1 | 0% | 1,731 | 2,246 | +30% | 0 | 0 | — |
case-08 | fail→pass | 11,874 | 7,111 | -40% | 1 | 1 | 0% | 2,032 | 2,540 | +25% | 0 | 0 | — |
case-09 | fail→pass | 11,135 | 2,463 | -78% | 1 | 1 | 0% | 1,976 | 1,714 | -13% | 0 | 0 | — |
case-10 | fail→pass | 23,445 | 1,990 | -92% | 1 | 1 | 0% | 2,401 | 1,585 | -34% | 0 | 0 | — |
case-11 | fail→pass | 9,646 | 2,610 | -73% | 1 | 1 | 0% | 1,559 | 1,722 | +10% | 0 | 0 | — |
case-12 | fail→pass | 10,994 | 4,728 | -57% | 1 | 1 | 0% | 2,003 | 1,749 | -13% | 0 | 0 | — |
case-13 | fail→pass | 7,729 | 1,793 | -77% | 1 | 1 | 0% | 1,213 | 1,557 | +28% | 0 | 0 | — |
case-19 | pass→pass | 13,518 | 8,214 | -39% | 1 | 1 | 0% | 2,266 | 2,452 | +8% | 0 | 0 | — |
case-14 | fail→pass | 8,193 | 2,636 | -68% | 1 | 1 | 0% | 1,424 | 1,643 | +15% | 0 | 0 | — |
case-15 | fail→pass | 6,401 | 2,090 | -67% | 1 | 1 | 0% | 976 | 1,613 | +65% | 0 | 0 | — |
case-16 | pass→pass | 9,237 | 3,597 | -61% | 1 | 1 | 0% | 1,413 | 1,851 | +31% | 0 | 0 | — |
case-17 | fail→pass | 7,888 | 2,413 | -69% | 1 | 1 | 0% | 1,194 | 1,640 | +37% | 0 | 0 | — |
case-18 | fail→pass | 15,145 | 6,723 | -56% | 1 | 1 | 0% | 2,280 | 2,406 | +6% | 0 | 0 | — |
case-20 | pass→pass | 12,045 | 7,090 | -41% | 1 | 1 | 0% | 1,922 | 2,333 | +21% | 0 | 0 | — |
case-21 | fail→pass | 10,366 | 4,090 | -61% | 1 | 1 | 0% | 1,658 | 1,928 | +16% | 0 | 0 | — |
case-22 | fail→pass | 10,423 | 1,393 | -87% | 1 | 1 | 0% | 1,669 | 1,467 | -12% | 0 | 0 | — |
case-23 | fail→pass | 10,813 | 3,021 | -72% | 1 | 1 | 0% | 1,670 | 1,736 | +4% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted. The headline lift of +52 percentage points is the difference between those two pass rates over the 23 comparable cases. 2 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.