Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when completing tasks, implementing major features, or before merging to verify work meets requirements
.claude/skills/jamditis-requesting-code-review/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-10 | ✗→✓ | ▲ Improved | 25% | 0% |
| case-15 | ✗→✓ | ▲ Improved | -43% | 0% |
| case-22 | ✗→✓ | ▲ Improved | 13% | 0% |
| case-23 | ✗→✓ | ▲ Improved | 7% | 0% |
| case-25 | ✗→✓ | ▲ Improved | -2% | 0% |
<!-- Adapted from obra/superpowers requesting-code-review skill (v5.0.7), MIT-licensed, copyright 2025 Jesse Vincent. Modifications copyright 2026 Joe Amditis. v0.4.0 ports as a consumer category, no research phase per the v0.2.0 architecture, since dispatch mechanic; reviewer preferences live in CLAUDE.md and memory rather than a research phase. See CREDITS.md. -->
Dispatch pr-review-toolkit:code-reviewer subagent to catch issues before they cascade. The reviewer gets precisely crafted context for evaluation, never your session's history. This keeps the reviewer focused on the work product, not your thought process, and preserves your own context for continued work.
Core principle: Review early, review often.
Mandatory:
Optional but valuable:
1. Get git SHAs:
bashBASE_SHA=$(git rev-parse HEAD~1) # or origin/main HEAD_SHA=$(git rev-parse HEAD)
2. Dispatch code-reviewer subagent:
Use Task tool with pr-review-toolkit:code-reviewer type, fill template at code-reviewer.md
Placeholders:
{WHAT_WAS_IMPLEMENTED} - What you just built{PLAN_OR_REQUIREMENTS} - What it should do{BASE_SHA} - Starting commit{HEAD_SHA} - Ending commit{DESCRIPTION} - Brief summary3. Act on feedback:
[Just completed Task 2: Add verification function]
You: Let me request code review before proceeding.
BASE_SHA=$(git log --oneline | grep "Task 1" | head -1 | awk '{print $1}')
HEAD_SHA=$(git rev-parse HEAD)
[Dispatch pr-review-toolkit:code-reviewer subagent]
WHAT_WAS_IMPLEMENTED: Verification and repair functions for conversation index
PLAN_OR_REQUIREMENTS: Task 2 from docs/superpowers/plans/deployment-plan.md
BASE_SHA: a7981ec
HEAD_SHA: 3df7661
DESCRIPTION: Added verifyIndex() and repairIndex() with 4 issue types
[Subagent returns]:
Strengths: Clean architecture, real tests
Issues:
Important: Missing progress indicators
Minor: Magic number (100) for reporting interval
Assessment: Ready to proceed
You: [Fix progress indicators]
[Continue to Task 3]Subagent-Driven Development:
Executing Plans:
Ad-Hoc Development:
Never:
If reviewer wrong:
See template at: requesting-code-review/code-reviewer.md
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-03 | fail→fail | 7,288 | 2,524 | -65% | 1 | 1 | 0% | 1,190 | 1,098 | -8% | 0 | 0 | — |
case-01 | fail→fail | 8,695 | 2,275 | -74% | 1 | 1 | 0% | 1,498 | 1,099 | -27% | 0 | 0 | — |
case-02 | fail→fail | 12,138 | 3,318 | -73% | 1 | 1 | 0% | 1,510 | 1,210 | -20% | 0 | 0 | — |
case-04 | pass→pass | 10,329 | 8,669 | -16% | 1 | 1 | 0% | 2,015 | 2,279 | +13% | 0 | 0 | — |
case-05 | pass→pass | 12,575 | 42,365 | +237% | 1 | 1 | 0% | 2,141 | 2,856 | +33% | 0 | 0 | — |
case-06 | pass→pass | 15,788 | 16,430 | +4% | 1 | 1 | 0% | 2,608 | 3,031 | +16% | 0 | 0 | — |
case-07 | pass→pass | 8,455 | 6,189 | -27% | 1 | 1 | 0% | 1,407 | 1,804 | +28% | 0 | 0 | — |
case-08 | pass→pass | 11,383 | 5,011 | -56% | 1 | 1 | 0% | 1,775 | 1,630 | -8% | 0 | 0 | — |
case-09 | pass→pass | 12,132 | 36,827 | +204% | 1 | 1 | 0% | 1,929 | 1,914 | -1% | 0 | 0 | — |
case-10 | fail→pass | 14,591 | 10,063 | -31% | 1 | 1 | 0% | 2,094 | 2,616 | +25% | 0 | 0 | — |
case-11 | pass→pass | 27,533 | 4,564 | -83% | 1 | 1 | 0% | 2,099 | 1,631 | -22% | 0 | 0 | — |
case-12 | pass→pass | 10,956 | 6,075 | -45% | 1 | 1 | 0% | 1,716 | 1,551 | -10% | 0 | 0 | — |
case-13 | pass→pass | 10,965 | 5,616 | -49% | 1 | 1 | 0% | 1,548 | 1,976 | +28% | 0 | 0 | — |
case-14 | pass→pass | 8,331 | 4,729 | -43% | 1 | 1 | 0% | 1,698 | 1,729 | +2% | 0 | 0 | — |
case-15 | fail→pass | 12,525 | 3,006 | -76% | 1 | 1 | 0% | 2,433 | 1,398 | -43% | 0 | 0 | — |
case-16 | pass→pass | 10,720 | 5,114 | -52% | 1 | 1 | 0% | 1,614 | 1,723 | +7% | 0 | 0 | — |
case-17 | pass→pass | 12,800 | 5,877 | -54% | 1 | 1 | 0% | 2,147 | 1,801 | -16% | 0 | 0 | — |
case-18 | pass→pass | 9,341 | 3,792 | -59% | 1 | 1 | 0% | 1,535 | 1,486 | -3% | 0 | 0 | — |
case-19 | pass→pass | 12,325 | 8,362 | -32% | 1 | 1 | 0% | 1,951 | 2,220 | +14% | 0 | 0 | — |
case-20 | pass→pass | 9,491 | 4,792 | -50% | 1 | 1 | 0% | 1,665 | 1,686 | +1% | 0 | 0 | — |
case-21 | pass→pass | 8,670 | 4,343 | -50% | 1 | 1 | 0% | 1,465 | 1,627 | +11% | 0 | 0 | — |
case-22 | fail→pass | 9,100 | 5,261 | -42% | 1 | 1 | 0% | 1,638 | 1,849 | +13% | 0 | 0 | — |
case-23 | fail→pass | 6,658 | 2,728 | -59% | 1 | 1 | 0% | 1,244 | 1,325 | +7% | 0 | 0 | — |
case-24 | pass→pass | 7,096 | 2,863 | -60% | 1 | 1 | 0% | 1,175 | 1,331 | +13% | 0 | 0 | — |
case-25 | fail→pass | 8,728 | 3,808 | -56% | 1 | 1 | 0% | 1,466 | 1,443 | -2% | 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. 25 cases were attempted. The headline lift of +20 percentage points is the difference between those two pass rates over the 25 comparable cases.
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.
| Model | Method | Date | Lift |
|---|---|---|---|
| gemini-3.6-flash | verified | 8/21/2026 | +18% |
Other measured skills in the registry, with their headline benchmark lift.