Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Prepare and request a code review after implementation or before merge by assembling scope, requirements, git range, and reviewer instructions.
.claude/skills/foryourhealth111-pixel-requesting-code-review/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -18% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 24% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -8% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 41% | 0% |
| case-15 | ✗→✓ | ▲ Improved | -22% | 0% |
Prepare a complete review request so the reviewer can evaluate the exact change against the intended requirements.
Core principle: Review early, review often.
Use this skill when the user needs to prepare or request a code review.
This skill owns the request package: implementation summary, requirements reference, base/head git range, reviewer prompt, and response handling checklist.
Use code-reviewer for the actual review findings.
Use receiving-code-review when review feedback already exists and must be evaluated or applied.
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 superpowers: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 superpowers:code-reviewer subagent]
WHAT_WAS_IMPLEMENTED: Verification and repair functions for conversation index
PLAN_OR_REQUIREMENTS: Task 2 from docs/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-01 | fail→pass | 10,976 | 5,543 | -49% | 1 | 1 | 0% | 1,942 | 1,591 | -18% | 0 | 0 | — |
case-02 | fail→pass | 10,180 | 8,109 | -20% | 1 | 1 | 0% | 1,803 | 2,244 | +24% | 0 | 0 | — |
case-03 | fail→fail | 10,383 | 5,778 | -44% | 1 | 1 | 0% | 1,618 | 971 | -40% | 0 | 0 | — |
case-04 | fail→fail | 8,378 | 11,069 | +32% | 1 | 1 | 0% | 812 | 2,018 | +149% | 0 | 0 | — |
case-05 | pass→pass | 12,270 | 7,026 | -43% | 1 | 1 | 0% | 1,936 | 1,833 | -5% | 0 | 0 | — |
case-06 | pass→pass | 4,645 | 3,482 | -25% | 1 | 1 | 0% | 863 | 1,396 | +62% | 0 | 0 | — |
case-07 | pass→pass | 11,066 | 4,440 | -60% | 1 | 1 | 0% | 1,776 | 1,518 | -15% | 0 | 0 | — |
case-08 | pass→pass | 11,966 | 6,297 | -47% | 1 | 1 | 0% | 1,879 | 1,735 | -8% | 0 | 0 | — |
case-09 | fail→pass | 9,825 | 3,365 | -66% | 1 | 1 | 0% | 1,482 | 1,357 | -8% | 0 | 0 | — |
case-10 | pass→pass | 10,155 | 6,289 | -38% | 1 | 1 | 0% | 1,639 | 1,711 | +4% | 0 | 0 | — |
case-11 | pass→pass | 9,468 | 5,925 | -37% | 1 | 1 | 0% | 1,387 | 1,691 | +22% | 0 | 0 | — |
case-12 | pass→pass | 11,331 | 8,311 | -27% | 1 | 1 | 0% | 1,939 | 1,983 | +2% | 0 | 0 | — |
case-13 | pass→pass | 8,629 | 3,711 | -57% | 1 | 1 | 0% | 1,364 | 1,303 | -4% | 0 | 0 | — |
case-14 | fail→pass | 6,061 | 4,072 | -33% | 1 | 1 | 0% | 1,086 | 1,536 | +41% | 0 | 0 | — |
case-15 | fail→pass | 6,815 | 1,703 | -75% | 1 | 1 | 0% | 1,171 | 917 | -22% | 0 | 0 | — |
case-16 | pass→pass | 10,572 | 4,266 | -60% | 1 | 1 | 0% | 1,566 | 1,465 | -6% | 0 | 0 | — |
case-17 | fail→pass | 13,329 | 7,897 | -41% | 1 | 1 | 0% | 2,052 | 1,953 | -5% | 0 | 0 | — |
case-18 | pass→pass | 6,699 | 2,875 | -57% | 1 | 1 | 0% | 1,060 | 1,185 | +12% | 0 | 0 | — |
case-19 | pass→pass | 11,121 | 5,329 | -52% | 1 | 1 | 0% | 1,852 | 1,787 | -4% | 0 | 0 | — |
case-20 | fail→pass | 8,378 | 2,462 | -71% | 1 | 1 | 0% | 1,292 | 1,103 | -15% | 0 | 0 | — |
case-21 | pass→pass | 12,729 | 4,980 | -61% | 1 | 1 | 0% | 1,964 | 1,497 | -24% | 0 | 0 | — |
case-22 | fail→pass | 12,254 | 6,784 | -45% | 1 | 1 | 0% | 2,011 | 1,904 | -5% | 0 | 0 | — |
case-23 | pass→pass | 12,225 | 9,381 | -23% | 1 | 1 | 0% | 1,907 | 2,116 | +11% | 0 | 0 | — |
case-24 | pass→pass | 9,531 | 2,490 | -74% | 1 | 1 | 0% | 1,460 | 1,073 | -27% | 0 | 0 | — |
case-25 | fail→pass | 11,650 | 2,320 | -80% | 1 | 1 | 0% | 1,977 | 1,097 | -45% | 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, and 24 counted toward the lift figure. The other 1 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +36 percentage points is the difference between those two pass rates over the 24 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.
Other measured skills in the registry, with their headline benchmark lift.