Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
.claude/skills/dokhacgiakhoa-receiving-code-review/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -12% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -19% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 2% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -5% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -24% | 0% |
Code review requires technical evaluation, not emotional performance.
Core principle: Verify before implementing. Ask before assuming. Technical correctness over social comfort.
WHEN receiving code review feedback:
1. READ: Complete feedback without reacting
2. UNDERSTAND: Restate requirement in own words (or ask)
3. VERIFY: Check against codebase reality
4. EVALUATE: Technically sound for THIS codebase?
5. RESPOND: Technical acknowledgment or reasoned pushback
6. IMPLEMENT: One item at a time, test eachNEVER:
INSTEAD:
IF any item is unclear:
STOP - do not implement anything yet
ASK for clarification on unclear items
WHY: Items may be related. Partial understanding = wrong implementation.Example:
your human partner: "Fix 1-6"
You understand 1,2,3,6. Unclear on 4,5.
❌ WRONG: Implement 1,2,3,6 now, ask about 4,5 later
✅ RIGHT: "I understand items 1,2,3,6. Need clarification on 4 and 5 before proceeding."| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 9,805 | 6,118 | -38% | 1 | 1 | 0% | 1,639 | 1,449 | -12% | 0 | 0 | — |
case-02 | fail→pass | 8,597 | 4,103 | -52% | 1 | 1 | 0% | 1,461 | 1,185 | -19% | 0 | 0 | — |
case-03 | pass→pass | 10,760 | 4,691 | -56% | 1 | 1 | 0% | 1,798 | 1,250 | -30% | 0 | 0 | — |
case-04 | pass→pass | 7,046 | 5,215 | -26% | 1 | 1 | 0% | 1,230 | 1,229 | -0% | 0 | 0 | — |
case-05 | pass→pass | 12,499 | 9,957 | -20% | 1 | 1 | 0% | 2,054 | 1,699 | -17% | 0 | 0 | — |
case-06 | pass→pass | 15,809 | 4,700 | -70% | 1 | 1 | 0% | 1,145 | 1,128 | -1% | 0 | 0 | — |
case-07 | pass→pass | 8,092 | 4,826 | -40% | 1 | 1 | 0% | 1,283 | 1,288 | +0% | 0 | 0 | — |
case-08 | fail→pass | 9,014 | 7,418 | -18% | 1 | 1 | 0% | 1,484 | 1,507 | +2% | 0 | 0 | — |
case-09 | pass→pass | 7,774 | 5,453 | -30% | 1 | 1 | 0% | 1,360 | 1,331 | -2% | 0 | 0 | — |
case-10 | fail→pass | 7,629 | 3,596 | -53% | 1 | 1 | 0% | 1,086 | 1,029 | -5% | 0 | 0 | — |
case-11 | fail→pass | 9,789 | 5,027 | -49% | 1 | 1 | 0% | 1,730 | 1,321 | -24% | 0 | 0 | — |
case-12 | pass→pass | 6,175 | 3,259 | -47% | 1 | 1 | 0% | 1,273 | 960 | -25% | 0 | 0 | — |
case-13 | fail→pass | 6,024 | 2,883 | -52% | 1 | 1 | 0% | 957 | 899 | -6% | 0 | 0 | — |
case-14 | pass→fail | 5,185 | 3,623 | -30% | 1 | 1 | 0% | 896 | 1,067 | +19% | 0 | 0 | — |
case-15 | pass→pass | 7,769 | 3,552 | -54% | 1 | 1 | 0% | 1,241 | 986 | -21% | 0 | 0 | — |
case-16 | fail→pass | 11,763 | 8,061 | -31% | 1 | 1 | 0% | 1,961 | 1,910 | -3% | 0 | 0 | — |
case-17 | pass→pass | 16,209 | 9,175 | -43% | 1 | 1 | 0% | 2,331 | 1,898 | -19% | 0 | 0 | — |
case-18 | pass→pass | 8,634 | 5,110 | -41% | 1 | 1 | 0% | 1,518 | 1,108 | -27% | 0 | 0 | — |
case-19 | pass→fail | 8,432 | 4,282 | -49% | 1 | 1 | 0% | 1,371 | 1,086 | -21% | 0 | 0 | — |
case-20 | fail→fail | 5,787 | 3,808 | -34% | 1 | 1 | 0% | 1,062 | 1,113 | +5% | 0 | 0 | — |
case-21 | fail→pass | 11,320 | 26,787 | +137% | 1 | 1 | 0% | 1,802 | 1,390 | -23% | 0 | 0 | — |
case-22 | fail→pass | 9,651 | 4,939 | -49% | 1 | 1 | 0% | 1,583 | 1,259 | -20% | 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. 22 cases were attempted. The headline lift of +32 percentage points is the difference between those two pass rates over the 22 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.