Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Auto-fix issues found by code review in REVIEW.md. Spawns fixer agent, commits each fix atomically, produces REVIEW-FIX.md summary.
.claude/skills/coco-research-gsd-code-review-fix/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-05 | ✗→✓ | ▲ Improved | -39% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -59% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -69% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -67% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -60% | 0% |
<objective> Auto-fix issues found by code review. Reads REVIEW.md from the specified phase, spawns gsd-code-fixer agent to apply fixes, and produces REVIEW-FIX.md summary.
Arguments:
--all (optional) — include Info findings in fix scope (default: Critical + Warning only)--auto (optional) — enable fix + re-review iteration loop, capped at 3 iterationsOutput: {padded_phase}-REVIEW-FIX.md in phase directory + inline summary of fixes applied </objective>
<execution_context> @$HOME/.claude/get-shit-done/workflows/code-review-fix.md </execution_context>
<context> Phase: $ARGUMENTS (first positional argument is phase number)
Optional flags parsed from $ARGUMENTS:
--all — Include Info findings in fix scope. Default behavior fixes Critical + Warning only.--auto — Enable fix + re-review iteration loop. After applying fixes, re-run code-review at same depth. If new issues found, iterate. Cap at 3 iterations total. Without this flag, single fix pass only.Context files (CLAUDE.md, REVIEW.md, phase state) are resolved inside the workflow via gsd-tools init phase-op and delegated to agent via config blocks. </context>
<process> This command is a thin dispatch layer. It parses arguments and delegates to the workflow.
Execute the code-review-fix workflow from @$HOME/.claude/get-shit-done/workflows/code-review-fix.md end-to-end.
The workflow (not this command) enforces these gates:
</process>
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 19,155 | 16,977 | -11% | 1 | 1 | 0% | 1,018 | 870 | -15% | 0 | 0 | — |
case-02 | fail→fail | 10,532 | 11,131 | +6% | 1 | 1 | 0% | 854 | 752 | -12% | 0 | 0 | — |
case-03 | fail→fail | 11,138 | 12,149 | +9% | 1 | 1 | 0% | 1,026 | 789 | -23% | 0 | 0 | — |
case-04 | pass→pass | 10,465 | 9,658 | -8% | 1 | 1 | 0% | 1,731 | 1,234 | -29% | 0 | 0 | — |
case-05 | fail→pass | 16,418 | 8,647 | -47% | 1 | 1 | 0% | 1,786 | 1,083 | -39% | 0 | 0 | — |
case-06 | pass→pass | 12,281 | 8,233 | -33% | 1 | 1 | 0% | 1,812 | 955 | -47% | 0 | 0 | — |
case-07 | pass→pass | 10,763 | 8,486 | -21% | 1 | 1 | 0% | 1,461 | 1,118 | -23% | 0 | 0 | — |
case-08 | fail→pass | 17,107 | 7,365 | -57% | 1 | 1 | 0% | 1,984 | 808 | -59% | 0 | 0 | — |
case-09 | fail→pass | 20,310 | 2,362 | -88% | 1 | 1 | 0% | 2,744 | 858 | -69% | 0 | 0 | — |
case-10 | fail→pass | 12,731 | 8,010 | -37% | 1 | 1 | 0% | 2,106 | 685 | -67% | 0 | 0 | — |
case-11 | fail→pass | 11,316 | 6,619 | -42% | 1 | 1 | 0% | 1,869 | 745 | -60% | 0 | 0 | — |
case-12 | pass→pass | 9,597 | 8,721 | -9% | 1 | 1 | 0% | 1,405 | 1,113 | -21% | 0 | 0 | — |
case-13 | pass→fail | 15,728 | 8,513 | -46% | 1 | 1 | 0% | 1,717 | 880 | -49% | 0 | 0 | — |
case-14 | fail→pass | 17,696 | 6,692 | -62% | 1 | 1 | 0% | 2,687 | 715 | -73% | 0 | 0 | — |
case-15 | fail→fail | 9,473 | 1,851 | -80% | 1 | 1 | 0% | 812 | 750 | -8% | 0 | 0 | — |
case-16 | fail→pass | 10,297 | 10,079 | -2% | 1 | 1 | 0% | 1,425 | 1,339 | -6% | 0 | 0 | — |
case-17 | pass→pass | 15,034 | 8,786 | -42% | 1 | 1 | 0% | 1,651 | 1,043 | -37% | 0 | 0 | — |
case-18 | pass→pass | 13,545 | 4,376 | -68% | 1 | 1 | 0% | 1,108 | 1,214 | +10% | 0 | 0 | — |
case-19 | fail→pass | 16,628 | 2,439 | -85% | 1 | 1 | 0% | 2,613 | 787 | -70% | 0 | 0 | — |
case-20 | fail→pass | 13,019 | 3,439 | -74% | 1 | 1 | 0% | 1,247 | 1,006 | -19% | 0 | 0 | — |
case-21 | fail→pass | 9,729 | 17,902 | +84% | 1 | 1 | 0% | 177 | 2,600 | +1369% | 0 | 0 | — |
case-22 | pass→fail | 10,377 | 11,325 | +9% | 1 | 1 | 0% | 1,934 | 738 | -62% | 0 | 0 | — |
case-23 | pass→fail | 18,773 | 8,846 | -53% | 1 | 1 | 0% | 4,109 | 757 | -82% | 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, and 17 counted toward the lift figure. The other 6 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 +30 percentage points is the difference between those two pass rates over the 17 comparable cases. 3 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.