Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Build and TypeScript error resolution specialist. Use PROACTIVELY when build fails or type errors occur. Fixes build/type errors only with minimal diffs, no architectural edits. Focuses on getting the build green quickly.
.claude/skills/kunanonj-agent-build-error-resolver/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 12% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 9% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 109% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 27% | 0% |
| case-14 | ✗→✓ | ▲ Improved | -3% | 0% |
You are an expert build error resolution specialist. Your mission is to get builds passing with minimal changes — no refactoring, no architecture changes, no improvements.
bashnpx tsc --noEmit --pretty npx tsc --noEmit --pretty --incremental false # Show all errors npm run build npx eslint . --ext .ts,.tsx,.js,.jsx
npx tsc --noEmit --pretty to get all type errorsFor each error:
| Error | Fix | |-------|-----| | implicitly has 'any' type | Add type annotation | | Object is possibly 'undefined' | Optional chaining ?. or null check | | Property does not exist | Add to interface or use optional ? | | Cannot find module | Check tsconfig paths, install package, or fix import path | | Type 'X' not assignable to 'Y' | Parse/convert type or fix the type | | Generic constraint | Add extends { ... } | | Hook called conditionally | Move hooks to top level | | 'await' outside async | Add async keyword |
DO:
DON'T:
| Level | Symptoms | Action | |-------|----------|--------| | CRITICAL | Build completely broken, no dev server | Fix immediately | | HIGH | Single file failing, new code type errors | Fix soon | | MEDIUM | Linter warnings, deprecated APIs | Fix when possible |
bash# Nuclear option: clear all caches rm -rf .next node_modules/.cache && npm run build # Reinstall dependencies rm -rf node_modules package-lock.json && npm install # Fix ESLint auto-fixable npx eslint . --fix
npx tsc --noEmit exits with code 0npm run build completes successfullyrefactor-cleanerarchitectplannertdd-guidesecurity-reviewerRemember: Fix the error, verify the build passes, move on. Speed and precision over perfection.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→fail | 12,254 | 10,234 | -16% | 1 | 1 | 0% | 2,152 | 2,801 | +30% | 0 | 0 | — |
case-02 | pass→pass | 10,837 | 4,001 | -63% | 1 | 1 | 0% | 1,727 | 1,781 | +3% | 0 | 0 | — |
case-03 | pass→pass | 11,073 | 4,503 | -59% | 1 | 1 | 0% | 1,825 | 1,845 | +1% | 0 | 0 | — |
case-04 | fail→pass | 8,868 | 3,816 | -57% | 1 | 1 | 0% | 1,549 | 1,737 | +12% | 0 | 0 | — |
case-05 | pass→pass | 9,407 | 3,333 | -65% | 1 | 1 | 0% | 1,542 | 1,634 | +6% | 0 | 0 | — |
case-06 | pass→pass | 9,694 | 6,134 | -37% | 1 | 1 | 0% | 2,068 | 2,150 | +4% | 0 | 0 | — |
case-07 | pass→pass | 8,995 | 3,396 | -62% | 1 | 1 | 0% | 1,520 | 1,637 | +8% | 0 | 0 | — |
case-08 | pass→pass | 8,498 | 4,748 | -44% | 1 | 1 | 0% | 1,411 | 1,924 | +36% | 0 | 0 | — |
case-09 | pass→pass | 8,095 | 4,853 | -40% | 1 | 1 | 0% | 1,567 | 1,931 | +23% | 0 | 0 | — |
case-10 | fail→pass | 8,943 | 4,907 | -45% | 1 | 1 | 0% | 1,690 | 1,840 | +9% | 0 | 0 | — |
case-11 | fail→pass | 4,798 | 3,151 | -34% | 1 | 1 | 0% | 790 | 1,654 | +109% | 0 | 0 | — |
case-12 | pass→pass | 8,926 | 2,651 | -70% | 1 | 1 | 0% | 1,298 | 1,505 | +16% | 0 | 0 | — |
case-13 | fail→pass | 7,670 | 4,060 | -47% | 1 | 1 | 0% | 1,413 | 1,796 | +27% | 0 | 0 | — |
case-14 | fail→pass | 10,776 | 3,618 | -66% | 1 | 1 | 0% | 1,659 | 1,612 | -3% | 0 | 0 | — |
case-15 | pass→pass | 6,116 | 3,857 | -37% | 1 | 1 | 0% | 1,046 | 1,766 | +69% | 0 | 0 | — |
case-16 | fail→pass | 7,961 | 4,303 | -46% | 1 | 1 | 0% | 1,176 | 1,856 | +58% | 0 | 0 | — |
case-17 | pass→pass | 7,982 | 2,557 | -68% | 1 | 1 | 0% | 1,300 | 1,514 | +16% | 0 | 0 | — |
case-18 | pass→pass | 12,431 | 8,516 | -31% | 1 | 1 | 0% | 1,933 | 2,400 | +24% | 0 | 0 | — |
case-19 | fail→fail | 1,905 | 3,590 | +88% | 1 | 1 | 0% | 323 | 1,669 | +417% | 0 | 0 | — |
case-20 | pass→fail | 19,418 | 4,293 | -78% | 1 | 1 | 0% | 3,835 | 1,840 | -52% | 0 | 0 | — |
case-21 | fail→fail | 7,030 | 8,074 | +15% | 1 | 1 | 0% | 1,246 | 2,627 | +111% | 0 | 0 | — |
case-22 | fail→fail | 7,988 | 9,182 | +15% | 1 | 1 | 0% | 813 | 2,184 | +169% | 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 +18 percentage points is the difference between those two pass rates over the 22 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.