Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →MANDATORY: Run appropriate validation tools after EVERY code change. Do not finish a task until the code is error-free.
.claude/skills/sickn33-lint-and-validate/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-08 | ✗→✓ | ▲ Improved | 24% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -23% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 296% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 2% | 0% |
| case-20 | ✓→✗ | ▼ Worse | -74% | 0% |
> MANDATORY: Run appropriate validation tools after EVERY code change. Do not finish a task until the code is error-free.
npm run lint or npx eslint "path" --fixnpx tsc --noEmitnpm audit --audit-level=highruff check "path" --fix (Fast & Modern)bandit -r "path" -llmypy "path"npm run lint && npx tsc --noEmitruff check . --fix && mypy . && bandit -r . -lllint fails: Fix the style or syntax issues immediately.tsc fails: Correct type mismatches before proceeding..eslintrc, tsconfig.json, pyproject.toml and suggest creating one.Strict Rule: No code should be committed or reported as "done" without passing these checks.
| Script | Purpose | Command | |--------|---------|---------| | scripts/lint_runner.py | Unified lint check | python scripts/lint_runner.py <project_path> | | scripts/type_coverage.py | Type coverage analysis | python scripts/type_coverage.py <project_path> |
This skill is applicable to execute the workflow or actions described in the overview.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-02 | fail→fail | 4,626 | 6,669 | +44% | 1 | 1 | 0% | 192 | 821 | +328% | 0 | 0 | — |
case-01 | fail→fail | 13,497 | 22,174 | +64% | 1 | 1 | 0% | 1,350 | 1,107 | -18% | 0 | 0 | — |
case-03 | fail→fail | 43,114 | 5,399 | -87% | 1 | 1 | 0% | 223 | 858 | +285% | 0 | 0 | — |
case-04 | pass→pass | 9,020 | 3,738 | -59% | 1 | 1 | 0% | 1,578 | 997 | -37% | 0 | 0 | — |
case-05 | pass→pass | 7,584 | 3,920 | -48% | 1 | 1 | 0% | 1,248 | 1,166 | -7% | 0 | 0 | — |
case-06 | pass→pass | 5,773 | 2,132 | -63% | 1 | 1 | 0% | 963 | 884 | -8% | 0 | 0 | — |
case-07 | pass→pass | 5,720 | 2,855 | -50% | 1 | 1 | 0% | 927 | 943 | +2% | 0 | 0 | — |
case-08 | fail→pass | 13,902 | 9,038 | -35% | 1 | 1 | 0% | 1,797 | 2,228 | +24% | 0 | 0 | — |
case-09 | pass→pass | 10,410 | 4,136 | -60% | 1 | 1 | 0% | 1,851 | 1,259 | -32% | 0 | 0 | — |
case-10 | fail→pass | 6,341 | 3,953 | -38% | 1 | 1 | 0% | 1,130 | 871 | -23% | 0 | 0 | — |
case-11 | fail→pass | 2,516 | 2,151 | -15% | 1 | 1 | 0% | 229 | 906 | +296% | 0 | 0 | — |
case-12 | pass→pass | 7,199 | 3,328 | -54% | 1 | 1 | 0% | 1,098 | 1,130 | +3% | 0 | 0 | — |
case-13 | pass→pass | 6,968 | 3,795 | -46% | 1 | 1 | 0% | 997 | 1,103 | +11% | 0 | 0 | — |
case-14 | fail→pass | 5,485 | 2,760 | -50% | 1 | 1 | 0% | 924 | 938 | +2% | 0 | 0 | — |
case-15 | pass→pass | 4,780 | 1,533 | -68% | 1 | 1 | 0% | 759 | 773 | +2% | 0 | 0 | — |
case-16 | pass→pass | 3,679 | 2,387 | -35% | 1 | 1 | 0% | 583 | 950 | +63% | 0 | 0 | — |
case-17 | pass→pass | 5,310 | 2,689 | -49% | 1 | 1 | 0% | 899 | 952 | +6% | 0 | 0 | — |
case-18 | pass→pass | 11,995 | 4,413 | -63% | 1 | 1 | 0% | 1,671 | 1,331 | -20% | 0 | 0 | — |
case-19 | pass→pass | 6,434 | 2,332 | -64% | 1 | 1 | 0% | 1,152 | 935 | -19% | 0 | 0 | — |
case-20 | pass→fail | 17,903 | 5,740 | -68% | 1 | 1 | 0% | 3,624 | 926 | -74% | 0 | 0 | — |
case-21 | pass→fail | 30,224 | 4,130 | -86% | 1 | 1 | 0% | 6,827 | 718 | -89% | 0 | 0 | — |
case-22 | pass→fail | 16,847 | 6,849 | -59% | 1 | 1 | 0% | 3,354 | 1,314 | -61% | 0 | 0 | — |
case-23 | pass→pass | 11,770 | 35,892 | +205% | 1 | 1 | 0% | 1,848 | 6,076 | +229% | 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 +4 percentage points is the difference between those two pass rates over the 17 comparable cases. 4 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.