Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when setting up a new TypeScript project, auditing an existing tsconfig.json, or reviewing code where null-reference errors or implicit any types are present.
.claude/skills/thedaviddias-typescript-strict-mode/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | -12% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 22% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | 9% | 0% |
| case-05 | ✓→✓ | ＝ Same ✓ | 16% | 0% |
| case-06 | ✓→✓ | ＝ Same ✓ | 15% | 0% |
Without strict mode, TypeScript allows implicit any types, ignores possible null/undefined values, and silently accepts unsound function assignments — meaning the type system gives a false sense of safety. Enabling strict mode makes TypeScript catch the bugs it was designed to prevent, turning type errors into compile-time failures rather than runtime surprises in production.
Inspect the tsconfig.json in this project and report whether "strict": true (or individual strict flags) is enabled. List any missing strict flags.
Add "strict": true to the compilerOptions in tsconfig.json. If the project has existing type errors, explain how to enable strictNullChecks first as a stepping stone.
Explain what TypeScript strict mode enables, which individual flags it activates, and why each flag matters for catching real bugs.
Check whether the codebase relies on implicit any, unchecked null access, or loose function type assignments that strict mode would reject. Flag the specific patterns and show what stricter types would look like.
For full implementation details, code examples, and framework-specific guidance, see references/rule.md.
Rule page: https://frontendchecklist.io/en/rules/javascript/typescript-strict-mode
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 3,382 | 3,711 | +10% | 1 | 1 | 0% | 594 | 511 | -14% | 0 | 0 | — |
case-07 | fail→pass | 14,482 | 10,421 | -28% | 1 | 1 | 0% | 2,491 | 2,181 | -12% | 0 | 0 | — |
case-02 | fail→fail | 14,187 | 1,402 | -90% | 1 | 1 | 0% | 2,554 | 504 | -80% | 0 | 0 | — |
case-03 | pass→pass | 14,147 | 13,086 | -7% | 1 | 1 | 0% | 2,441 | 2,660 | +9% | 0 | 0 | — |
case-04 | fail→pass | 8,595 | 9,202 | +7% | 1 | 1 | 0% | 1,674 | 2,045 | +22% | 0 | 0 | — |
case-05 | pass→pass | 7,802 | 7,866 | +1% | 1 | 1 | 0% | 1,669 | 1,941 | +16% | 0 | 0 | — |
case-06 | pass→pass | 7,475 | 6,895 | -8% | 1 | 1 | 0% | 1,445 | 1,664 | +15% | 0 | 0 | — |
case-08 | pass→pass | 6,937 | 11,615 | +67% | 1 | 1 | 0% | 1,445 | 2,854 | +98% | 0 | 0 | — |
case-09 | pass→pass | 11,429 | 8,464 | -26% | 1 | 1 | 0% | 2,156 | 2,007 | -7% | 0 | 0 | — |
case-10 | pass→pass | 11,933 | 13,378 | +12% | 1 | 1 | 0% | 2,145 | 2,968 | +38% | 0 | 0 | — |
case-11 | pass→pass | 4,616 | 4,480 | -3% | 1 | 1 | 0% | 848 | 1,200 | +42% | 0 | 0 | — |
case-12 | pass→pass | 9,894 | 11,367 | +15% | 1 | 1 | 0% | 1,923 | 2,401 | +25% | 0 | 0 | — |
case-13 | pass→pass | 5,175 | 8,622 | +67% | 1 | 1 | 0% | 1,071 | 2,017 | +88% | 0 | 0 | — |
case-14 | pass→pass | 9,886 | 13,052 | +32% | 1 | 1 | 0% | 1,917 | 2,820 | +47% | 0 | 0 | — |
case-15 | fail→fail | 16,373 | 13,174 | -20% | 1 | 1 | 0% | 2,693 | 2,491 | -8% | 0 | 0 | — |
case-16 | pass→pass | 10,452 | 8,721 | -17% | 1 | 1 | 0% | 1,916 | 1,968 | +3% | 0 | 0 | — |
case-17 | pass→pass | 7,555 | 11,288 | +49% | 1 | 1 | 0% | 1,548 | 2,676 | +73% | 0 | 0 | — |
case-18 | fail→fail | 13,013 | 12,576 | -3% | 1 | 1 | 0% | 2,544 | 2,775 | +9% | 0 | 0 | — |
case-19 | pass→pass | 11,244 | 12,281 | +9% | 1 | 1 | 0% | 1,687 | 2,389 | +42% | 0 | 0 | — |
case-20 | pass→pass | 5,713 | 4,795 | -16% | 1 | 1 | 0% | 1,040 | 1,279 | +23% | 0 | 0 | — |
case-21 | pass→pass | 10,564 | 9,446 | -11% | 1 | 1 | 0% | 2,104 | 2,191 | +4% | 0 | 0 | — |
case-22 | pass→pass | 6,848 | 7,015 | +2% | 1 | 1 | 0% | 1,537 | 1,662 | +8% | 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 +9 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is 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.