Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Analyze test coverage gaps. Use when user says "test coverage", "what's not tested", "coverage gaps", "missing tests", "coverage report", or "what needs testing".
.claude/skills/alirezarezvani-coverage/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | -9% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -54% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -19% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -2% | 0% |
| case-14 | ✗→✓ | ▲ Improved | -32% | 0% |
Map all testable surfaces in the application and identify what's tested vs. what's missing.
Use the Explore subagent to catalog:
Routes/Pages:
app/, React Router config, Vue Router, etc.)Components:
API Endpoints:
User Flows:
Scan all *.spec.ts / *.spec.js files:
page.goto() calls)## Coverage Matrix
| Area | Route | Tests | Status |
|---|---|---|---|
| Auth | /login | 5 | ✅ Covered |
| Auth | /register | 0 | ❌ Missing |
| Auth | /forgot-password | 0 | ❌ Missing |
| Dashboard | /dashboard | 3 | ⚠️ Partial (no error states) |
| Settings | /settings | 0 | ❌ Missing |
| Checkout | /checkout | 8 | ✅ Covered |Rank uncovered areas by business impact:
For each gap, recommend:
templates/ to use## Recommended Test Plan
### Priority 1: Critical
1. /register (4 tests) — use auth/registration template — quick
2. /forgot-password (3 tests) — use auth/password-reset template — quick
### Priority 2: High
3. /settings (4 tests) — use settings/ templates — medium
4. Dashboard error states (2 tests) — use dashboard/data-loading template — quickAsk user: "Generate tests for the top N gaps? Yes/No/Pick specific]"
If yes, invoke /pw:generate for each gap with the recommended template.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 11,066 | 2,325 | -79% | 1 | 1 | 0% | 1,753 | 1,098 | -37% | 0 | 0 | — |
case-02 | fail→fail | 15,231 | 4,773 | -69% | 1 | 1 | 0% | 2,428 | 962 | -60% | 0 | 0 | — |
case-03 | fail→fail | 8,866 | 2,109 | -76% | 1 | 1 | 0% | 1,609 | 1,001 | -38% | 0 | 0 | — |
case-04 | pass→pass | 10,974 | 3,637 | -67% | 1 | 1 | 0% | 1,699 | 1,234 | -27% | 0 | 0 | — |
case-05 | pass→pass | 11,747 | 13,801 | +17% | 1 | 1 | 0% | 2,377 | 3,264 | +37% | 0 | 0 | — |
case-06 | pass→pass | 14,795 | 12,130 | -18% | 1 | 1 | 0% | 2,535 | 2,700 | +7% | 0 | 0 | — |
case-07 | fail→pass | 8,609 | 3,673 | -57% | 1 | 1 | 0% | 1,477 | 1,337 | -9% | 0 | 0 | — |
case-08 | fail→fail | 10,694 | 5,922 | -45% | 1 | 1 | 0% | 1,819 | 1,712 | -6% | 0 | 0 | — |
case-09 | fail→pass | 17,842 | 2,409 | -86% | 1 | 1 | 0% | 2,254 | 1,038 | -54% | 0 | 0 | — |
case-10 | fail→pass | 15,149 | 7,742 | -49% | 1 | 1 | 0% | 2,272 | 1,838 | -19% | 0 | 0 | — |
case-11 | fail→pass | 8,354 | 5,268 | -37% | 1 | 1 | 0% | 1,654 | 1,621 | -2% | 0 | 0 | — |
case-12 | pass→pass | 12,770 | 8,929 | -30% | 1 | 1 | 0% | 1,915 | 1,849 | -3% | 0 | 0 | — |
case-13 | pass→pass | 15,245 | 8,656 | -43% | 1 | 1 | 0% | 2,809 | 2,060 | -27% | 0 | 0 | — |
case-14 | fail→pass | 16,178 | 5,401 | -67% | 1 | 1 | 0% | 2,425 | 1,650 | -32% | 0 | 0 | — |
case-15 | fail→fail | 11,652 | 8,011 | -31% | 1 | 1 | 0% | 1,864 | 2,023 | +9% | 0 | 0 | — |
case-16 | fail→pass | 10,756 | 1,452 | -87% | 1 | 1 | 0% | 1,814 | 868 | -52% | 0 | 0 | — |
case-17 | fail→pass | 11,786 | 5,310 | -55% | 1 | 1 | 0% | 1,692 | 890 | -47% | 0 | 0 | — |
case-18 | fail→pass | 14,811 | 12,028 | -19% | 1 | 1 | 0% | 2,541 | 2,905 | +14% | 0 | 0 | — |
case-19 | fail→pass | 12,643 | 3,823 | -70% | 1 | 1 | 0% | 1,904 | 1,269 | -33% | 0 | 0 | — |
case-20 | pass→pass | 10,757 | 3,197 | -70% | 1 | 1 | 0% | 1,834 | 1,182 | -36% | 0 | 0 | — |
case-21 | pass→pass | 11,289 | 3,494 | -69% | 1 | 1 | 0% | 1,874 | 1,262 | -33% | 0 | 0 | — |
case-22 | fail→pass | 8,759 | 2,979 | -66% | 1 | 1 | 0% | 1,636 | 1,266 | -23% | 0 | 0 | — |
case-23 | fail→fail | 14,042 | 4,547 | -68% | 1 | 1 | 0% | 2,370 | 1,507 | -36% | 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. The headline lift of +43 percentage points is the difference between those two pass rates over the 23 comparable cases.
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.