Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Validates and analyzes Docusaurus MDX chapters for structure, pedagogical quality, and component usage.
.claude/skills/aiskillstore-chapter-analyzer/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 57% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -21% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -41% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -37% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -5% | 0% |
textbook/docs/.mdx or .md)Every chapter must have valid YAML frontmatter:
yaml--- id: my-chapter-id title: My Chapter Title sidebar_label: Sidebar Label description: Brief summary of the chapter. ---
##).#) within the body.We use custom components in MDX:
<Quiz questions={[...]} />: For knowledge checks.<Simulation type="ros2-node" ... />: For embedded simulations.<Tabs> / <TabItem>: For multi-language code blocks (Python/C++).| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 27,192 | 14,527 | -47% | 1 | 1 | 0% | 4,913 | 2,862 | -42% | 0 | 0 | — |
case-02 | fail→pass | 4,858 | 4,883 | +1% | 1 | 1 | 0% | 746 | 1,174 | +57% | 0 | 0 | — |
case-03 | fail→pass | 9,008 | 4,785 | -47% | 1 | 1 | 0% | 1,484 | 1,170 | -21% | 0 | 0 | — |
case-04 | fail→pass | 10,509 | 4,094 | -61% | 1 | 1 | 0% | 1,691 | 1,001 | -41% | 0 | 0 | — |
case-05 | fail→fail | 10,607 | 5,403 | -49% | 1 | 1 | 0% | 1,729 | 1,286 | -26% | 0 | 0 | — |
case-06 | fail→pass | 10,797 | 4,758 | -56% | 1 | 1 | 0% | 1,722 | 1,089 | -37% | 0 | 0 | — |
case-07 | fail→pass | 8,529 | 5,969 | -30% | 1 | 1 | 0% | 1,376 | 1,309 | -5% | 0 | 0 | — |
case-08 | fail→pass | 6,560 | 3,287 | -50% | 1 | 1 | 0% | 1,084 | 887 | -18% | 0 | 0 | — |
case-09 | fail→pass | 7,300 | 3,872 | -47% | 1 | 1 | 0% | 1,217 | 974 | -20% | 0 | 0 | — |
case-10 | pass→pass | 8,914 | 5,116 | -43% | 1 | 1 | 0% | 1,707 | 1,359 | -20% | 0 | 0 | — |
case-15 | pass→pass | 7,897 | 7,095 | -10% | 1 | 1 | 0% | 1,451 | 1,600 | +10% | 0 | 0 | — |
case-11 | pass→pass | 10,485 | 4,640 | -56% | 1 | 1 | 0% | 1,515 | 1,039 | -31% | 0 | 0 | — |
case-12 | fail→pass | 12,762 | 7,194 | -44% | 1 | 1 | 0% | 2,096 | 1,608 | -23% | 0 | 0 | — |
case-13 | pass→pass | 9,588 | 8,296 | -13% | 1 | 1 | 0% | 1,439 | 1,615 | +12% | 0 | 0 | — |
case-14 | pass→pass | 8,741 | 5,619 | -36% | 1 | 1 | 0% | 1,441 | 1,199 | -17% | 0 | 0 | — |
case-16 | pass→pass | 6,479 | 5,677 | -12% | 1 | 1 | 0% | 1,369 | 1,372 | +0% | 0 | 0 | — |
case-17 | pass→pass | 13,275 | 9,956 | -25% | 1 | 1 | 0% | 2,428 | 2,071 | -15% | 0 | 0 | — |
case-18 | pass→pass | 11,026 | 3,018 | -73% | 1 | 1 | 0% | 1,701 | 859 | -50% | 0 | 0 | — |
case-19 | fail→pass | 8,953 | 3,261 | -64% | 1 | 1 | 0% | 1,436 | 878 | -39% | 0 | 0 | — |
case-20 | fail→pass | 11,284 | 3,412 | -70% | 1 | 1 | 0% | 1,744 | 784 | -55% | 0 | 0 | — |
case-21 | pass→pass | 10,763 | 7,447 | -31% | 1 | 1 | 0% | 1,857 | 1,523 | -18% | 0 | 0 | — |
case-22 | fail→pass | 8,744 | 3,205 | -63% | 1 | 1 | 0% | 1,327 | 732 | -45% | 0 | 0 | — |
case-23 | fail→pass | 9,356 | 3,253 | -65% | 1 | 1 | 0% | 1,619 | 941 | -42% | 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 +52 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.