Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Generate AntV Infographic syntax outputs. Use when asked to turn user content into the Infographic DSL (template selection, data structuring, theme), or to output `infographic <template>` plain syntax.
.claude/skills/thinkinaixyz-infographic-syntax-creator/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | -9% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -53% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -82% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -66% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -41% | 0% |
Generate AntV Infographic syntax output from user content, following the rules in references/prompt.md.
references/prompt.md for syntax rules, templates, and output constraints.references/prompt.md as the formatting baseline.infographic markdown code block; no extra text.infographic <template-name>.key value; arrays use -.compare-*) must have exactly two root nodes with children.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 16,322 | 4,785 | -71% | 1 | 1 | 0% | 3,456 | 1,163 | -66% | 0 | 0 | — |
case-02 | fail→pass | 5,666 | 4,275 | -25% | 1 | 1 | 0% | 1,198 | 1,085 | -9% | 0 | 0 | — |
case-03 | fail→pass | 12,044 | 5,724 | -52% | 1 | 1 | 0% | 2,654 | 1,258 | -53% | 0 | 0 | — |
case-04 | pass→fail | 26,728 | 4,520 | -83% | 1 | 1 | 0% | 6,178 | 1,077 | -83% | 0 | 0 | — |
case-05 | pass→fail | 6,298 | 6,559 | +4% | 1 | 1 | 0% | 1,231 | 1,447 | +18% | 0 | 0 | — |
case-06 | fail→fail | 27,207 | 8,018 | -71% | 1 | 1 | 0% | 6,170 | 1,676 | -73% | 0 | 0 | — |
case-07 | fail→fail | 11,093 | 4,484 | -60% | 1 | 1 | 0% | 2,338 | 1,078 | -54% | 0 | 0 | — |
case-08 | fail→fail | 11,218 | 4,618 | -59% | 1 | 1 | 0% | 2,468 | 1,125 | -54% | 0 | 0 | — |
case-09 | fail→pass | 27,385 | 4,054 | -85% | 1 | 1 | 0% | 6,193 | 1,136 | -82% | 0 | 0 | — |
case-10 | fail→pass | 15,069 | 4,438 | -71% | 1 | 1 | 0% | 3,184 | 1,073 | -66% | 0 | 0 | — |
case-11 | fail→pass | 10,501 | 5,476 | -48% | 1 | 1 | 0% | 2,273 | 1,342 | -41% | 0 | 0 | — |
case-12 | pass→pass | 4,905 | 5,393 | +10% | 1 | 1 | 0% | 855 | 1,173 | +37% | 0 | 0 | — |
case-13 | fail→pass | 8,799 | 5,931 | -33% | 1 | 1 | 0% | 1,544 | 1,224 | -21% | 0 | 0 | — |
case-14 | fail→fail | 10,979 | 4,495 | -59% | 1 | 1 | 0% | 2,378 | 1,104 | -54% | 0 | 0 | — |
case-15 | fail→fail | 6,174 | 3,230 | -48% | 1 | 1 | 0% | 1,127 | 797 | -29% | 0 | 0 | — |
case-16 | fail→pass | 26,269 | 4,130 | -84% | 1 | 1 | 0% | 6,180 | 1,173 | -81% | 0 | 0 | — |
case-17 | fail→fail | 12,265 | 5,880 | -52% | 1 | 1 | 0% | 1,887 | 1,284 | -32% | 0 | 0 | — |
case-18 | fail→pass | 9,257 | 4,760 | -49% | 1 | 1 | 0% | 1,610 | 1,080 | -33% | 0 | 0 | — |
case-19 | fail→pass | 6,116 | 5,139 | -16% | 1 | 1 | 0% | 1,197 | 1,217 | +2% | 0 | 0 | — |
case-20 | fail→pass | 12,360 | 5,336 | -57% | 1 | 1 | 0% | 2,936 | 1,287 | -56% | 0 | 0 | — |
case-21 | fail→pass | 20,178 | 3,797 | -81% | 1 | 1 | 0% | 4,952 | 1,015 | -80% | 0 | 0 | — |
case-22 | fail→fail | 9,939 | 3,750 | -62% | 1 | 1 | 0% | 1,949 | 967 | -50% | 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 +41 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.