Install any skill in seconds. Free to start, no credit card required.
Get Started Free →DEPRECATED — superseded by /paper-poster-html. Kept only as a redirect for muscle memory; do not use for new posters.
.claude/skills/wanshuiyin-paper-poster/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 290% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 23% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -19% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -91% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 1% | 0% |
This skill is retired. The LaTeX/tcbposter pipeline it described produced posters with unbounded color palettes, no real paper figures, and no print-canvas verification, and has been replaced by the measurement-gated HTML/CSS pipeline.
Immediately proceed with /paper-poster-html, passing through all of the user's arguments unchanged. Do not attempt the legacy LaTeX flow.
The full legacy implementation remains available in git history (git log -- skills/skills-codex/paper-poster/SKILL.md) if a venue ever mandates LaTeX poster source — none is known to.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 10,303 | 22,853 | +122% | 1 | 1 | 0% | 1,592 | 5,845 | +267% | 0 | 0 | — |
case-02 | fail→pass | 11,360 | 29,720 | +162% | 1 | 1 | 0% | 1,619 | 6,314 | +290% | 0 | 0 | — |
case-03 | fail→pass | 16,731 | 18,469 | +10% | 1 | 1 | 0% | 3,147 | 3,857 | +23% | 0 | 0 | — |
case-04 | fail→pass | 33,468 | 23,539 | -30% | 1 | 1 | 0% | 6,170 | 4,989 | -19% | 0 | 0 | — |
case-05 | fail→pass | 27,434 | 2,654 | -90% | 1 | 1 | 0% | 6,164 | 559 | -91% | 0 | 0 | — |
case-06 | fail→fail | 21,520 | 27,006 | +25% | 1 | 1 | 0% | 3,633 | 6,308 | +74% | 0 | 0 | — |
case-07 | fail→fail | 20,687 | 22,955 | +11% | 1 | 1 | 0% | 3,896 | 5,042 | +29% | 0 | 0 | — |
case-08 | fail→pass | 30,819 | 28,226 | -8% | 1 | 1 | 0% | 5,860 | 5,894 | +1% | 0 | 0 | — |
case-09 | fail→fail | 31,336 | 25,145 | -20% | 1 | 1 | 0% | 5,895 | 5,922 | +0% | 0 | 0 | — |
case-10 | fail→fail | 19,044 | 55,960 | +194% | 1 | 1 | 0% | 2,968 | 6,305 | +112% | 0 | 0 | — |
case-11 | fail→fail | 23,115 | 26,829 | +16% | 1 | 1 | 0% | 3,749 | 5,411 | +44% | 0 | 0 | — |
case-12 | fail→pass | 3,260 | 3,928 | +20% | 1 | 1 | 0% | 419 | 704 | +68% | 0 | 0 | — |
case-13 | fail→pass | 16,372 | 1,381 | -92% | 1 | 1 | 0% | 2,565 | 338 | -87% | 0 | 0 | — |
case-14 | fail→fail | 26,912 | 19,570 | -27% | 1 | 1 | 0% | 4,719 | 3,797 | -20% | 0 | 0 | — |
case-15 | fail→pass | 15,187 | 24,348 | +60% | 1 | 1 | 0% | 2,480 | 5,249 | +112% | 0 | 0 | — |
case-16 | fail→pass | 17,382 | 19,982 | +15% | 1 | 1 | 0% | 3,015 | 4,341 | +44% | 0 | 0 | — |
case-17 | fail→pass | 29,132 | 29,187 | +0% | 1 | 1 | 0% | 6,156 | 6,303 | +2% | 0 | 0 | — |
case-18 | fail→pass | 21,869 | 22,330 | +2% | 1 | 1 | 0% | 4,271 | 5,165 | +21% | 0 | 0 | — |
case-19 | fail→fail | 32,170 | 34,766 | +8% | 1 | 1 | 0% | 6,160 | 6,307 | +2% | 0 | 0 | — |
case-20 | pass→pass | 9,067 | 8,081 | -11% | 1 | 1 | 0% | 1,420 | 1,310 | -8% | 0 | 0 | — |
case-21 | pass→pass | 13,773 | 10,753 | -22% | 1 | 1 | 0% | 2,096 | 1,794 | -14% | 0 | 0 | — |
case-22 | pass→pass | 16,776 | 14,418 | -14% | 1 | 1 | 0% | 2,385 | 2,409 | +1% | 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 +50 percentage points is the difference between those two pass rates over the 22 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.