Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →A two-spread digital e-guide preview — page 1 is a cover (display title, author, "What's inside" stats, table of contents teaser); page 2 is a spread (lesson body with pull-quote and a step list). Lifestyle / creator brand tone. Use when the brief asks for an "e-guide", "digital guide", "lookbook", "lead magnet", "creator guide", "playbook", "PDF guide", or "电子指南".
.claude/skills/nexu-io-digital-eguide/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 9% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 11% | 0% |
| case-19 | ✗→✓ | ▲ Improved | 134% | 0% |
| case-04 | ✓→✗ | ▼ Worse | 35% | 0% |
| case-05 | ✓→✗ | ▼ Worse | 29% | 0% |
Produce a two-page digital guide preview side-by-side. Cover on the left, inside spread on the right. Lifestyle creator tone, lots of negative space, serif display headings, careful column rhythm.
token for the title (italic ligatures encouraged), a body serif for long-form, and a mono token for stats / labels.
"The Creator's Style & Format Guide"), a real subtitle, and a one-line author byline.
("The Creator's Style & Format guide" — & and guide italic).
"1 BLOCK, ZERO TEMPLATES") in mono, separated by ·.
in mono, leader dots).
the rule", "02 Drop the filler"…).
attribution.
in italic).
<!doctype html> through </html>, CSS inline.opposing each other (±0.6deg) for a magazine-on-desk feel.
data-od-id on cover, spread, toc, pull-quote, exercise.Emit between <artifact> tags:
<artifact identifier="eguide-slug" type="text/html" title="E-Guide — Title">
<!doctype html>
<html>...</html>
</artifact>One sentence before the artifact, nothing after.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-14 | fail→fail | 19,228 | 21,566 | +12% | 1 | 1 | 0% | 4,930 | 6,232 | +26% | 0 | 0 | — |
case-01 | fail→pass | 27,874 | 24,608 | -12% | 1 | 1 | 0% | 6,203 | 6,766 | +9% | 0 | 0 | — |
case-02 | fail→fail | 25,853 | 27,060 | +5% | 1 | 1 | 0% | 6,206 | 6,903 | +11% | 0 | 0 | — |
case-03 | fail→fail | 26,536 | 21,506 | -19% | 1 | 1 | 0% | 6,203 | 6,490 | +5% | 0 | 0 | — |
case-04 | pass→fail | 18,719 | 24,180 | +29% | 1 | 1 | 0% | 4,783 | 6,473 | +35% | 0 | 0 | — |
case-05 | pass→fail | 21,075 | 22,852 | +8% | 1 | 1 | 0% | 5,349 | 6,874 | +29% | 0 | 0 | — |
case-06 | pass→fail | 15,502 | 25,195 | +63% | 1 | 1 | 0% | 3,204 | 6,869 | +114% | 0 | 0 | — |
case-07 | fail→fail | 24,952 | 21,690 | -13% | 1 | 1 | 0% | 6,193 | 5,978 | -3% | 0 | 0 | — |
case-08 | fail→fail | 23,172 | 20,023 | -14% | 1 | 1 | 0% | 6,195 | 5,793 | -6% | 0 | 0 | — |
case-09 | fail→pass | 28,098 | 23,285 | -17% | 1 | 1 | 0% | 6,184 | 6,881 | +11% | 0 | 0 | — |
case-10 | fail→fail | 19,147 | 19,900 | +4% | 1 | 1 | 0% | 5,127 | 6,324 | +23% | 0 | 0 | — |
case-11 | fail→fail | 24,032 | 23,331 | -3% | 1 | 1 | 0% | 6,187 | 6,699 | +8% | 0 | 0 | — |
case-12 | fail→fail | 24,726 | 20,908 | -15% | 1 | 1 | 0% | 6,196 | 5,693 | -8% | 0 | 0 | — |
case-13 | fail→fail | 17,489 | 22,578 | +29% | 1 | 1 | 0% | 4,461 | 6,660 | +49% | 0 | 0 | — |
case-15 | fail→fail | 17,316 | 18,662 | +8% | 1 | 1 | 0% | 4,225 | 5,943 | +41% | 0 | 0 | — |
case-16 | fail→fail | 17,067 | 23,981 | +41% | 1 | 1 | 0% | 4,072 | 6,885 | +69% | 0 | 0 | — |
case-17 | fail→fail | 24,899 | 20,579 | -17% | 1 | 1 | 0% | 6,185 | 5,833 | -6% | 0 | 0 | — |
case-18 | fail→fail | 20,966 | 19,048 | -9% | 1 | 1 | 0% | 5,224 | 5,611 | +7% | 0 | 0 | — |
case-19 | fail→pass | 12,417 | 20,770 | +67% | 1 | 1 | 0% | 2,452 | 5,732 | +134% | 0 | 0 | — |
case-20 | fail→fail | 17,014 | 25,213 | +48% | 1 | 1 | 0% | 3,667 | 6,880 | +88% | 0 | 0 | — |
case-21 | fail→fail | 23,532 | 26,702 | +13% | 1 | 1 | 0% | 4,547 | 6,881 | +51% | 0 | 0 | — |
case-22 | fail→fail | 24,715 | 26,861 | +9% | 1 | 1 | 0% | 4,993 | 6,885 | +38% | 0 | 0 | — |
case-23 | fail→fail | 24,668 | 21,574 | -13% | 1 | 1 | 0% | 5,434 | 5,762 | +6% | 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 0 percentage points is the difference between those two pass rates over the 23 comparable cases. 5 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.
| Model | Method | Date | Lift |
|---|---|---|---|
| gemini-3.6-flash | verified | 8/2/2026 | -5% |
Other measured skills in the registry, with their headline benchmark lift.