Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Generate beautifully designed PDF reports with a Nordic/Scandinavian aesthetic. Use when creating polished executive briefings, analysis reports, or presentation-style PDF outputs from markdown and HTML via Nutrient DWS.
.claude/skills/jdrhyne-elegant-reports/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | -60% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -24% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 20% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 6% | 0% |
| case-13 | ✗→✓ | ▲ Improved | -22% | 0% |
Generate minimalist PDF reports inspired by Scandinavian editorial design.
Use this skill when the user wants:
Install the pinned dependencies from package-lock.json, then run:
bashcd /path/to/elegant-reports node ./generate.js --list node ./generate.js examples/sample-executive.md output.pdf --template executive --theme light
For HTML debugging, add --output-html so the generator saves the rendered HTML alongside the PDF.
| Template | Use Case | |----------|----------| | executive | polished briefings and compact executive summaries | | report | denser narrative reports and analysis writeups | | presentation | bold slide-like outputs with one idea per page | | report-demo | legacy report variant for comparison/testing | | presentation-demo | legacy presentation variant for comparison/testing |
Each template supports light and dark themes where available.
Add YAML frontmatter to control the rendered output:
markdown--- title: Q4 Competitive Analysis subtitle: Market Intelligence Report author: Report Author template: report theme: dark --- Your content here...
--output-html and adjust the corresponding template/theme pair.When authoring a new visual variant:
The bundled Nordic design research note is the canonical reference for the visual system. Read it only when you need deeper design rationale.
package-lock.jsonNUTRIENT_DWS_API_KEY environment variable for PDF generationBefore calling the skill done:
node ./generate.js --listnpm test| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-19 | pass→pass | 10,271 | 1,946 | -81% | 1 | 1 | 0% | 1,687 | 1,135 | -33% | 0 | 0 | — |
case-01 | fail→fail | 7,400 | 3,499 | -53% | 1 | 1 | 0% | 400 | 1,320 | +230% | 0 | 0 | — |
case-02 | fail→fail | 4,757 | 6,300 | +32% | 1 | 1 | 0% | 277 | 1,090 | +294% | 0 | 0 | — |
case-03 | fail→fail | 5,532 | 4,615 | -17% | 1 | 1 | 0% | 386 | 996 | +158% | 0 | 0 | — |
case-04 | pass→pass | 9,731 | 3,622 | -63% | 1 | 1 | 0% | 1,577 | 1,386 | -12% | 0 | 0 | — |
case-05 | pass→pass | 2,684 | 3,088 | +15% | 1 | 1 | 0% | 418 | 1,283 | +207% | 0 | 0 | — |
case-06 | pass→fail | 5,274 | 5,084 | -4% | 1 | 1 | 0% | 827 | 1,559 | +89% | 0 | 0 | — |
case-07 | fail→pass | 15,835 | 1,721 | -89% | 1 | 1 | 0% | 2,510 | 994 | -60% | 0 | 0 | — |
case-08 | fail→pass | 9,384 | 2,168 | -77% | 1 | 1 | 0% | 1,417 | 1,083 | -24% | 0 | 0 | — |
case-09 | fail→pass | 6,298 | 3,108 | -51% | 1 | 1 | 0% | 1,063 | 1,275 | +20% | 0 | 0 | — |
case-10 | pass→pass | 11,803 | 6,776 | -43% | 1 | 1 | 0% | 1,970 | 1,843 | -6% | 0 | 0 | — |
case-11 | pass→pass | 11,516 | 2,449 | -79% | 1 | 1 | 0% | 1,787 | 1,167 | -35% | 0 | 0 | — |
case-12 | fail→pass | 13,125 | 7,596 | -42% | 1 | 1 | 0% | 1,955 | 2,078 | +6% | 0 | 0 | — |
case-13 | fail→pass | 16,196 | 7,283 | -55% | 1 | 1 | 0% | 2,372 | 1,859 | -22% | 0 | 0 | — |
case-14 | pass→pass | 6,459 | 2,016 | -69% | 1 | 1 | 0% | 954 | 1,102 | +16% | 0 | 0 | — |
case-15 | fail→pass | 7,369 | 2,685 | -64% | 1 | 1 | 0% | 1,008 | 1,149 | +14% | 0 | 0 | — |
case-16 | pass→pass | 12,298 | 3,097 | -75% | 1 | 1 | 0% | 1,795 | 1,170 | -35% | 0 | 0 | — |
case-17 | pass→pass | 9,627 | 3,017 | -69% | 1 | 1 | 0% | 1,538 | 1,220 | -21% | 0 | 0 | — |
case-18 | pass→pass | 12,047 | 4,703 | -61% | 1 | 1 | 0% | 1,750 | 1,468 | -16% | 0 | 0 | — |
case-20 | pass→pass | 9,959 | 2,476 | -75% | 1 | 1 | 0% | 1,524 | 1,158 | -24% | 0 | 0 | — |
case-21 | pass→pass | 3,075 | 1,230 | -60% | 1 | 1 | 0% | 482 | 935 | +94% | 0 | 0 | — |
case-22 | pass→pass | 12,712 | 2,427 | -81% | 1 | 1 | 0% | 1,970 | 1,123 | -43% | 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, and 19 counted toward the lift figure. The other 3 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +23 percentage points is the difference between those two pass rates over the 19 comparable cases. 1 case got worse with the skill loaded, and it is 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.