Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Swiss industrial-print web prototype. Newsprint canvas, monolithic black grotesque, viewport-bleeding numerals, hairline grid dividers, hazard-red accent, ASCII syntax decoration. Distilled from Leonxlnx/taste-skill `brutalist-skill` (Swiss Industrial Print mode).
.claude/skills/nexu-io-web-prototype-taste-brutalist/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 12% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 12% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 12% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 183% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 63% | 0% |
For briefs that ask for "editorial", "newspaper", "agency portfolio", "Swiss design", "manifesto site", or anywhere the goal is to project rigor and physicality rather than friendliness. This skill commits to ONE substrate (light Swiss print) — never mix with the dark CRT mode in the same artifact.
Distilled from Leonxlnx/taste-skill — skills/brutalist-skill/SKILL.md §2.1 (Swiss Industrial Print). For decks that lean into the dark CRT mode, see design-templates/html-ppt-taste-brutalist/.
#F4F4F0 or #EAE8E3. Foreground #050505 carbon ink.#E61919. Used on dividing rules, strikes, alerts. Never as a fill on large surfaces.clamp(4rem, 10vw, 15rem). Tracking -0.04em. Leading 0.88. Uppercase only.10–13px. Tracking 0.1em. Uppercase. Used for navigation, metadata, captions, coordinates.border-radius: 0 everywhere. 90° corners only.gap: 1px over an ink-colored background to render mathematically perfect 1px dividers.[ LABEL ], >>>, ///, registration ® / trademark ™ as structural ornament.border-radius above 0.01. / 02.) with hairline <hr> between each, hard-left aligned.display: grid; gap: 1px on an ink background.This aesthetic is mechanical, not animated. Use motion only as a precision mechanism:
IntersectionObserver reveal: instant opacity 0 → 1, no translate/blur.:active on links: invert ink/paper instantly. No transitions over 120ms.border-radius is 08vw)10–13px, letter-spacing: 0.1emdisplay: grid; gap: 1px ink-background module[ ... ], >>>, ///)| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 51,534 | 38,758 | -25% | 1 | 1 | 0% | 8,270 | 9,260 | +12% | 0 | 0 | — |
case-02 | fail→pass | 43,413 | 117,077 | +170% | 1 | 1 | 0% | 8,251 | 9,241 | +12% | 0 | 0 | — |
case-03 | fail→fail | 55,234 | 74,522 | +35% | 1 | 1 | 0% | 8,256 | 9,246 | +12% | 0 | 0 | — |
case-04 | fail→pass | 45,518 | 51,920 | +14% | 1 | 1 | 0% | 8,241 | 9,231 | +12% | 0 | 0 | — |
case-05 | fail→pass | 54,691 | 51,737 | -5% | 1 | 1 | 0% | 8,239 | 9,229 | +12% | 0 | 0 | — |
case-06 | fail→fail | 52,383 | 39,716 | -24% | 1 | 1 | 0% | 7,778 | 9,215 | +18% | 0 | 0 | — |
case-07 | fail→fail | 41,298 | 37,565 | -9% | 1 | 1 | 0% | 5,234 | 8,599 | +64% | 0 | 0 | — |
case-08 | fail→fail | 27,270 | 36,178 | +33% | 1 | 1 | 0% | 5,326 | 6,802 | +28% | 0 | 0 | — |
case-09 | fail→fail | 17,162 | 36,105 | +110% | 1 | 1 | 0% | 3,684 | 9,119 | +148% | 0 | 0 | — |
case-10 | fail→pass | 17,114 | 42,243 | +147% | 1 | 1 | 0% | 2,526 | 7,138 | +183% | 0 | 0 | — |
case-11 | fail→pass | 19,333 | 21,730 | +12% | 1 | 1 | 0% | 2,670 | 4,360 | +63% | 0 | 0 | — |
case-12 | fail→fail | 22,061 | 39,150 | +77% | 1 | 1 | 0% | 4,355 | 9,213 | +112% | 0 | 0 | — |
case-13 | fail→pass | 18,499 | 36,057 | +95% | 1 | 1 | 0% | 3,431 | 8,577 | +150% | 0 | 0 | — |
case-14 | fail→pass | 33,070 | 40,510 | +22% | 1 | 1 | 0% | 5,536 | 9,208 | +66% | 0 | 0 | — |
case-15 | fail→fail | 30,820 | 39,757 | +29% | 1 | 1 | 0% | 6,217 | 9,205 | +48% | 0 | 0 | — |
case-16 | fail→pass | 17,586 | 19,246 | +9% | 1 | 1 | 0% | 3,315 | 4,711 | +42% | 0 | 0 | — |
case-17 | fail→pass | 9,773 | 40,913 | +319% | 1 | 1 | 0% | 1,568 | 9,053 | +477% | 0 | 0 | — |
case-18 | fail→pass | 24,307 | 28,202 | +16% | 1 | 1 | 0% | 4,667 | 5,458 | +17% | 0 | 0 | — |
case-19 | fail→fail | 42,110 | 50,178 | +19% | 1 | 1 | 0% | 6,585 | 8,934 | +36% | 0 | 0 | — |
case-20 | pass→pass | 39,270 | 47,803 | +22% | 1 | 1 | 0% | 8,228 | 9,218 | +12% | 0 | 0 | — |
case-21 | pass→fail | 36,226 | 52,757 | +46% | 1 | 1 | 0% | 8,226 | 9,216 | +12% | 0 | 0 | — |
case-22 | pass→fail | 46,959 | 52,282 | +11% | 1 | 1 | 0% | 8,220 | 9,210 | +12% | 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 +36 percentage points is the difference between those two pass rates over the 22 comparable cases. 4 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.