Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →One character across 16 anime and manga sub-styles, each with the prompt, from Ghibli to webtoon to noir manga.
.claude/skills/whatsuppiyush-ai-anime-styles/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 9% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 15% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 8% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 2% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 22% | 0% |
"Anime style" is not one look, it is dozens. This guide holds one character across 16 anime and manga sub-styles, so the difference you see is the style, not the subject. Ghibli's soft watercolour worlds, shonen's high-energy lines, seinen's mature realism, webtoon's clean digital colour, noir manga's ink and screentone. Copy a prompt, swap in your character, and you have the look. Model-agnostic across Midjourney, GPT Image, Flux and Nano Banana.
Works in: Midjourney, GPT Image, Flux, Nano Banana, Stable Diffusion.
When the user asks for an image prompt in this style, compose one using the formulas and vocabulary below. Fill each slot with a concrete choice, then return the finished prompt. Prefer naming a real camera/lens, a light, and a colour or film treatment, which is what makes the output read as a real photograph rather than an AI render.
The anime formula
[character + action], in the [anime sub-style] style, [two signature traits], [studio or era, optional]The signature traits stop the model averaging. For shoujo: 'sparkling eyes, soft pastels'. For seinen: 'realistic proportions, muted tones'. For manga: 'black and white, screentone shading'.
_Naming the studio_
A young woman with windswept hair, anime character, upper body, in the Studio Ghibli style, soft painterly watercolour backgrounds, gentle warm colours, hand-drawn_Modern cel-shaded_
A young woman with windswept hair, anime character, upper body, in a modern cel-shaded anime style, clean flat shading, crisp lineart, vibrant_Noir manga_
A young woman with windswept hair, anime character, upper body, as black-and-white manga, bold ink, screentone shading, dramatic_Webtoon / manhwa_
A young woman with windswept hair, anime character, upper body, in a Korean webtoon manhwa style, clean digital colouring, soft gradientsClassic anime
Manga & ink
Modern digital
From God of Skills: a curated, hand-tested directory of AI skills, prompts, templates and image style guides. Source: https://godofskills.com/guides/ai-anime-styles?ref=claude-skill
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-05 | pass→pass | 15,210 | 15,183 | -0% | 1 | 1 | 0% | 2,633 | 3,398 | +29% | 0 | 0 | — |
case-01 | fail→pass | 10,405 | 5,265 | -49% | 1 | 1 | 0% | 1,641 | 1,786 | +9% | 0 | 0 | — |
case-02 | fail→fail | 10,432 | 4,047 | -61% | 1 | 1 | 0% | 1,681 | 1,611 | -4% | 0 | 0 | — |
case-03 | fail→pass | 8,705 | 4,256 | -51% | 1 | 1 | 0% | 1,452 | 1,667 | +15% | 0 | 0 | — |
case-04 | pass→pass | 13,272 | 10,384 | -22% | 1 | 1 | 0% | 2,611 | 2,755 | +6% | 0 | 0 | — |
case-06 | pass→pass | 11,200 | 11,034 | -1% | 1 | 1 | 0% | 2,395 | 3,140 | +31% | 0 | 0 | — |
case-07 | fail→pass | 8,803 | 4,513 | -49% | 1 | 1 | 0% | 1,540 | 1,668 | +8% | 0 | 0 | — |
case-08 | pass→pass | 9,424 | 4,305 | -54% | 1 | 1 | 0% | 1,589 | 1,577 | -1% | 0 | 0 | — |
case-09 | pass→pass | 10,101 | 3,658 | -64% | 1 | 1 | 0% | 1,379 | 1,622 | +18% | 0 | 0 | — |
case-10 | fail→pass | 8,945 | 3,280 | -63% | 1 | 1 | 0% | 1,447 | 1,479 | +2% | 0 | 0 | — |
case-11 | fail→pass | 9,387 | 5,317 | -43% | 1 | 1 | 0% | 1,471 | 1,794 | +22% | 0 | 0 | — |
case-12 | pass→pass | 7,214 | 3,989 | -45% | 1 | 1 | 0% | 1,214 | 1,553 | +28% | 0 | 0 | — |
case-13 | pass→pass | 7,955 | 2,964 | -63% | 1 | 1 | 0% | 1,258 | 1,440 | +14% | 0 | 0 | — |
case-14 | fail→pass | 8,601 | 3,297 | -62% | 1 | 1 | 0% | 1,491 | 1,436 | -4% | 0 | 0 | — |
case-15 | fail→pass | 8,214 | 3,893 | -53% | 1 | 1 | 0% | 1,394 | 1,606 | +15% | 0 | 0 | — |
case-16 | fail→pass | 9,689 | 2,705 | -72% | 1 | 1 | 0% | 1,553 | 1,361 | -12% | 0 | 0 | — |
case-17 | fail→pass | 9,319 | 3,826 | -59% | 1 | 1 | 0% | 1,450 | 1,555 | +7% | 0 | 0 | — |
case-18 | fail→pass | 7,972 | 4,607 | -42% | 1 | 1 | 0% | 1,313 | 1,770 | +35% | 0 | 0 | — |
case-19 | pass→pass | 7,071 | 3,415 | -52% | 1 | 1 | 0% | 1,173 | 1,499 | +28% | 0 | 0 | — |
case-20 | fail→pass | 8,457 | 4,566 | -46% | 1 | 1 | 0% | 1,471 | 1,694 | +15% | 0 | 0 | — |
case-21 | pass→pass | 8,032 | 3,225 | -60% | 1 | 1 | 0% | 1,268 | 1,459 | +15% | 0 | 0 | — |
case-22 | fail→pass | 8,824 | 4,226 | -52% | 1 | 1 | 0% | 1,307 | 1,577 | +21% | 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 +55 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.
| Model | Method | Date | Lift |
|---|---|---|---|
| gemini-3.6-flash | verified | 8/9/2026 | +27% |
| gemini-3.6-flash | verified | 8/6/2026 | +23% |
Other measured skills in the registry, with their headline benchmark lift.