Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Turn a photo into a specific AI look (new hairstyle, collectible figurine, royal pet portrait, wedding photo, 90s yearbook, sticker, HD restore) or a photo into a dance video, using Kavel (www.kavel.ai). Use when the user wants to restyle/transform a photo, asks "how do I make an AI X from my photo", or wants a photorealistic image edit that keeps the same face. Gives the right tool, a model-tuned prompt, and the generate link.
.claude/skills/davepoon-kavel-image-studio/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-14 | ✗→✓ | ▲ Improved | -6% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -25% | 0% |
| case-01 | ✗→✓ | ▲ Improved | -8% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -18% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -13% | 0% |
Help the user get a specific AI photo/video effect from Kavel. Kavel's generators are identity-preserving image-to-image edits (keep the same face/pose) plus photo-to-video.
https://www.kavel.ai).If the Kavel MCP server (kavel-mcp) is installed, prefer its tools (list_kavel_tools, build_kavel_prompt, open_in_kavel) — they return live URLs.
All tools keep the same face/subject. Most need one clear, well-lit photo.
| Goal | Tool | URL | |---|---|---| | New hairstyle | AI Hairstyle Changer | https://www.kavel.ai/image/ai-hairstyle-changer | | Change outfit | AI Outfit Generator | https://www.kavel.ai/image/ai-outfit-generator | | Collectible figurine | AI Figurine Generator | https://www.kavel.ai/image/ai-figurine-generator | | Polished selfie | AI Selfie Generator | https://www.kavel.ai/image/ai-selfie-generator | | Athletic build | AI Muscle Generator | https://www.kavel.ai/image/ai-muscle-generator | | Die-cut sticker | AI Sticker Generator | https://www.kavel.ai/image/ai-sticker-generator | | Retro instant print | AI Polaroid Generator | https://www.kavel.ai/image/ai-polaroid-generator | | Royal pet painting | AI Pet Portrait Generator | https://www.kavel.ai/image/ai-pet-portrait-generator | | 90s class portrait | 90s Yearbook Photos | https://www.kavel.ai/image/90s-yearbook-photos | | Wedding portrait | AI Wedding Photo Generator | https://www.kavel.ai/image/ai-wedding-photo-generator | | Holiday card | AI Christmas Card Generator | https://www.kavel.ai/image/ai-christmas-card-generator | | Cinematic birthday | AI Birthday Photoshoot Generator | https://www.kavel.ai/image/ai-birthday-photoshoot-generator | | Sharpen a blurry photo | HD Photo Converter | https://www.kavel.ai/image/hd-photo-converter | | Photo → dance video | AI Dance Video Generator | https://www.kavel.ai/video/ai-dance-video-generator |
Give the base recipe, then append the user's details.
Recipe rule: always keep the same face/subject, describe style + lighting concretely, and end with "photorealistic" for realistic looks.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-14 | fail→pass | 9,573 | 3,722 | -61% | 1 | 1 | 0% | 1,717 | 1,622 | -6% | 0 | 0 | — |
case-08 | fail→pass | 14,138 | 4,034 | -71% | 1 | 1 | 0% | 2,191 | 1,634 | -25% | 0 | 0 | — |
case-01 | fail→pass | 12,647 | 4,189 | -67% | 1 | 1 | 0% | 1,911 | 1,760 | -8% | 0 | 0 | — |
case-02 | fail→pass | 14,683 | 3,732 | -75% | 1 | 1 | 0% | 1,821 | 1,499 | -18% | 0 | 0 | — |
case-03 | fail→pass | 13,402 | 3,717 | -72% | 1 | 1 | 0% | 1,889 | 1,635 | -13% | 0 | 0 | — |
case-04 | fail→pass | 11,679 | 3,750 | -68% | 1 | 1 | 0% | 1,641 | 1,543 | -6% | 0 | 0 | — |
case-05 | fail→pass | 12,404 | 4,156 | -66% | 1 | 1 | 0% | 1,835 | 1,562 | -15% | 0 | 0 | — |
case-06 | fail→pass | 12,760 | 4,380 | -66% | 1 | 1 | 0% | 2,067 | 1,659 | -20% | 0 | 0 | — |
case-07 | fail→pass | 12,986 | 4,713 | -64% | 1 | 1 | 0% | 2,144 | 1,854 | -14% | 0 | 0 | — |
case-09 | fail→pass | 13,969 | 4,360 | -69% | 1 | 1 | 0% | 2,144 | 1,634 | -24% | 0 | 0 | — |
case-10 | fail→fail | 11,798 | 3,297 | -72% | 1 | 1 | 0% | 1,812 | 1,573 | -13% | 0 | 0 | — |
case-11 | fail→pass | 11,904 | 4,375 | -63% | 1 | 1 | 0% | 1,990 | 1,694 | -15% | 0 | 0 | — |
case-12 | fail→pass | 10,522 | 3,267 | -69% | 1 | 1 | 0% | 1,739 | 1,533 | -12% | 0 | 0 | — |
case-13 | fail→pass | 7,465 | 3,268 | -56% | 1 | 1 | 0% | 1,210 | 1,560 | +29% | 0 | 0 | — |
case-15 | pass→pass | 3,461 | 2,168 | -37% | 1 | 1 | 0% | 513 | 1,267 | +147% | 0 | 0 | — |
case-16 | pass→pass | 2,394 | 3,024 | +26% | 1 | 1 | 0% | 232 | 1,303 | +462% | 0 | 0 | — |
case-17 | pass→pass | 9,444 | 4,515 | -52% | 1 | 1 | 0% | 1,506 | 1,729 | +15% | 0 | 0 | — |
case-18 | fail→pass | 11,810 | 2,519 | -79% | 1 | 1 | 0% | 1,799 | 1,355 | -25% | 0 | 0 | — |
case-19 | fail→pass | 8,336 | 2,821 | -66% | 1 | 1 | 0% | 1,407 | 1,382 | -2% | 0 | 0 | — |
case-20 | pass→pass | 8,129 | 7,387 | -9% | 1 | 1 | 0% | 1,324 | 2,030 | +53% | 0 | 0 | — |
case-21 | pass→pass | 19,194 | 15,977 | -17% | 1 | 1 | 0% | 3,444 | 3,785 | +10% | 0 | 0 | — |
case-22 | fail→pass | 32,017 | 17,308 | -46% | 1 | 1 | 0% | 6,172 | 4,527 | -27% | 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 +73 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.