muapi-color-analysis-board
The muapi-color-analysis-board skill transforms a portrait photograph into a luxury editorial color analysis board styled like high-end fashion magazines. It analyzes the subject's skin undertone, hair color, and eye color, then generates a comprehensive visual guide featuring recommended color palettes, makeup suggestions, flattering prints, hairstyle options, jewelry recommendations, and coordinated capsule wardrobe outfits arranged on an elegant beige and ivory grid layout. Use this when creating personalized style guides for clients or generating fashion consultation materials.
git clone --depth 1 https://github.com/SamurAIGPT/Generative-Media-Skills /tmp/muapi-color-analysis-board && cp -r /tmp/muapi-color-analysis-board/library/visual/color-analysis-board ~/.claude/skills/muapi-color-analysis-boardSKILL.md
# Color Analysis Board
**Turn a portrait photo into a high-end editorial "Color Analysis Board" in a luxury fashion-magazine style (Dior / Ralph Lauren aesthetic) — best colors, undertone, makeup guide, capsule wardrobe, hair & jewelry recommendations, all laid out on a clean beige/ivory grid.**
## Inputs
| Name | Type | Required | Default | Description |
|:---|:---|:---|:---|:---|
| `person_image` | image_url | yes | — | A clear, well-lit portrait of the person. Front-facing, neutral background, and natural lighting give the strongest color reads (undertone, hair, eyes). Avoid heavy filters or makeup that masks the natural complexion. |
## Steps
### Phase A — Color Analysis Board Generation
If `{{person_image}}` is not provided, ask the user to upload a clear front-facing portrait. Make sure the face is well-lit with natural color (no heavy filters, color-cast lighting, or sunglasses) — the model needs accurate skin, hair, and eye color to pick the right palette.
Once the photo is available, submit ONE step to generate the color analysis board:
1. **Color Analysis Board Generation** — `muapi image edit` (model=`gpt-image-2-image-to-image`):
- Reference Image: `{{person_image}}`
- Image size: `3840x2160` (16:9 landscape) — magazine-spread aspect ratio
- Background: `auto`
- Output format: `png`
- Quality: `auto`
- Moderation: `low`
- Prompt:
```
Create a high-end editorial "Color Analysis Board" from this portrait in a luxury fashion magazine style (Dior / Ralph Lauren aesthetic). Clean beige/ivory background, warm tones, soft diffused lighting, ultra-detailed photorealistic quality, consistent lighting, minimal elegant typography, grid-based layout.
Main portrait: enhanced natural beauty (same identity, smooth skin, soft glow, realistic texture)
Top section: "Your Best Colors" with fabric swatches with the best algorithm choices
Undertone panel: warm / neutral / cool with marked result.
Colors to avoid
Neutrals that work
Prints that flatter
Makeup guide: eyeshadows, blush, lips, highlighter
"You in your colors": multiple outfit best variations
Hair colors: best.
Jewelry
Style notes
Capsule wardrobe: coordinated outfits, shoes, bags, accessories
Style: best style for me
```
Present the generated board to the user. Suggest variations they can try: a different source portrait (different lighting / hairstyle for comparison), or asking to bias the palette toward a season (e.g. "spring warm" vs "winter cool") or a specific brand aesthetic (e.g. minimalist Scandinavian, Old Money, streetwear).
## Trigger Keywords
`color analysis`, `color analysis board`, `personal color palette`, `seasonal color analysis`, `undertone analysis`, `style guide board`, `fashion color board`, `capsule wardrobe board`
---
## Notes for the Executing Agent
- This recipe is LLM-orchestrated: read each phase, gather any missing inputs from the user, then call `muapi` CLI commands. Use `muapi auth configure` first if `MUAPI_API_KEY` is unset.
- For model IDs without a CLI alias yet, fall back to the raw endpoint via `curl -X POST https://api.muapi.ai/api/v1/<endpoint> -H "x-api-key: $MUAPI_API_KEY" -H 'content-type: application/json' -d '{...}'` and poll with `muapi predict wait <request_id>`.
- Substitute `{{input_name}}` placeholders with the user's actual inputs before issuing each call.
- Source schema reference: `gpt-image-v2-edit` (from the source workflow JSON) maps to `gpt-image-2-image-to-image` in the muapi catalog.
- The output is intentionally 16:9 (3840×2160) so it reads as a magazine spread / desktop wallpaper / Pinterest landscape board. For IG-feed square or 9:16 vertical, request a re-crop or re-run with a different `image_size`.Edit and enhance images and videos with AI via muapi.ai — prompt-based editing, upscaling, background removal, face swap, lipsync, video effects, and more
Generate AI images, videos, music, and audio from the terminal via muapi.ai — supports 100+ models including Flux, Midjourney v7, Kling 3.0, Veo3, and Suno V5
Setup and utility scripts for muapi.ai — configure API keys, test connectivity, and poll for async generation results
Turn a long video into N viral-ready short clips with a single managed API call. Wraps muapi.ai's `/ai-clipping` endpoint, which handles transcription, highlight ranking through a virality framework (hook / emotional peak / opinion bomb / revelation / conflict / quotable / story peak / practical value), overlap dedupe, and vertical face-tracking auto-crop server-side. No local Whisper, no local LLM, no GPU.
Transform a 2D logo into a premium 3D version and animate it with professional cinematic effects.
Generate a high-cut-density action / fight scene by first composing a 16-cell storyboard image, then driving Seedance 2.0 image-to-video off that storyboard. Stacks GPT-Image-2 (character sheet + storyboard), Nano-Banana-2 (environment concept), and Seedance 2.0 i2v.
Create a hilarious and ultra-realistic video of an anthropomorphic animal acting like a human vlogger in a real-world setting.
Generate a 15-second cinematic awards-ceremony video — a host announces a winner from the stage, a spotlight finds them in the crowd, they walk up to the podium, receive the award, and the LED display reveals their name and "THE BEST ACTOR".