Skip to main content
ClaudeWave
Skill3.5k estrellas del repoactualizado today

muapi-rednote-cover

This Claude Code skill generates Xiaohongshu (RedNote) style cover images tailored for the Chinese lifestyle social platform, featuring vibrant aesthetic photography with optional typography overlays. Use it when creating engaging feed or grid posts optimized for RedNote's visual preferences, including portrait and square orientations, customizable style moods, and optional reference image editing for lifestyle content like fashion, beauty, and café aesthetics.

Instalar en Claude Code
Copiar
git clone --depth 1 https://github.com/SamurAIGPT/Generative-Media-Skills /tmp/muapi-rednote-cover && cp -r /tmp/muapi-rednote-cover/library/social/rednote-cover ~/.claude/skills/muapi-rednote-cover
Después abre una sesión nueva de Claude Code; el skill carga automáticamente.

SKILL.md

# RedNote Cover

**Create a Xiaohongshu (RedNote/小红书) style cover image — vibrant, lifestyle-focused, with aesthetic typography overlay suitable for the Chinese social platform.**

## Inputs

| Name | Type | Required | Default | Description |
|:---|:---|:---|:---|:---|
| `topic` | text | yes | — | The post topic (e.g. "morning skincare routine", "cozy café study vlog", "ootd autumn fashion"). |
| `style` | text | no | aesthetic, warm tones, lifestyle photography | Visual style (e.g. "minimalist Korean aesthetic", "cottagecore", "dark moody luxe", "bright Taiwanese street style"). |
| `text_overlay` | text | no | — | Optional Chinese or English text to appear in the cover design (e.g. "今日穿搭✨" or "Morning Glow"). |
| `orientation` | text | no | portrait | Image orientation — "portrait" (3:4) for feed, "square" (1:1) for grid. |
| `reference_image` | image_url | no | — | Optional reference photo of the subject or product. |


## Steps

### Phase A — Cover Image

Submit the plan with ONE or TWO steps:

1. **Cover image** — If `{{reference_image}}` is provided, use `muapi image edit` (model=`bytedance-seedream-v4.5-edit`); otherwise use `muapi image generate` (model=`bytedance-seedream-v4.5`).
   - Prompt: `Xiaohongshu (RedNote/小红书) style cover photo for {{topic}} post. {{style}}. Aesthetic lifestyle photography, soft natural lighting, visually appealing composition, clean and airy feel. High engagement social media cover, editorial quality. Platform optimized for Chinese lifestyle app.`
   - If `{{text_overlay}}` is provided, append: `Include elegant text overlay saying "{{text_overlay}}" in a stylish font, placed at top or bottom third of image.`
   - Aspect ratio: `3:4` if orientation is portrait, `1:1` if square

After generation, present the cover and offer:
- A set of 3 variations with different color moods (warm / cool / neutral)
- A carousel set (3 images for a RedNote carousel post)
- Upscaling for print/export quality

## Notes
- RedNote covers perform best with: soft bokeh backgrounds, centered subjects, warm or pastel tones, and clear visual hierarchy.
- If topic is fashion/outfit, suggest `ugc-lifestyle-try-on` skill for wearable product shots.
- Korean/Japanese aesthetic filters (soft, matte, film grain) trend highly on the platform.

## Trigger Keywords

`rednote`, `xiaohongshu`, `小红书`, `red note`, `rednote cover`, `xhs cover`, `chinese social`, `lifestyle cover`


---

## 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.
muapi-media-editingSkill

Edit and enhance images and videos with AI via muapi.ai — prompt-based editing, upscaling, background removal, face swap, lipsync, video effects, and more

muapi-media-generationSkill

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

muapi-platformSkill

Setup and utility scripts for muapi.ai — configure API keys, test connectivity, and poll for async generation results

muapi-ai-clippingSkill

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.

muapi-3d-logo-animationSkill

Transform a 2D logo into a premium 3D version and animate it with professional cinematic effects.

muapi-ai-fight-sceneSkill

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.

muapi-animal-video-generatorSkill

Create a hilarious and ultra-realistic video of an anthropomorphic animal acting like a human vlogger in a real-world setting.

muapi-award-ceremony-videoSkill

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".