发现优质的 AI Agent 技能
聚合 Claude Skills、LangChain、AutoGPT 等优质资源，助力开发者快速构建智能应用
Role
You are a prompt expert proficient in natural language text-to-image models (such as Flux, Pony Diffusion, DALL-E 3). Please read the **3 Chinese model planning proposals** I provide, and convert them into **3 high-quality English natural language prompts**.
Fal 模型 llms.txt 链接获取
输入一个 fal.ai 模型页面链接，自动发现该模型下的所有变体（如 pro/standard、image-to-video/text-to-video），输出每个变体对应的 llms.txt 文档链接。
Card generation SOP (optional)
Goal: After logging a pee/poop event, optionally generate a **consistent, cute, lighthearted** 3:4 vertical card image.
Best Practices and Tips for configuration
> Our model only works on REAL people or the portrait image similar to REAL person. The anime talking head genreation method will be released in future.
ComfyUI ImageGen\n\n## Changelog\n- **[2026-02-11 20:42 EST]**: **v1.5.0** (published) - Standalone `--structured-prompt` fix (no positional arg required); workflow updated to 1920x1080 16:9; production-ready with live tests (JSON direct-to-positive-prompt, async sub-agent delivery).\n- **[2026-02-11 10:10 EST]**: **v1.4.0** - Refactored prompting: agent converts human prompt to structured JSON string; script sends JSON directly as ComfyUI positive prompt (no prose conversion). Added text-in-image quoting rule.
- **[2026-02-11 10:10 EST]**: **v1.4.0** - Refactored prompting: agent converts human prompt to structured JSON string; script sends JSON directly as ComfyUI positive prompt (no prose conversion). Added text-in-image quoting rule. - **[2026-02-11 09:52 EST]**: **v1.3.0** - Script now accepts `--structured-prompt` JSON directly (auto-generates prose internally). Removed agent-side prose step. Updated usage/examples. - **[2026-02-11 09:20 EST]**: **v1.2.0** - Added structured prompt parsing: trans
Video, Film & TV Downloads
- [Torrent Sites](#torrent-sites) - [Torrent Search Engines](#torrent-search-engines) - [Direct Download (DDL) Sites](#direct-download-ddl-sites) - [Subtitle Sites](#subtitle-sites) - [Chinese Video Resources](#chinese-video-resources)
Media Assets: Images, Video, Audio & Fonts
- [Stock Images](#stock-images) - [Stock Video](#stock-video) - [Stock Audio & Sound Effects](#stock-audio--sound-effects) - [English Fonts](#english-fonts) - [Chinese Fonts](#chinese-fonts)
libvips Image Processing
Fast, memory-efficient image processing using libvips via pyvips. Supports 300+ operations including resize, crop, rotate, convert, watermark, composite, and more. Ideal for batch processing large images.
Gemini Watermark Remover
Remove the visible Gemini AI watermark (star/sparkle logo) from generated images using mathematically accurate reverse alpha blending.
Reverse Image Search
Find the source, similar images, or context for any image using reverse image search engines.
Media Downloader
Smartly download media (Video/Music) from URLs (YouTube, Bilibili, X, etc.) to the appropriate local folders.