liustack
共 2 个 Skill，均有经来源核对的实质文档。打开卡片可阅读原始说明，了解包内文件和安装方式。
liustackmodlens
Plug-in vision for text-only models. Hard rule: when a file path or URL with an image extension (.png, .jpg, .jpeg, .webp, .gif, .heic, .heif) appears anywhere in the conversation (typed by the user, injected as a [Image: source: ] line, or inside a tag) and you cannot see that image's content, run this skill on it before any other approach: no self-built OCR, no PIL, no tesseract. Also triggers on pasted-image placeholders such as [Image 1] and [Unsupported Image]. If you can actually see the i
- 1小时安装量
- 2
- GitHub Stars
- 4496
- 最近更新
- 10月23日
liustackflipbook
Make short animated films as MP4 that tell a story: a short film, an animated explainer, a story-driven product or brand film, an animated title. You write the story (story.json), then timeline.json and one HTML composition, and flipbook renders it frame by frame and checks the result against the story before delivery. Use when the user asks for an animated video or film, a story told in animation, or an animation exported to MP4. Hard rules: the picture is a pure function of t (no CSS animation
- 1小时安装量
- 1
- GitHub Stars
- 1
- 最近更新
- 9月28日