Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Lightweight WSI tile extraction and preprocessing. Use for basic slide processing tissue detection, tile extraction, stain normalization for H&E images. Best for simple pipelines, dataset preparation, quick tile-based analysis. For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml.
Use when building a LaTeX manuscript submission pipeline with templates, latexmk, BibTeX/Biber, chktex, latexindent, CI PDF builds, compile debugging, and submission zip packaging.
AI 生成动画短片生产线：图（关键帧锁确定性）→ 视频（i2v 给活气）→ 后期（剪辑做节奏）。 Use when: 做动画短剧/角色 IP 短片、猫咖日记系列新集、图生视频管线、剧情类 AI 视频。 Not for: 录屏/教程/showcase 视频（用 video-forge）、单张图生成（用 image-generation）、PPT（用 ppt-forge）。 Output: charter+分镜+prompt book+素材账本+EDL 驱动的成片，全程可复现可重渲。
猫猫指导外部项目文档重构 — AI FDE 知识工程方法论。 Use when: 猫猫部署到外部项目、用户项目缺少结构化文档、需要知识工程指导、冷启动理解业务。 Not for: cat-cafe 项目自身开发、已有完善 docs/ 结构的项目（直接用 CatCafeScanner）。 Output: 文档现状诊断 + 路径选择 + 三层知识注入建议 + 文档骨架模板。
视频制作全链路：素材入库 → 剧本冻结 → 全局配音 → 对齐 → 渲染 → 审查 → 交付。 Use when: 做视频、做 showcase、做教程视频、录屏剪辑、video review、节奏审查。 Not for: 纯代码开发（用 worktree/tdd）、纯文档写作（直接写）、PPT（用 ppt-forge）。 Output: schema 驱动的视频成片 + 多猫审查通过 + 可发布。
猫猫可编程导航 Workspace 面板：operator说模糊意图，猫猫找到路径，自动打开文件/目录。 Use when: operator说"打开日志""看看代码""打开设计图""帮我打开那个文档"等模糊指令。 Not for: 打开 localhost 前端页面（用 browser-preview）、纯代码编写（不涉及展示给operator看）。 Output: Hub 右侧 Workspace 面板自动打开并导航到目标文件/目录。
Generate captions (descriptions) for images, videos, and documents using ZhiPu GLM-V multimodal model series. Use this skill whenever the user wants to describe, caption, summarize, or interpret the content of images, videos, or files. Supports single/multiple inputs, URLs, local paths, and base64 (images only).
A skill that uses GLM-V native grounding capabilities for coordinate conversion, bounding-box visualization, and more. GLM-V native grounding can locate any target specified by the prompt in an image and output relative coordinates normalized to 0-1000 based on image size. Coordinate formats include 2D bounding box (default), 2D points, and 3D bounding box. GLM-V also supports spatiotemporal localization and tracking of multiple prompt-specified targets in videos, outputting 2D bounding boxes per second.
Convert a PDF (research paper, report, or any document) into a polished multi-slide HTML presentation with a structured outline JSON and summary markdown. Trigger this skill when the user mentions making slides or a PPT from a PDF — in Chinese or English.