Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Frame screenshots and screen recordings with the `frames` CLI. Use this skill when the user asks to add Apple device bezels, frame screenshots or videos, create device mockups, inspect screenshot/device matches, or batch-process screenshot/video folders with the command line.
Use for PowerPoint tasks that need slide generation, deck structure, layout cleanup, speaker notes, visual consistency, translation, review, or chart/table insertion.
Use for Word tasks that need document context, proofreading, formatting, heading and numbering restructuring, style application, translation, continuation, or multi-step document editing.
Detect whether a passage shows AI-like writing signals and return an explainable risk estimate with confidence, caveats, and next steps.
Fetch one or more Readwise Reader documents into raw/ without loading bodies into context. Streams content to disk via jq pipe, then chains into ingest.
Mine Readwise highlights via vector search, group by parent document, and write highlight collections into raw/. Streams results to disk without loading into context, then chains into ingest.
短剧制作技能。用于生成完整短剧作品，包括剧本编写、角色设计、9宫格分镜、故事板配置。每次运行生成1部作品（25集，每集30秒=上下两部分各15秒，每部分9宫格分镜）。关键词：短剧、影视、drama、剧本、分镜、storyboard、角色设计。
MV制作技能。根据歌曲歌词或已有MV剧本，结合用户提供的角色/场景参考图片（支持读取指定文件夹），生成完整MV分镜、故事板配置和Seedance视频生成任务。关键词：MV、音乐视频、Music Video、分镜、歌词、storyboard、视频生成。
Convert `make demo/img` statusline snapshots into ANSI-stripped plain text for diffing and PR embedding. Use when comparing statusline renders before/after a change, producing a text representation of a demo scenario, or preparing before/after statusline output for a pull request without screenshots.