rad-workflow

Convert novel text, web-novel chapters, or prose scenes into manga/comic production plans and image-generation prompts. Use when the user asks to turn a novel into manga, make comic pages from story text, create manga page prompts, generate character/scene bibles, split prose into beats/panels/pages, batch-generate comic images, or revise generated manga pages while preserving character consistency.

Standardize Radiology Obsidian notes to V4, organize video/lecture content, and summarize papers. Trigger on: 整理, 修正, cleanup, V4, 影片整理, 字幕, 論文筆記, paper summary, YAML fix, footnote conversion, 閱片 callout, subtitle/audio organization, Paper L3 creation, SRT分段, JSON導航, 課程筆記, course listing. 7-task pipeline: (1) YAML V4 frontmatter fix, (2) citation→footnote, (3) 閱片 table→callout, (4) video content from subtitles/audio/slides, (5) paper PDF summarization with L3 deep-study template + visual canvas map, (6) SRT→segmented JSON for web player navigation, (7) course series listing note with media links. Use even for partial requests like "fix the YAML", "整理這個影片", "幫我摘要這篇論文", "製作分段JSON", or "建立課程筆記". Also trigger for: 讀書筆記, 章節整理, textbook, 教科書, 深度閱讀, 字幕導航, 更名, 目錄.

Turn a PDF (slides, case reports, handouts) into a single narrated Traditional Chinese audiobook MP3. Rasterize each page to an image, read it, write a natural spoken 繁體中文逐字稿 per page, synthesize each with edge-tts, then concatenate into one mp3. Use when asked to make a Chinese voiceover/audio/podcast/audiobook from a PDF or slide deck, "把 PDF 轉成語音/逐字稿/有聲書", or "用 edge-tts 唸投影片".

Implement or resume tasks from a Spectra change

Query openspec/documents and answer questions

Have a focused discussion about a topic and reach a conclusion

Update an existing Spectra change from external context

Create a change proposal with all required artifacts