{"skill":{"slug":"shumianyu","displayName":"shumianyu","summary":"将分段 asr 文本流在结束时统一整理成流畅书面语，并在用户指定 target_language 时输出译文。适用于语音听写、会议转写、采访整理、播客或视频字幕后处理等场景，尤其适合不需要实时字幕、只需要在整段结束后得到最终书面结果的任务。保持接口抽象、可替换，不绑定任何特定厂商 api。","tags":{"latest":"1.0.0"},"stats":{"comments":0,"downloads":244,"installsAllTime":0,"installsCurrent":0,"stars":0,"versions":1},"createdAt":1773464411417,"updatedAt":1777526009276},"latestVersion":{"version":"1.0.0","createdAt":1773464411417,"changelog":"- Initial release of the asr-written-rewriter-stream skill.\n- Accepts segmented ASR text streams and outputs a single, fluent written result only after receiving an explicit end signal.\n- Optionally translates the finalized written result when a target_language is provided.\n- Designed for post-processing meeting transcripts, interviews, podcasts, and similar scenarios—optimized for whole-segment finalization over real-time subtitle needs.\n- Keeps interfaces abstract and compatible with any upstream ASR provider; not tied to any specific API or service.\n- Respects and applies domain lexicons for consistent handling of names, technical terms, and abbreviations.","license":"MIT-0"},"metadata":null,"owner":{"handle":"hei-maom","userId":"publishers:hei-maom","displayName":"HeiMaoM","image":"https://avatars.githubusercontent.com/u/145641200?v=4"},"moderation":null}