Transform raw auto-generated captions into clean, readable transcripts with zero content loss.
Auto-generated captions (Zoom, YouTube, Teams, etc.) are messy: fragmented sentences, timestamps everywhere, speaker tags on every line, filler words, transcription errors. This skill reconstructs them into coherent, flowing text that can be consumed by humans or downstream skills (like lecture-alchemist).
Zero Content Loss Every substantive statement, technical term, concept, question, and answer from the raw captions MUST appear in the output. Only noise is removed, never content.
将原始自动生成的字幕(Zoom、YouTube、Teams、Google Meet、Otter.ai 等)清理并重建为可读、连贯的文字记录。当用户提供原始字幕文件(.txt、.vtt、.srt)、带有时间戳和演讲者标签的会议记录或要求清理/优化记录时使用。处理:时间戳删除、说话人标签标准化、填充词删除、断句重建、转录错误纠正、段落形成。保留每一段实质性内容,同时消除噪音。触发短语:“清理此文字记录”、“优化字幕”、“修复此文字记录”、“处理缩放字幕”、“清理会议记录”。 来源:prakharmnnit/skills-and-personas。