from xiaoyuzhou-transcription-skill12
Automates transcription of Xiaoyuzhou podcast episodes, producing speaker-segmented verbatim transcripts, 5–8 key-point summaries, and 8–10 Q&A pairs; integrate
This skill automates extraction and transcription of Xiaoyuzhou (小宇宙) podcast episodes. It provides scripts and an agent workflow: extract audio from an episode page, submit audio to Qwen ASR for async transcription, format a speaker-segmented verbatim transcript with timestamps, and generate concise key-point summaries and Q&A pairs in Chinese. The output is assembled into a Markdown file suitable for publishing or archival.
Use when a user shares a Xiaoyuzhou podcast link or requests podcast-to-text conversion, verbatim transcripts, or concise summaries in Chinese. It's designed for long-form episodes (up to several hours) and includes validation steps to ensure the transcription result is complete before formatting.
Best used by agents that can run or orchestrate shell/python helpers and call external ASR services (agents with exec or code capability).
This skill has not been reviewed by our automated audit pipeline yet.
