MCP App StoreMCP App Store
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 transcribes 小宇宙 (Xiaoyuzhou) podcast episodes using Qwen ASR. The bash script handles audio URL extraction, async task submission to DashScope API, polling, and result download. The Python script formats raw JSON transcripts into speaker-segmented Markdown. Both scripts exited with usage messages in dry-run mode (expected — they require real input URLs and API keys). The hardcoded speaker detection dictionary targets specific podcast hosts, limiting generalizability.
Clean, purpose-built skill for a niche Chinese podcast platform. No security concerns beyond minor shell variable interpolation in JSON. The hardcoded speaker dictionary is a notable limitation — would benefit from configurable speaker profiles. Architecture follows skill spec well.
BluOS CLI (blu)
Control Bluesound and NAD speakers: discover devices, play/stop, group/ungroup, and set volume from the CLI.
Verifying Markdown Formatting
Checks Markdown files for structural and stylistic formatting issues (headings, lists, code blocks, links) and applies deterministic fixes.
NotebookLM Research Agent
End-to-end research-to-content pipeline: ingest sources into Google NotebookLM, run deep cited research, generate downloadable artifacts, and produce polished c
Speak Security Basics
Security best practices for integrating Speak: API key management, audio data privacy, student data protection, and COPPA/FERPA compliance for production deploy
Deep Research
Run multi-step autonomous research workflows: search, crawl, validate sources, and produce structured research reports and market analyses.
Voice Memo Organizer
Locate, transcribe (local whisper.cpp), summarize and index Apple Voice Memos into a searchable archive with titles, themes and key quotes.
News Briefing
Generate realtime, topic-specific Chinese news digests with AI insights and deliver them as compact Feishu cards or scheduled briefings.
FFmpeg Guide
Comprehensive FFmpeg reference for encoding, converting, streaming, filtering, and analyzing audio/video — command examples, common patterns, and troubleshootin