Convert Douyin video and comment data into evidence-graded learning assets.
npx skills add https://github.com/Rimagination/dy-note --skill dy-note
Please help me install this Agent Skill. Skill: dy-note Source: https://github.com/Rimagination/dy-note/tree/main Command: npx skills add https://github.com/Rimagination/dy-note --skill dy-note
DyNote turns scattered Douyin videos, captions, speech, comments, and metadata into reusable, traceable learning materials without mistaking quick summaries or sparse transcripts for complete evidence.
Ask the Agent to use DyNote to analyze a Douyin share text, first checking existing assets and then extracting the strongest available transcript before generating a traceable learning note.
High-intent search queries and answers about installing and using this skill.
To extract ASR transcripts and learning notes from Douyin videos, the Skill utilizes Whisper or Qwen3-ASR to process video data, producing traceable learning assets with provenance.
Evidence-graded video analysis assesses transcript density and uses visual evidence like keyframes or OCR, ensuring knowledge archiving preserves source provenance and distinguishes evidence levels rather than relying on quick summaries.
Yes, you can analyze Douyin comments and account metadata for audience insights through routed analysis plans that extract audience signals and structured segments into a reusable asset package.
Yes, you need ffmpeg and Python tooling to execute local video analysis and subtitle extraction, as these dependencies handle media processing and ASR transcription workflows.
Yes, web-access supports authorized logged-in Douyin Web AI workflows for fact checking, enabling secure processing of high-stakes factual claims while protecting browser credentials and signed media URLs.
The best way to archive reusable video assets without losing source provenance is to package transcripts, structured segments, metadata, and provenance limits together, allowing later knowledge-base retrieval to reuse existing outputs safely.
coderfengyunTranscribe audio and video into Markdown transcripts with Qwen3-ASR.
jsphh7124Convert academic journals from PDF, Word, PowerPoint, Excel, images, and transcripts into structured Markdown.
yangliu2060Automate AI video creation and multi-platform publishing via MCP services.
bomberoxenviosdosruedasBuild speech transcription pipelines using Whisper models and cloud ASR services.
