Transcribes a YouTube video or local audio/video file to plain text with ./fw yt2sub. Use when a task needs spoken content as text: the user gives a YouTube URL or media file to transcribe, summarize, or watch, or wants notes or an assignment written from a talk, lecture, or podcast. Tries YouTube captions first (zh-Hant/en) and falls back to local faster-whisper, so use it instead of a hand-rolled yt-dlp + whisper pipeline.
This skill, enstw/thesisbug2, provides a streamlined solution for transcribing spoken content from YouTube videos or local audio/video files into plain text. It is particularly useful when a user needs to extract text from a lecture, podcast, or talk for note-taking, summarization, or assignment writing. The skill prioritizes fetching existing YouTube captions in Traditional Chinese (zh-Hant) or English, which is faster and more accurate, but gracefully falls back to a local faster-whisper model for full transcription when captions are unavailable. Designed for AI agents like Claude Code, it replaces manual pipelines using yt-dlp and whisper, offering a single command (`./fw yt2sub`) that handles the entire process efficiently.
npx skills add https://github.com/enstw/thesisbug2/tree/main/.agents/skills/yt2subTranscribes a YouTube video or local audio/video file to plain text with ./fw yt2sub. Use when a task needs spoken content as text: the user gives a YouTube URL or media file to transcribe, summarize, or watch, or wants notes or an assignment written from a talk, lecture, or podcast. Tries YouTube captions first (zh-Hant/en) and falls back to local faster-whisper, so use it instead of a hand-rolled yt-dlp + whisper pipeline.
Extract frames or short clips from videos using ffmpeg.
Summarize or transcribe URLs, YouTube/videos, podcasts, articles, transcripts, PDFs, and local files.
Use when testing, fixing, or extending the OpenClaw Control UI GUI with Vitest + Playwright end-to-end checks, mocked Gateway WebSocket flows, mocked dashboard runs, screenshots/videos, or agent-verifiable browser proof.
Obra superpowers agent skills.
See, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand- extract frames, build visual/semantic/temporal indexes, and search moments with timestamps and auto-clips. Act- transcode and normalize (codec, fps, resolution, aspect ratio), perform timeline edits (subtitles, text/image overlays, branding, audio overlays, dubbing, translation), generate media assets (image, audio...
End-to-end marketing campaign planning and execution. Covers audience research, positioning, campaign angle definition, landing page copy, email sequences, social posts, ad copy, short-form video scripts, and content calendars. Use as the orchestration layer for multi-channel product launches. Use when planning or executing a multi-channel product launch, or producing landing page, email, social, or ad copy.