AI导哈

设计与多媒体

watch-video

coreyhaines31/m…erskills

When you want to extract content from a video — YouTube, Loom, Vimeo, Riverside, Zoom recording, local MP4, X/IG video, anything yt-dlp supports. Three depth modes user picks per invocation — transcript (just words, fast/free), visual (transcript + ffmpeg frame extraction + Claude vision pass on key moments), multimodal (Gemini native video ingestion if $GEMINI_API_KEY set, else dense Claude vision). Uses local Whisper for transcription (MLX-Whisper on Apple Silicon, faster-whisper elsewhere), falls back to platform-provided transcripts when available (Loom, Riverside, YouTube auto-subs). Saves to ~/Documents/videos/<source>-<slug>-<date>/ and optionally captures summary to second-brain raw/ as call-/meeting-/note-. Triggers on "/watch-video <url>," "watch this video," "transcribe this loom," "analyze this video," "summarize this recording," "key moments from this," "what happened in this video." For a post's text and engagement, use social-fetch.

  • 749 次安装
  • 876 星标
  • 收录于

安装命令

npx skills add https://github.com/coreyhaines31/makerskills --skill watch-video

SKILL.md

/watch-video — Transcribe and analyze any video at the depth you choose

Replaces and broadens the prior youtube-transcript skill. YouTube is now one of many sources; depth is user-controlled.

Step 1 — Parse input

Accept:

  • YouTube: full URL, youtu.be/<id>, youtube.com/shorts/<id>, raw 11-char ID
  • Loom: loom.com/share/<id> or loom.com/embed/<id>
  • Vimeo: vimeo.com/<id>
  • Riverside: download URL or local file
  • Zoom: local .mp4 from a downloaded recording
  • X / IG / TikTok video: URL — defers to social-fetch for metadata, uses yt-dlp for the file
  • Local file: any path to an .mp4 / .mov / .webm / .mkv

Detect source from URL pattern or file extension. If ambiguous, ask.

Step 2 — Parse depth mode

相关 Skills

decidecoreyhaines31/m…erskillsWhen you have a decision to make and want a structured workflow that picks the load-bearing questions, walks through them, reaches a call (or "wait"), and archives the rationale for future reference. Based on the 37signals Guide to Making Decisions (38 questions) plus house additions like Q39 opportunity cost ("what does saying yes displace?"). Triages to 6–8 relevant questions per decision instead of forcing the full set. Archives every decision to ~/.config/makerskills/decide/archive/ with a revisit date so you can check later whether the call was right. Triggers on "/decide," "help me decide," "should I [X]," "I need to make a decision about," "stuck on a decision," "deciding between," "go/no-go on," "what should I do about." This is both the decision-making workflow AND the decision log — making the decision is the act of logging it.智能体工作流504