Skills for Real Engineers. Straight from my .agents directory.
39 skills
watch-video
Agent skill from
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.
How to install watch-video
install watch-video
# install the makerskills pack with the skills CLI
npx skills add coreyhaines31/makerskills# or add only this skill to Claude Code: copy the folder
skills/watch-video/
# into
~/.claude/skills/watch-video/ (all projects)
.claude/skills/watch-video/ (one project)
1# /watch-video — Transcribe and analyze any video at the depth you choose23Replaces and broadens the prior `youtube-transcript` skill. YouTube is now one of many sources; depth is user-controlled.45## Step 1 — Parse input67Accept:8- **YouTube**: full URL, `youtu.be/<id>`, `youtube.com/shorts/<id>`, raw 11-char ID9- **Loom**: `loom.com/share/<id>` or `loom.com/embed/<id>`10- **Vimeo**: `vimeo.com/<id>`11- **Riverside**: download URL or local file12- **Zoom**: local `.mp4` from a downloaded recording13- **X / IG / TikTok video**: URL — defers to `social-fetch` for metadata, uses yt-dlp for the file14- **Local file**: any path to an `.mp4` / `.mov` / `.webm` / `.mkv`1516Detect source from URL pattern or file extension. If ambiguous, ask.1718## Step 2 — Parse depth mode1920| Invocation | Mode | What you get |21|---|---|---|22| `/watch-video <url>` | **transcript** (default) | Clean text, metadata, optional chapters |23| `/watch-video <url> transcript` | transcript | Same as default |24| `/watch-video <url> visual` | visual | Transcript + frames at intervals + Claude vision pass identifying key moments |25| `/watch-video <url> multimodal` | multimodal | Native video to Gemini (if `$GEMINI_API_KEY`), else dense Claude vision frame-by-frame |2627If the depth isn't specified and the video is >10 minutes, ask before defaulting (visual/multimodal cost real money on long videos).2829## Step 3 — Pull metadata3031For URL sources, use yt-dlp:3233```bash34…
Excerpt shown under the repository's MIT license.
More skills in makerskills
Keep exploring
Similar skill repositories
Public repository for Agent Skills
20 skills
An AI skill that provides design intelligence for building professional UI/UX across multiple platforms.
CCCXCUGH6 skills
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
CCCXGHGM+135 skills
Production-grade engineering skills for AI coding agents.
CCCXCU25 skills
The open-source app everyone uses to manage agents at work
CCCX33 skills