sonpiaz / watch-cli
Gives a coding agent eyes and ears for any social video: timestamped frames plus a transcript, about 50x cheaper than sending the whole file to a multimodal API.
Why this job: says: coding agent; topics: claude-code
What it does
Eyes and ears for your AI agent. watch-cli composes yt-dlp + ffmpeg + a Whisper-class ASR into a single command that hands an agent the raw materials to "watch" any video: VIDEO + FRAMES + TRANSCRIPT, ready for an LLM to read frames as images and transcript as text.
Get started
./install.sh --with-skill
# also drop SKILL.md into ~/.claude/skills/watch-cli/
./install.sh --with-mcp
# print the npm install hint for the MCP stdio server - Maintenance
- Active
- Last commit 57 days ago
- Stars
- 260
- +1 this week
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v0.3.4
- Released 2 months ago
- Built with
- Shell
- 92% of the code
Is it looked after?
- Contributors
- 1
- Last 90 days
- Issues
- None
- No issues filed
- Pull requests
- 17 merged
- 1 waiting
- Releases
- 5
- 5 in the last year
- No contributing guide
- No security policy
- No code of conduct
More: languages, topics and project record
Languages
- Shell 92%
- TypeScript 8%
Topics
- ai-agents
- claude-code
- cli
- mcp
- transcription
- video
Project record
- JobCoding agents
- StatusListed
- Commits23
- Forks72
- Watching2
- Stars in 28 days+11
- CreatedApr 29, 2026
- First seen by usNov 7, 2026
- CheckedNov 7, 2026