watch-skill MCP
Turns video, audio and screen recordings into searchable timestamped evidence and checks whether the intended result was achieved. MCP server, version 0.1.x
- 477 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- Processes screen and sound recordings with personal data
- Version 0.1.x, an early project
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add mcp/watch-skillDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Processes screen and sound recordings with personal data
- Version 0.1.x, an early project
This is third-party code. Review the repository files before installing.
What it does
watch-skill gives an agent eyes and ears: it turns video, audio and screen recordings into searchable evidence with timestamps and checks whether the intended result was achieved. It works as an MCP server and a skill. Installation: `pip install 'watch-skill[standard]'`, `npx skills add oxbshw/watch-skill -g`, `npm install -g @deepwatch/cli`. Version deepwatch-v0.1.4 from 08.09.2026, MIT license. The project is early, version 0.1.x.
Who it is for. For developers and testers who need an agent to go through screen recordings, video and audio and find the right places by time.
Good fit when
- You need to go through a screen recording or video and find a moment by time
- You need a check that the intended action happened
- You need audio and video search for an agent
Not a fit when
- You cannot pass screen and sound recordings to a tool
- You need a mature version: it is 0.1.x now
Example request
Go through the bug reproduction recording, find the moment the error appears and give the timestampMCP
- Transport
- stdio
- Authentication
- not required
Limitations
The tool processes screen and sound recordings that may contain personal data and other people's voices, so access is extended: make sure you have the right to the recording and do not process other people's recordings without consent. Version 0.1.x, an early project.
How to disable. Remove the skill and the packages (pip uninstall watch-skill, npm uninstall -g @deepwatch/cli), the server entry from the client and the created indexes.
FAQ
What does watch-skill do?
It turns video, audio and screen recordings into searchable evidence with timestamps.
How do I install it?
pip install 'watch-skill[standard]', npx skills add oxbshw/watch-skill -g or npm install -g @deepwatch/cli.
Is it mature?
No, version 0.1.x, an early project.
Discussion
No questions or reviews yet.
Related
MCP serversMotion Video Skill
motion-video-skill
1080p beat-synced video: HyperFrames and GSAP, voice-over, karaoke captions, sound effects and music. Provider keys are kept in the CLI configuration
A set of SKILL.md skills for short-video and content production: topic, script, voice, avatar, editing, covers and motion graphics
ChatGPT short-video editing skills
ChatGPT 剪短影音 Skills
Two agent skills: set up the editing environment and build a vertical short video in eight verified steps
A skill that teaches the agent to build narrated videos through narrator-ai-cli: source, template, music, voice, script and composing
Video skills for Claude Code and Codex: break a clip into a shot-by-shot analysis and render video with a storyboard overlay
Claude Video Vision
claude-video-vision
An MCP server and Claude Code plugin that let the agent watch video: frames via ffmpeg and audio transcription via Gemini, local Whisper or OpenAI
README in short
The README describes a tool that turns video, audio and screen recordings into searchable evidence for an agent, an MCP server and a skill. MIT license.