watch-skill MCP Server
oxbshw/watch-skill
[](https://agentrank-ai.com/tool/oxbshw--watch-skill/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) Give AI agents eyes, ears, and verifiable results. Watch Skill turns video, audio and screen activity into searchable, timestamped evidence and proves work with deterministic contracts, not model opinion. DeepWatch is the agent workspace built on DeepSeek Harness. Python + npm, MCP, CLI, REST, Web.
claude mcp add agentrank -- npx -y agentrank-mcp-server Overview
oxbshw/watch-skill is a Python tool licensed under MIT. Give AI agents eyes, ears, and verifiable results. Watch Skill turns video, audio and screen activity into searchable, timestamped evidence and proves work with deterministic contracts, not model opinion. DeepWatch is the agent workspace built on DeepSeek Harness. Python + npm, MCP, CLI, REST, Web. Topics: ai-agents, computer-vision, mcp, multimodal, ocr, video-understanding, python, speech-to-text, video-analysis, agent-observability, agentic-ai, audio-understanding, deepseek, deepseek-harness, local-first, typescript, verification, deepwatch, agent-skills, llm.
Ranked #3006 out of 24846 indexed tools.
Ecosystem
Score Breakdown
481 stars → growing community
Last commit 1mo ago → moderate activity
11/14 issues closed → decent issue management
4 contributors → small team
No dependents → no downstream usage
340 weekly installs → early adoption
Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →
How to Improve
Badge all embed codes →
[](https://agentrank-ai.com/tool/oxbshw--watch-skill/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) <a href="https://agentrank-ai.com/tool/oxbshw--watch-skill/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/v1/badge/oxbshw--watch-skill" alt="AgentRank"></a> Matched Queries
From the README
<div align="center"> # Watch Skill · DeepWatch **Give AI agents eyes, ears, and verifiable results.** **Watch Skill** turns video, audio and screen activity into searchable, timestamped evidence, and answers *did that actually work?* with a deterministic contract rather than a model's opinion. Add it to the agent you already use over MCP. **DeepWatch** is a ready-made agent workspace, built on the official DeepSeek Harness with Watch Skill already composed in, where a tool call leaves a receipt you can open and a result can be checked by something other than the agent that produced it. **Python · PyPI** **Node · npm** **Gates and directories** [Install](#start-here) · [Use it](#the-deepwatch-workspace) · [THE LOOP](#the-loop-observe-act-verify) · [Packages](#which-package-is-for-you) · [Architecture](#how-it-fits-together) · [Docs](#documentation) · [Community](#community--ecosystem) </div> --- ## Two capabilities, and they work apart **Perception.** Video, audio and screenRead full README on GitHub →
Get the weekly AgentRank digest
Top movers, new tools, ecosystem insights — straight to your inbox.