watch-skill

Name: watch-skill
Author: oxbshw

Verified

Video understanding and self-verification for AI agents. Turn videos, streams, and agent screen recordings into searchable, timestamped evidence—then use THE LOOP to inspect, fix, and verify the work. MCP, CLI, REST, local-first.

203stars

26forks

Python

Installation

# Add to your Claude Code skills
git clone https://github.com/oxbshw/watch-skill

Getting Started

Guides for using ai agents skills like watch-skill.

Caveman: Cut Claude Token Use by 65%
How agent-side prompt compression works, when to use it, and when not to.
What is an AI Skills Marketplace?
Definitions, how marketplaces work, and how to choose between them in 2026.
Getting Started with AI Skills

Security ReportVerified

Last scanned: 7/7/2026

{
  "issues": [
    {
      "file": "README.md",
      "line": 32,
      "type": "remote-install",
      "message": "Install command (remote install script piped to a shell — review the source before running): \"curl -fsSL https://raw.githubusercontent.com/oxbshw/watch-skill/main/scripts/ins\"",
      "severity": "low"
    }
  ],
  "status": "PASSED",
  "scannedAt": "2026-07-07T07:39:55.981Z",
  "npmAuditRan": true,
  "pipAuditRan": true,
  "promptInjectionRan": true
}

README.md

Frequently Asked Questions

What is watch-skill?

watch-skill is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by oxbshw. Video understanding and self-verification for AI agents. Turn videos, streams, and agent screen recordings into searchable, timestamped evidence—then use THE LOOP to inspect, fix, and verify the work. MCP, CLI, REST, local-first. It has 203 GitHub stars.

Is watch-skill safe to use?

Yes. watch-skill passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.

How do I install watch-skill?

Clone the repository with "git clone https://github.com/oxbshw/watch-skill" and add it to your Claude Code skills directory (see the Installation section above).

What programming language is watch-skill written in?

watch-skill is primarily written in Python. It is open-source under oxbshw on GitHub, so you can review or fork the full source.

Are there alternatives to watch-skill?

Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh watch-skill against similar tools.

Agentic AI for Beginners

Build your first AI agent from scratch - tool use, ReAct pattern, memory, deployment

41 minBeginner

Comments (0)

to leave a comment.

No comments yet. Be the first to share your thoughts!

Related Skills

superpowers

by obra

An agentic skills framework & software development methodology that works.

234,966

open-browser-use superseo-skills

Watch Skill

Give every AI agent eyes for video—and a way to inspect its own work.

Watch Skill is a local-first video intelligence layer for agents. It turns videos, live streams, meetings, and screen recordings into searchable, timestamped evidence. Agents can understand what happened, retain it across sessions, and cite the exact moment behind an answer.

When the video is the agent's own browser or desktop session, THE LOOP closes the feedback cycle: record the work, evaluate it against plain-language criteria, guide the fix, and verify the result. The same engine is available through skills, 23 MCP tools, a CLI, REST, and native framework adapters.

Watch. Remember. Fix. Verify.

One video layer, three agent capabilities

Capability	What the agent gains
Watch	Scene-aware frames, on-screen text, and local-first transcription from 1,800+ sites, live HLS/DASH streams, local media, meetings, browsers, windows, and desktops.
Remember	A persistent, searchable index with timestamp citations, hybrid retrieval, cross-video synthesis, and reusable lessons.
Verify	A capture → critique → fix → proof loop for browser flows, interfaces, generated video, gameplay, and monitored streams.

Start in 60 seconds

Claude Code

/plugin marketplace add oxbshw/watch-skill
/plugin install watch-skill@watch-skill

Run /watch-skill:setup-watch-skill once after installation. It installs the engine, checks the binary dependencies, registers the MCP server, and offers to configure a vision provider.

macOS and Linux

curl -fsSL https://raw.githubusercontent.com/oxbshw/watch-skill/main/scripts/install.sh | sh

Windows

powershell -ExecutionPolicy Bypass -c "irm https://raw.githubusercontent.com/oxbshw/watch-skill/main/scripts/install.ps1 | iex"

Then watch a video and ask a follow-up:

watch-skill watch "https://youtu.be/..." "Summarize the important moments."
watch-skill ask <video_id> "When does the demo first fail?"
watch-skill search "pricing decision"       # search every indexed video
watch-skill serve                           # MCP over stdio

Transcription, OCR, and search can run locally without an API key. For visual Q&A, use Gemini, Anthropic, OpenAI, OpenRouter, or a local Ollama model. See Getting started for manual installation and Configuration for provider and privacy settings.

Why use it

Evidence instead of frame dumps. Scene detection and perceptual deduplication spend the frame budget on distinct moments. Answers include timestamps, confidence, and the evidence used to support them.
Persistent video memory. Analyze once, ask again without downloading or transcribing the same video. Hybrid full-text and vector retrieval works within one video or across the entire library.
Local-first processing. Original-language captions are preferred, local Whisper is the default fallback, and cloud speech-to-text is opt-in. An Ollama configuration keeps the complete pipeline on the machine.
Flow verification. THE LOOP records an agent's browser, screen, or window; checks the result against plain-language criteria; and produces before/after proof after a fix.
Corrections that persist. report_mistake stores a local lesson, applies it to related questions, and turns it into a replayable evaluation.
Measured cost controls. Text-first answers, semantic caching, configurable token budgets, and explicit cheapest, quality_first, and offline_only policies keep the trade-offs visible.
Multilingual retrieval. Script-aware OCR routing, Arabic normalization, CJK substring matching, and multilingual embeddings support questions across languages.

The repository includes reproducible cost and perception benchmarks. Product claims in this README link to the relevant implementation notes or testable example rather than relying on unqualified marketing numbers.

Works with your agent

The setup command detects supported clients and updates their configuration with a backup. Manual guides are available for every entry below.


Claude Code	Claude Desktop	Cursor	Codex CLI
Cline	Windsurf	Gemini CLI	VS Code
GitHub Copilot CLI	Kimi Code	Qwen Code	OpenCode
Goose	OpenHands	Kilo Code	Qodo
Agent Zero	OpenClaw	Pi	Hermes

Native tools are also available for LangChain/LangGraph, CrewAI, OpenAI Agents SDK, LlamaIndex, and AutoGen; any other framework can use REST or MCP.

Connection	Supported agents and frameworks
Plugin and skills	Claude Code, OpenClaw, Pi, Hermes-style agents
MCP	Claude Desktop, Cursor, Codex CLI, Cline, Windsurf, Gemini CLI, VS Code, GitHub Copilot CLI, Kimi Code, Qwen Code, OpenCode, Goose, OpenHands, Kilo Code, Qodo, Agent Zero
Native Python tools	LangChain/LangGraph, CrewAI, OpenAI Agents SDK, LlamaIndex, and AutoGen
HTTP	Vercel AI SDK, n8n, and any client that can call REST/OpenAPI

The full compatibility matrix separates machine-tested, machine-configured, and documentation-verified integrations. If your agent is missing, the adapter template provides a short contribution path.

Common workflows

Build a searchable video library

watch-skill batch ./recordings --limit 50
watch-skill library overview
watch-skill library ask "What did the team decide about authentication?"

library ask synthesizes evidence across videos and retains per-video timestamp provenance. The [library example](exam