AI Agent Skills

Your AI agents can write code and automate tasks brilliantly. But they’re missing one critical capability: the ability to work with video and audio - capturing screens, searching through recordings, editing clips, and streaming results. VideoDB Agent Skills give coding assistants like Claude Code and Cursor the power to execute server-side video workflows. OpenClaw Monitoring adds visual observability for autonomous agents. Both turn text-only agents into multimodal collaborators.

For Coding Assistants

Claude Code, Cursor, Copilot - Execute video workflows as code

For Autonomous Agents

OpenClaw agents - Monitor, record, and audit agent sessions

Prerequisites

Before installing any agent skill, you’ll need:

VideoDB API Key

Get a free API key from console.videodb.ioNo credit card required. Free tier includes 50 uploads.

System Requirements

Python 3.9+ (for VideoDB Skills)
Node.js 18+ (for OpenClaw Monitoring)
Platform: macOS, Linux, Windows (PowerShell)

Set Your API Key

Export your API key in your shell:

export VIDEO_DB_API_KEY=your-key-here

Or add it to a .env file in your project root.

VideoDB Skills works on any platform (macOS, Linux, Windows) and any agent that supports skills. OpenClaw Monitoring requires Node.js and OpenClaw installed. Both use VideoDB’s platform - ingestion is billed at $0.084/hour for recording. Indexing is on-demand.

VideoDB Skills

VideoDB Skills on GitHub

Complete source code, installation guide, and configuration examples

What It Does

VideoDB Skills is a perception capability for AI coding agents that enables See → Understand → Act, as an API, for video and audio. It gives agents working with Claude Code, Cursor, Copilot, and other platforms the ability to execute server-side video workflows. One unified interface for:

See - Capture desktop screens, microphone/system audio, RTSP streams, and ingest files, URLs, and YouTube content
Understand - Visual analysis, transcription, indexing, and searching moments with playable clips
Act - Stream results, trigger alerts, edit timelines, generate subtitles/overlays, and export clips

Works with: Claude Code, Cursor, Copilot, and other skill-compatible coding agents

Why Use It

Video Workflows
Real-Time Perception
Search & Intelligence

Execute video operations without local ffmpeg installation:

Upload from YouTube, URLs, or local files
Trim, merge, clip, overlay text/images/audio
Transcode, reframe, adjust resolution and aspect ratio
Get instant playable HLS links via built-in CDN

Installation

Option 1: NPX (Recommended)
Option 2: Claude Code Plugin

npx skills add video-db/skills

/plugin marketplace add video-db/skills
/plugin install videodb@videodb-skills

Setup

After installation, run the setup command:

/videodb setup

The agent guides you through:

Obtaining your VideoDB API key ($20 free credits, no credit card)
Installing the SDK
Verifying connectivity

Quick Start

Ask your agent to execute video tasks:

Upload [YouTube URL] and provide a shareable stream link

Extract clips from 10s-30s and 45s-60s and merge them

Generate background music and add to this clip

Add white text on black background subtitles to the original video

Capture my screen for two minutes and report my activities with insights

Monitor my IP Camera RTSP stream and log person detection alerts with timestamps

Capabilities

Capability	What It Does
Capture	Desktop screen, microphone, and system audio for real-time processing
Upload	Ingest from YouTube, URLs, or local files
Context	Generate structured context from RTSP feeds or desktop streams
Search	Locate moments by speech, scenes, or metadata with playable evidence
Transcripts	Generate timestamped transcripts
Subtitles	Auto-generate, style, and burn-in subtitles
Edit	Trim, merge, clip, overlay text/images/audio; add dubbing/translation
AI Generate	Create images, video, music, sound effects, voiceovers
Transcode/Reframe	Adjust resolution, quality, aspect ratio, social crops server-side
Stream	Obtain instant playable HLS links via built-in CDN

OpenClaw Monitoring

OpenClaw Monitoring on GitHub

Complete source code, installation guide, and configuration examples

What It Does

OpenClaw Monitoring is “CCTV for AI agents” - a skill that monitors, records, and audits your OpenClaw autonomous agent sessions. Every agent run becomes:

A live stream you can watch in real-time
A replayable recording with a shareable URL
A searchable archive you can query with natural language

Think of it as: A dashcam for your AI agent. A black box recorder for browser automation. Ask “when did it open the spreadsheet?” and get the exact moment with a playable clip.

Why Use It

Full Visibility
Searchable History
Compliance & Security

Watch your agent work live or replay sessions later. No more “send task → wait → hope for the best.”Catch issues before they become incidents.

Prerequisites (OpenClaw Specific)

In addition to the prerequisites above, you’ll need:

OpenClaw installed and running
An OpenClaw agent configured

Installation

Option 1: Agent-Guided (Recommended)
Option 2: Manual

Point your OpenClaw agent at the repo:

please install https://github.com/video-db/openclaw-monitoring skill and set it up

The agent will handle installation automatically.

git clone https://github.com/video-db/openclaw-monitoring.git
mkdir -p ~/.openclaw/workspace/skills/videodb-monitoring
cp -r openclaw-monitoring/videodb-monitoring-skill/* ~/.openclaw/workspace/skills/videodb-monitoring/
cd ~/.openclaw/workspace/skills/videodb-monitoring
npm install

Setup

Set Your VideoDB API Key

openclaw config set skills.entries.videodb-monitoring.env.VIDEODB_API_KEY 'sk-xxx'

Start the Monitor

cd ~/.openclaw/workspace/skills/videodb-monitoring
nohup npx tsx monitor.ts > ~/.videodb/logs/monitor.log 2>&1 & disown

Restart OpenClaw Gateway

openclaw gateway restart

This makes the skill available to your agent.

Quick Start

Once installed, ask your agent:

Do X on the browser and send me the recording

What did I do in the last hour?

Find when I opened the spreadsheet

The agent can even use its own recordings:

Summarize what you did in the last 2 hours

CLI Commands

The videodb.ts CLI provides these commands:

Command	What It Does
`start-indexing`	Start all indexing (visual + audio + transcript)
`stop-indexing`	Stop all indexing
`start-visual-index`	Start visual scene indexing
`start-audio-index`	Start audio indexing
`start-transcript`	Start transcript extraction
`search`	Natural language search
`summary`	Generate AI summary
`transcript`	Get full transcript
`stream`	Get playable stream URL

Indexing is on-demand and separate from recording. You only pay for AI processing when you trigger it.

Try Without Setup

Skip installation and try indexing against a hosted live OpenClaw session:

git clone https://github.com/video-db/openclaw-monitoring.git
cd openclaw-monitoring
echo "VIDEO_DB_API_KEY=your_api_key_here" > .env
uv run try_without_setup.py

This connects to matrix.videodb.io, starts indexing, and prints events to your terminal.

Which Skill Should I Use?

Feature	VideoDB Skills	OpenClaw Monitoring
Best For	Coding assistants (Claude Code, Cursor, Copilot)	Autonomous agents (OpenClaw)
Use Case	Video workflows: capture, upload, edit, search, stream	Remote agent monitoring, compliance, auditing
Capabilities	Server-side video editing, transcription, AI generation	Desktop recording, live streaming, visual audit trails
Real-Time	Yes - capture desktop, RTSP feeds, trigger alerts	Yes - watch agents work live, get webhook alerts
Search	Search by speech, scenes, metadata with playable clips	Natural language search with timestamped results
Platform	Any OS (macOS, Linux, Windows) - works with any skill-compatible agent	Any platform OpenClaw supports (requires Node.js)
Language	Python 3.9+	Node.js 18+

Next Steps

Capture SDK Overview

Deep dive: channels, permissions, client code, and event handling

Real-time Context

How real-time indexing and search works

AI Copilot Examples

Explore more AI copilot projects and use cases

Quickstart

Try desktop perception with a hosted OpenClaw agent

Start Here

Core Concepts

Ingest

Understand

Act

Automate

Open Source Frameworks

For Coding Assistants

For Autonomous Agents

Prerequisites

VideoDB Skills

VideoDB Skills on GitHub

What It Does

Why Use It

Installation

Setup

Quick Start

Capabilities

OpenClaw Monitoring

OpenClaw Monitoring on GitHub

What It Does

Why Use It

Prerequisites (OpenClaw Specific)

Installation

Setup

Quick Start

CLI Commands

Try Without Setup

Which Skill Should I Use?

Next Steps

Capture SDK Overview

Real-time Context

AI Copilot Examples

Quickstart

Start Here

Core Concepts

Ingest

Understand

Act

Automate

Open Source Frameworks

For Coding Assistants

For Autonomous Agents

​Prerequisites

​VideoDB Skills

VideoDB Skills on GitHub

​What It Does

​Why Use It

​Installation

​Setup

​Quick Start

​Capabilities

​OpenClaw Monitoring

OpenClaw Monitoring on GitHub

​What It Does

​Why Use It

​Prerequisites (OpenClaw Specific)

​Installation

​Setup

​Quick Start

​CLI Commands

​Try Without Setup

​Which Skill Should I Use?

​Next Steps

Capture SDK Overview

Real-time Context

AI Copilot Examples

Quickstart

Prerequisites

VideoDB Skills

What It Does

Why Use It

Installation

Setup

Quick Start

Capabilities

OpenClaw Monitoring

What It Does

Why Use It

Prerequisites (OpenClaw Specific)

Installation

Setup

Quick Start

CLI Commands

Try Without Setup

Which Skill Should I Use?

Next Steps