An intelligent vision-based agent that monitors video streams to automatically capture, extract, and organize slide content into structured Markdown notes.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install slide-sniper
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install slide-sniper using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Slide Sniper?
Slide Sniper is a specialized background agent designed for Openclaw Skills that functions as a tireless digital teaching assistant. It is specifically built for scenarios where users are watching non-downloadable content such as live webinars, online courses, or virtual conferences. By leveraging Computer Use - Vision technology, the skill monitors the screen in the background, identifying exactly when a presenter transitions to a new slide.
This tool eliminates the distraction of manual note-taking, allowing you to focus on the speaker while the agent handles the heavy lifting of documentation. It bridges the gap between video consumption and knowledge management within the Openclaw Skills ecosystem by creating high-fidelity, searchable archives of visual presentations without requiring user intervention.
Slide Sniper Use Cases
- Capturing key insights from live technical webinars or corporate presentations where slides are not shared.
- Automatically generating study guides from online video course platforms.
- Archiving visual data from live trading streams or data-heavy research presentations.
- Creating structured documentation from software demonstrations and walkthroughs.
How Slide Sniper Works
- The agent identifies the primary video playback window or full-screen stream to establish a baseline visual frame.
- It initializes a local workspace in the Documents directory, creating a timestamped Markdown or Word file for the session.
- Every 5 seconds, the agent utilizes vision models to perform a structural comparison between the current screen and the baseline frame.
- It intelligently ignores minor visual noise, such as mouse movements or speaker video overlays, triggering only when a significant slide change is detected.
- Upon a slide flip, the agent captures a high-definition screenshot and performs OCR to extract core titles and bullet points.
- The extracted text is cleaned of metadata (like page numbers) and appended to the note file alongside the image path, resetting the baseline for the next cycle.
Slide Sniper Setup
Ensure your Openclaw environment has the necessary filesystem permissions enabled for the local Documents folder. To manually prepare the storage environment for this skill, you can use the following command:
mkdir -p ~/Documents/Notes/SlideSniper
Once configured, simply activate the agent via voice or text command within any Openclaw Skills compatible interface by saying 'Start slide sniper mode' or 'Monitor this live stream and take notes.'
Slide Sniper Data Schema & Taxonomy
Slide Sniper organizes information using a structured filesystem approach to ensure compatibility with various note-taking applications:
| Data Type | Storage Location | Description |
|---|---|---|
| Note Files | ~/Documents/Notes/SlideSniper/*.md |
Markdown files named by date and time. |
| Image Assets | ~/Documents/Notes/SlideSniper/assets/ |
High-resolution screenshots extracted from the video. |
| OCR Metadata | Embedded in Markdown | Extracted slide headers and body text formatted with proper hierarchy. |
| Baseline Cache | Temporary Memory | Used for real-time frame comparison during the session. |
Slide Sniper Advanced Features
- Smart structural detection that focuses on main content areas while ignoring floating chat windows or pop-up notifications.
- Privacy-centric filtering to ensure only relevant presentation areas are captured and analyzed.
- High-fidelity OCR cleaning that strips redundant headers, footers, and page numbers for a clean note-taking experience.
- Silent background operation that does not interfere with the user's mouse or keyboard during active monitoring.
- Local-first storage strategy ensuring all captured data and Openclaw Skills assets remain on the user's machine.
SKILL.md
Loading
Related Openclaw Skills
open-market-data
A unified command-line interface for querying free financial data across stocks, crypto, and macroeconomic indicators with automatic fallback routing.
twitter-openclaw
A comprehensive interface for AI agents to interact with Twitter/X, enabling tweet reading, posting, engagement, and timeline management.
Clawzembic
A zero-dependency efficiency auditor that provides Lighthouse-style grading and performance optimization for Openclaw Skills instances.
Gold Price Checker
An automated financial tracking tool providing real-time data on domestic and international gold markets, retail jewelry, and investment bars.
Task Watchdog
A digital guardian that monitors long-running computer tasks and automatically clears interfering popups to ensure uninterrupted completion.
Vibe Harvester
An intelligent visual assistant that automatically scrolls through image platforms to screen and download high-quality reference photos based on your aesthetic preferences.
Featured*
