A browser automation skill for capturing screenshots and performing visual reconnaissance to analyze pages for security indicators.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install screenshot-visual
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 screenshot-visual 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 Screenshot + Visual Analysis?
The Screenshot + Visual Analysis skill is a powerful extension designed for browser automation and visual reconnaissance. By leveraging Playwright, this tool enables AI agents to automatically navigate to target URLs, capture high-quality screenshots, and inspect page layouts for visual anomalies or configuration issues. As part of the growing ecosystem of Openclaw Skills, it helps developers and security researchers build automated pipelines to visually audit their web surfaces.
By combining browser automation with structural analysis, the skill collects page sources, security headers, and visual layouts to flag potentially exposed panels, login forms, or debugging interfaces. It provides an efficient way to maintain a visual inventory of active web assets without manual overhead.
Screenshot + Visual Analysis Use Cases
- Visual Asset Inventory: Automatically capture and organize screenshots of web assets to maintain a visual record of your attack surface.
- Exposed Panel Detection: Identify login interfaces, admin panels, and debug dashboards that should not be publicly accessible.
- Security Header Auditing: Inspect visual clues alongside response headers to find missing security configurations.
- Automated Bug Bounty Recon: Streamline the initial reconnaissance phase of web assessments using intelligent Openclaw Skills.
How Screenshot + Visual Analysis Works
- Target Navigation: The skill uses browser automation to navigate to the specified target URL.
- Capture & Collection: It captures a full-page or viewport screenshot and gathers page source code, security headers, and active JavaScript endpoints.
- Visual & Contextual Analysis: The agent analyzes the visual layout and collected metadata to flag interesting elements like form fields, tech stacks, or error messages.
- Structured Reporting: It saves the structured results locally, outputting both the PNG image and a detailed JSON metadata file for further review.
Screenshot + Visual Analysis Setup
To get started with this component from the Openclaw Skills library, ensure you have Node.js and the necessary browser binaries installed:
# Install the Playwright MCP package
npm install -g @playwright/mcp
# Install the required browser binaries
npx playwright install chromium
Run the visual analysis script against any target URL:
node scripts/screenshot.js https://example.com
Screenshot + Visual Analysis Data Schema & Taxonomy
The skill structures its output systematically within the workspace to facilitate easy integration and automated analysis. Each execution generates files under the screenshots/ directory:
| File Path | Description |
|---|---|
screenshots/<domain>/<path>-<timestamp>.png |
The captured full-page visual screenshot of the target. |
screenshots/<domain>/<path>-<timestamp>.json |
Metadata file containing response headers, page title, and captured console logs. |
Screenshot + Visual Analysis Advanced Features
- Custom Viewports: Configure the browser viewport size to test responsive layouts or simulate mobile devices.
- Full-Page Captures: Toggle between standard viewport screenshots and full-height page renders.
- Local-First Privacy: All screenshots and extracted metadata are saved locally on your machine, ensuring complete privacy during assessments.
- Agentic Workflows: Integrate seamlessly with other Openclaw Skills to trigger visual audits based on discovered subdomains or ports.
SKILL.md
Loading
Related Openclaw Skills
Audio Transcribe
A local, privacy-first audio transcription skill that converts speech to text, subtitles (SRT), or JSON using OpenAI's Whisper model.
AI-Native Founder Playbook
A bilingual, vendor-neutral operating playbook designed to convert AI-native startup ideas into stage-appropriate strategic experiments and automated agent workflows.
Nuclei Analysis
A utility to parse raw Nuclei vulnerability scan results, filter noise, and generate prioritized markdown reports.
Morning Briefing
An automated workflow that aggregates A-share market trends and RSS news into custom Markdown digests and WeChat push notifications.
Comic Create
An AI-powered pre-production assistant that converts unstructured creative ideas into production-ready comic scripts, storyboards, and character designs.
iFlow Search
Equip your AI agents with real-time web search, image discovery, and LLM-friendly webpage extraction capabilities using the iFlow Search API.
METADATA
Featured*
