A specialized utility designed to bridge the gap between browser automation and user messaging by ensuring captured screenshots are successfully delivered to communication channels.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install browser-screenshot-send
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 browser-screenshot-send 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 Browser Screenshot Send?
The Browser Screenshot Send skill solves a critical friction point in AI agent workflows: the delivery of visual data. While standard browser tools can capture page states, the files often remain trapped on the local disk. This tool, a key component within the Openclaw Skills ecosystem, facilitates the active transmission of these media files directly to the end user.
By prioritizing the message tool over simple file reading, this skill ensures that screenshots are not just visible to the agent's internal context, but are actively pushed to external platforms like Slack, Discord, or Telegram. It is an essential addition for developers building reliable web scraping, UI testing, or automated reporting agents.
Browser Screenshot Send Use Cases
- Delivering visual confirmation of successful web scraping or form submissions.
- Providing real-time UI automation progress reports to remote team members.
- Page verification and debugging during complex multi-step web workflows.
- Visual regression testing and verification of layout changes.
- Generating and sharing visual documentation of automated research tasks.
How Browser Screenshot Send Works
- The agent initiates a browser action to capture a screenshot (e.g., full-page or element-specific).
- The system saves the resulting image to a temporary path within the media directory.
- Instead of simply reading the file, the agent uses the message tool with the specific media path provided.
- The Openclaw Skills infrastructure transmits the media file through the active conversation channel to the user.
Browser Screenshot Send Setup
To implement this workflow, ensure your environment has both the browser and message tools enabled. Use the following commands as a template for your agent:
# Step 1: Capture the page content
browser action=screenshot targetId=<page_id>
# Step 2: Use the returned MEDIA path to send the file
message action=send media=/root/.openclaw/media/browser/<uuid>.png
Browser Screenshot Send Data Schema & Taxonomy
| Data Type | Location / Format | Purpose |
|---|---|---|
| Source Path | /root/.openclaw/media/browser/<uuid>.png |
Temporary storage for raw captures. |
| Persistence | /workspace/media/screenshots/ |
Recommended directory for saving permanent logs. |
| Metadata | UUID-based filenames | Ensures unique identification for multiple concurrent sessions. |
| Integration | Channel-specific media objects | Formats data for delivery across diverse messaging APIs. |
Browser Screenshot Send Advanced Features
- Multi-channel delivery support for synchronized updates across different platforms.
- Workspace persistence workflows to move temporary browser media to long-term storage.
- Section-based cropping using canvas integration for handling extremely long full-page screenshots.
- Automated descriptive renaming patterns for better file organization within Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
Relay Logic & Wiring Helper
A specialized CLI utility for managing relay logic tasks, wiring diagrams, and electrical status tracking through structured JSON and CSV workflows.
PDF Parser Agent
A high-performance local agent that converts PDF documents into structured Markdown and JSON formats for seamless data ingestion.
Executive Function Support
A cognitive scaffolding system designed to act as an external brain for planning, sequencing, and managing the mental overhead of daily tasks.
Whimsical Design Skill
A creative-focused skill designed to push AI-generated interfaces beyond sterile corporate defaults toward warmth, personality, and tactile delight.
focusavatar
A command-line interface tool for generating AI digital human videos and querying task results via professional backend APIs.
AI Logo Generator
The AI Logo Generator leverages advanced artificial intelligence to transform text-based prompts into professional, high-resolution logos.
Featured*
