A sophisticated agent skill that captures browser actions to generate replayable test scripts and visual HTML reports automatically.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install ui-test-agent
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 ui-test-agent 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 UI Automation Test Agent?
The UI Automation Test Agent is designed to transform natural language instructions into rigorous, automated web tests. By utilizing a record-then-report workflow, this skill enables an agent to perform real browser operations, capture visual evidence at every junction, and compile these actions into a structured session. As a key part of the Openclaw Skills library, it bridges the gap between manual exploration and automated regression testing.
This skill is particularly valuable for developers and QA engineers who need to document bugs or verify features without writing boilerplate automation code. It handles the complexities of browser interaction, screenshot management, and report generation, ensuring that every test run is transparent, reproducible, and easy to analyze.
UI Automation Test Agent Use Cases
- Automating repetitive UI regression tests for complex web applications.
- Generating comprehensive bug reports with step-by-step screenshot evidence for engineering teams.
- Creating cross-platform replayable scripts (Shell and Batch) to standardize testing environments.
- Validating user journeys and critical conversion paths using Openclaw Skills to ensure site reliability.
How UI Automation Test Agent Works
- The agent analyzes the user request to identify the target URL and specific functional steps like clicking, typing, or asserting text.
- It executes browser commands sequentially using the agent-browser CLI tool.
- After every action, it captures a screenshot of the current page state using the get_screenshot tool.
- Each step, including the command, status, and screenshot path, is recorded into a session.json file using a dedicated Python utility.
- Once the sequence is finished, the agent generates executable shell and batch scripts for future re-runs.
- Finally, it compiles all session data into a standalone HTML report with embedded Base64 images for easy sharing.
UI Automation Test Agent Setup
To utilize this skill, ensure the agent-browser CLI is installed and the skill files are placed in your local Openclaw Skills directory.
# Verify the skill directory exists
ls ~/.workbuddy/skills/ui-test-agent/scripts/
# Ensure Python dependencies for reporting are available
python --version
UI Automation Test Agent Data Schema & Taxonomy
The skill follows a strict organizational structure for test outputs to ensure clarity and metadata integrity:
| Component | File Path | Purpose |
|---|---|---|
| Session Data | session.json |
Primary manifest of all recorded actions and metadata. |
| Visual Evidence | screenshots/ |
Directory containing PNG images for every test step. |
| Replay Scripts | {test_name}.sh / .bat |
Executable scripts to replicate the test on different OS. |
| Structured Case | {test_name}.test.json |
JSON representation of the test steps for programmatic use. |
| Final Report | test_report.html |
Self-contained visual report with embedded Base64 screenshots. |
UI Automation Test Agent Advanced Features
- Resilience-focused recording that logs failures without interrupting the entire test sequence.
- Multi-format exports including shell scripts, batch files, and structured JSON for CI/CD integration.
- Portable HTML reports with zero external dependencies, making them ideal for attachment in Jira or GitHub issues.
- Seamless integration with the broader Openclaw Skills ecosystem for multi-step browser automation workflows.
SKILL.md
Loading
Related Openclaw Skills
Deprecated Skill
A legacy component within the ecosystem that has been retired and is no longer supported for active development workflows.
Iceberg Excavation
A deep-dive psychological analysis tool that transforms emotional triggers into profound self-awareness and systemic behavioral change.
Mortgage Rate Lookup
A comprehensive automation tool that scrapes and compares real-time mortgage rates from 13 lenders and national benchmarks.
Windows Browser Ops
A powerful remote automation tool for controlling Windows browsers to capture evidence and manage web-based workflows through Openclaw Skills.
Skill Creator
A professional toolkit for authoring, auditing, and packaging high-quality agent skills with a focus on executable precision.
Skill Forge
A specialized tool for generating automated test suites and SKILL.md files to evaluate and improve AI agent capabilities.
Featured*
