Compound Engineering Browser Test
Skill Verified ActiveRun browser tests on pages affected by current PR or branch
To enable developers to automatically run end-to-end browser tests on affected pages for current PRs or branches, ensuring code quality and stability.
Features
- Run browser tests on PR/branch changes
- Integrates with `agent-browser` CLI
- Handles headed or headless test execution
- Detects and maps affected files to routes
- Manages local development server startup and port detection
Use Cases
- Automate regression testing for a new feature branch
- Verify UI stability after code modifications
- Ensure visual consistency across key pages before merging
- Integrate browser testing into CI/CD pipelines
Non-Goals
- Performing general web scraping
- Replacing full end-to-end testing frameworks
- Managing remote browser environments
Workflow
- Verify agent-browser installation
- Ask user for headed or headless mode (if not pipeline mode)
- Determine test scope (PR, current branch, or named branch)
- Map changed files to testable routes
- Detect and claim a free port for the dev server
- Start dev server if not running (pipeline mode only)
- Navigate to and test each affected page
- Perform human verification for critical flows
- Handle and document test failures
- Present a summary of test results
Practices
- Automated Testing
- CI/CD Integration
- Browser Automation
Prerequisites
- Local development server running
- `agent-browser` CLI installed
- Git repository with changes to test
Installation
First, add the marketplace
/plugin marketplace add EveryInc/compound-engineering-plugin/plugin install compound-engineering@compound-engineering-pluginQuality Score
VerifiedTrust Signals
Similar Extensions
Agent Browser
100Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
Telegram Crabbox E2e Proof
100Use when reviewing, reproducing, or proving OpenClaw Telegram behavior with a real Telegram user on Crabbox, including PR review workflows that need an agent-controlled Telegram Desktop recording, TDLib user-driver commands, Convex-leased credentials, WebVNC observation, and motion-trimmed artifacts.
AutoBrowse
100Self-improving browser automation via the auto-research loop. Iteratively runs a browsing task, reads the trace, and improves the navigation skill (strategy.md) until it reliably passes. Supports parallel runs across multiple tasks using sub-agents. Use when you want to build or improve browser automation skills for specific website tasks.
Openclaw Testing
100Choose, run, rerun, or debug OpenClaw tests, CI checks, Docker E2E lanes, release validation, and the cheapest safe verification path.
Crabbox
100Use Crabbox for OpenClaw remote validation across Linux, macOS, Windows, and WSL2. Default to Blacksmith Testbox for broad Linux proof; includes direct Blacksmith and owned AWS/Hetzner fallback notes when Crabbox fails.
NotebookLM Skill
99Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.