Coordinate autonomous UI tests across web app routes with batched execution and bug reporting.
npx skills add https://github.com/visual-z/agent-test --skill agent-test
Please help me install this Agent Skill. Skill: agent-test Source: https://github.com/visual-z/agent-test/tree/main Command: npx skills add https://github.com/visual-z/agent-test --skill agent-test
The skill automates end-to-end autonomous UI testing of web applications by coordinating route discovery, batched test execution, screenshot capture, and bug reporting through a Ralph Loop harness.
Kick off an autonomous UI test on your project to automatically discover routes, run batched DFS tests, capture screenshots, and generate final reports.
High-intent search queries and answers about installing and using this skill.
You can automate autonomous UI testing by using a Ralph Loop harness to coordinate route discovery, batched test execution, screenshot collection, and bug reporting across your web app. It runs parallel subagent tests with isolated browser sessions for comprehensive coverage.
A Ralph Loop harness is a testing framework that manages autonomous UI tests by implementing strict subagent lifecycles, global state management, and per-route action trees. It ensures test runs remain safe, restartable, and auditable across discovered application routes.
Automatic route discovery and testing is achieved by initiating an autonomous test run that maps available application paths and executes batched depth-first search tests. The system manages per-route action trees to track test progress and capture independent results.
Yes, interrupted UI test runs can be safely restarted and resumed because the system manages a global state and per-route action trees. This state management ensures that autonomous test execution remains auditable and recoverable across batched subagent lifecycles.
Yes, autonomous UI testing supports parallel execution by running batched subagent tests simultaneously, each utilizing isolated browser sessions. This approach ensures independent test results and comprehensive screenshot collection across multiple application routes.
Subagent lifecycles for UI testing require strict state management and external harness plugins to ensure safe and auditable runs. Without proper coordination of per-route action trees and global state, complex web app testing may encounter restartability issues.
raphaelchristiConfigure Harness Evolver, LangSmith, and baseline evaluations for Python projects.
databrickslabsInvestigate root causes through a structured 4-phase debugging workflow.
BrennonTWilliamsCreate project issues from natural language input or conversation context.
faizkhairiAutomate end-to-end testing and interactive browser verification with Playwright.
