Agent Claude Code
An agent for generating test cases, with defined input rules, generation rules, output formatting, and JSON writing requirements.
An enterprise-grade E2E test automation skill system based on Claude Code. Covers the full loop from requirements documents to test cases, Playwright scripts, execution, and self-healing; V2 introduces a SQLite knowledge graph that explicitly links features, test cases, interfaces, rules, and workflows, supporting coverage analysis, impact regression, and dual-track Sprint iterations.
Agent Claude Code
An agent for generating test cases, with defined input rules, generation rules, output formatting, and JSON writing requirements.
Agent Claude Code
An agent that records selectors for a specified module and creates Playwright end-to-end test scripts. Playwright is a tool for controlling a browser in automated tests.
Agent Claude Code
An agent that runs Playwright end-to-end tests, examines failures, and automatically fixes them. End-to-end tests check a complete user flow through an application.
Agent Claude Code
A specialist for checking end-to-end tests, which test a complete user flow, against the results those tests are meant to verify.
Agent Claude Code
A knowledge-graph helper agent that runs a Bash script to build an index, perform five queries, and request confirmation before applying changes. It returns JSON for the main conversation to use.
Agent Claude Code
A browser-based exploration agent that examines system pages and creates Markdown files describing discovered functions. It can explore everything or a chosen module.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: