#test-automation

AI Testing Agent Framework · 16 experts + 32 skills + 49 utils · Multi-LLM (Claude/OpenAI/Qwen/etc) · MCP-native · Open-source · Learn-while-using

Autonomous Web Agent Toolkit 2026 - AI Browser Automation for Testing & Scraping

Your development workspace inside GPT. A local Codex App for projects, worktrees and managed test evidence, with web and desktop access.

Checks whether a test-count claim is actually true - in a commit message, or in what your coding agent just told you. Runs the suite and compares. pytest, vitest, jest. Pre-commit hook, Claude Code plugin, or CLI. If no claim was made, it does nothing.

Turn failing pytest runs into structured repair reports: failure parsing, root-cause diagnosis, flaky detection, dry-run fix diffs, and an optional LLM layer. 把失败的 pytest 运行转化为结构化修复报告。

AI-powered test automation framework: plain-English user story → executable, self-healing test suite (Claude AI + Playwright + RestAssured + Allure)

Local TUI Agent for iPhone real-device and simulator testing: understand iOS projects, drive real devices, collect evidence, analyze failures, output reports.

Make an AI agent's 'done' mean 'here is the command output that proves it.' Deterministic, LLM-free verification for AI coding agents: sealed plans, SHA-256 hash-chained evidence, STRIPS/PDDL reachability, and a fail-closed completion gate.

Find Rust test-oracle gaps before mutation testing: static RIPR evidence for CI, editors, and agents.

Reusable Claude Code skills for test automation workflows

On this task an LLM did not beat free deterministic clustering. Clustering is worth +60.6 macro F1 over the majority floor at zero cost; adding claude-opus-5 cost 11.9 macro F1 and $0.31. Measured against a published corpus. Project 1 of an AI-in-QA portfolio.

NAC v1.0 -- Navegabilidad Automatica Compliance. A design norm that makes UIs navigable by AI agents, voice assistants, RPA bots and automated test runners without source-code access.

AI-powered Quality Engineering Platform built with FastAPI, React, PostgreSQL, and Docker for requirement analysis, API test generation, and automation failure analysis.

Claude Code skill for Appium mobile UI automation: generates Appium 3 + WebdriverIO + Jest/TypeScript suites for Android and iOS (native, React Native, Flutter, hybrid) using a 4-tier Locators/Pages/Data/Specs model, with a stage gate that enforces finished, verified modules.

GitHub Action that groups failed tests by root cause and explains them on the PR

Claude Code skill for Appium mobile UI automation: generates Appium 3 + WebdriverIO + Jest/TypeScript suites for Android and iOS (native, React Native, Flutter, hybrid) using a 4-tier Locators/Pages/Data/Specs model, with a stage gate that enforces finished, verified modules.