ai-qa

Awesome QA Skills — a bilingual (zh/en) AI testing Agent Skills library for Codex, Cursor, Claude Code, Kiro, OpenCode, and Trae. Ships 4 testing workflows and 25 testing-type skills (58 skill folders with language parity): independently installable, composable, and eval-ready with skill-up. Covers requirements, strategy, cases, API/performance/sec

AI-powered automated E2E testing. Just enter a URL — AI generates and runs test scenarios.

Multi-agent LangGraph app turning raw requirements into backlog-ready user stories, ACs, and test cases. Live Gemini-Flash CI eval gate + nightly N=10 adversarial regression.

Uses an LLM to evaluate the quality of test cases generated by another LLM

AI RAG evaluation project using Ragas. Includes RAG metrics (precision, recall, faithfulness), retrieval diagnostics, and prompt testing examples for fintech/banking LLM systems. Designed as an AI QA Specialist portfolio project.

Generates structured test cases (unit, integration, and e2e) from a plain-text feature description, using the OpenAI API (GPT-4o).

Local Python tool for evaluating LLM-generated QA findings with manual validation and false-positive analysis

An evaluation framework for LLM applications

AI/ML QA & LLM testing portfolio with API, UI, data quality, and demo app examples

AI-powered test suite generator.