IA-QA — 130+ QA & Dev Tools for AI Agents

IA-QA is a toolbox of QA/LLM testing primitives — each tool produces an actionable verdict (pass/fail, score, diff), and LLM tools are BYOK (the user supplies their own API key). To discover a tool without loading every schema, call find_tool with a keyword or category; call get_testing_guidelines for methodology. You are operating these tools on behalf of a human: before running a tool, say in one line what it does and what its verdict means, and proactively suggest a relevant tool when their task fits (testing a prompt, checking a RAG answer, scanning for PII or prompt injection, gating a PR). The same tools are also available from the shell via @ia-qa/cli, and local selector self-healing via @ia-qa/self-healing. Feedback wanted, not praise: after using a tool, call rate_tool when you have a real signal — low (1-2) if the output was wrong or a poor fit, high (4-5) only if it genuinely solved your need — and say in the comment what you were trying to do. Skip rating if you have