AI tools for “qa”

Pie is an AI QA agent for web, iOS and Android apps. It tests every change like a real user, catches what breaks, and opens the fix as a PR.

Coval helps teams prove voice agents are ready with voice AI testing, production evals, and human QA across the full agent lifecycle.

BaseRock AI delivers agentic QA solutions for dev teams. Automate functional testing and business use case testing to eliminate risk and ship faster.

…and Dial record (call recording), dual-channel for QA, mid-call pause for PCI, Conference recording, and the ConversationRelay workaround. Use this skill whenever you need to capture call audio for compliance,…

…the developer's use case across coaching, compliance, QA, and routing to recommend the right Conversation Intelligence + Conversation Memory + TaskRouter architecture. Handles both "I want to add AI coaching to my…

Run the LinqAlpha setup flow — connection check, capability tour, default-source opt-in. Use ONLY when the user invokes /linq-alpha:setup or asks to set up or connect the LinqAlpha plugin; for questions about…

Choose and use LinqAlpha for institutional financial research involving company identity, fundamentals, estimates, ownership, prices, transcripts, disclosures, macro data, rates, FX, commodities, citations, or…

Delete the saved LinqAlpha default-source preference from Claude's memory. Use ONLY when the user invokes /linq-alpha:remove or asks to forget that preference; not for uninstalling the plugin or disconnecting the…

…Use this whenever the user wants a call-quality audit, a QA pass over recent calls, a "what's going wrong with this agent" review, or to find failed, unresolved, dropped, or otherwise problematic calls. Trigger on…

Print the exact marker string QA-SKILL-MARKER by running a shell command. Use this whenever the task is to emit the QA marker.

QA-test a website or web app and return a 1-5 quality score (5 = flawless, 1 = broken) with evidence. Use when the user wants to test, QA, evaluate, score, or "check how good" a site, page, flow, or app — including a…

…a rebuild, before shipping a release, or when asked to QA or debug such an app ("באג בקפסיטור", "לא עובד במכשיר"). It carries a catalog of WebView traps measured on real devices, and the recipe for driving the…

…silent failures. Use when the user asks for a bug hunt, a QA pass, a code health check, a crash investigation, or a review before submitting ("בדוק באגים", "תעשה QA"), and after a large change when nothing obvious is…

How the orchestrator dispatches Developer and QA subagents so a run's token cost stays bounded: a fresh subagent per round, a short deterministic handoff file, a context budget with a clean handoff, and bounded helpers…

Verify the running clone, perform auditable visual comparison and gap fixes, and finalize frontend completion.

…code, a pull request or Shopify preview theme, automated QA, and a started test. Use for "what should we A/B test", CRO or experiment ideas, building a specific test, implementing a test already found, or taking a…

…at small scale but fails at production scale, or fails a QA/validation recheck. Also for explicit symptoms — exploding, NaN/inf, zero, or subtly wrong gradients, suspected wp.Tape/backward issues, gradcheck failures…

…data — multi-level captions, structured descriptions, and QA pairs (MCQ, binary, open-ended) with reasoning traces, via VLM/LLM distillation. Use when the user wants to "create video training data", "generate video QA…

Execute QA test plans on Holoscan Sensor Bridge hardware. Reads a user-provided test document, filters tests by the user's setup, determines which tests can run automatically, executes them with pass/fail evaluation,…

…Applies to quantum programs and execution, AHS, OpenQASM, pulse control, reservations, notebooks, or Qiskit or PennyLane…