QA projects being shaped for production.

Reusable AI skills and deterministic behavior evaluations for everyday software QA.

A collection of detailed QA workflow skills with a safe installation lifecycle and repeatable evaluation system.

Automation lab for repeatable QA checks and product validation.

Needs release hardening and a clear first workflow before production deployment.

Visual workflow builder for QA automation — compose test and verification flows without code.

A visual canvas for assembling QA automation flows, turning manual verification steps into repeatable, shareable pipelines.

Multi-screen QA grid for visual comparison and review workflows.

Strong QA tool concept. Needs deployment scope, fixture data, and smoke tests before public release.

A broader QA project space for testing workflows and learning.

Keep in QA projects while the first production feature set and release boundary are narrowed.

AI task planner for QA — turns requirements, user stories, and bug reports into structured test and regression plans.

Converts product requirements, user stories, bug reports, and release notes into structured QA execution and regression plans.

AI QA agent that clicks through your website like a real human — API key, Claude Code/Codex plan, or local Ollama.

An autonomous end-to-end QA agent that drives a real browser through your site the way a human tester would, powered by an API key, your existing Claude Code/Codex plan, or a local Ollama model. Built on Playwright.

Generic website uptime monitor — point at any URL, capture full-page screenshots, write status.json, optional Slack alerts.

A Node + Playwright uptime monitor you point at any URL: it captures full-page screenshots, writes a machine-readable status.json, and can post Slack alerts. Ships with 9 offline tests plus a live integration check.