What problem does it solve? Manually verifying that a pull request's UI changes actually work in a browser is slow and often skipped, letting visual regressions slip through. This Skill automates that verification: it boots the app, drives the changed surfaces through a real browser, captures screenshots, and produces a pass/fail report — all without modifying source code. ## Core Features & Use Cases - Browser-based UI verification: Derives a scoped QA scenario from the PR diff, drives the app through a configured browser provider, and captures a screenshot at every checkpoint. - PR and local modes: With a tracker configured it claims the PR, enforces a review-first gate, and posts inline screenshot evidence as a PR comment; without one it verifies the current worktree and writes artifacts locally. - Conservative label and lock management: Claims and releases PR locks with stale-lock recovery, applies qa-approved or qa-failed labels only via explicit opt-in flags, and never edits source, pushes, or merges. - Use Case: A reviewer receives a PR changing a checkout form. Run this Skill with the PR number to get a comment containing step-by-step screenshots proving the form renders, submits, and handles errors correctly, plus a follow-up test scenario when no browser-level test exists. ## Quick Start Run the om-auto-qa-pr skill with a PR number to verify its UI changes in a browser and post screenshot evidence to the pull request.
