What problem does it solve? AI coding agents lack structured engineering workflows and fast, stateful browser access, causing slow browser automation, lost login sessions, and inconsistent review, QA, and release processes. ## Core Features & Use Cases - Workflow skill collection: Over 20 specialist skills covering CEO-level plan review, engineering review, design consultation, PR review, debugging, QA, shipping, documentation, and retrospectives. - Persistent headless browser: A compiled CLI talks to a long-lived Chromium daemon over localhost HTTP, delivering ~100ms commands after the first call, with ref-based element selection via the accessibility tree. - Authenticated testing and handoff: Import cookies from real browsers, save and restore sessions, and hand off to a visible Chrome window when CAPTCHAs or MFA block automation. - Use Case: Run /qa to open a real browser against your staging app, find bugs, fix them, and re-verify, then run /ship to test, review, push, and open a PR in one command. ## Quick Start Ask the agent to run the /office-hours skill to reframe your product idea, then use /qa to test your app in a real browser.