What problem does it solve? Manually interacting with websites for testing, scraping, or repetitive workflows is slow and error-prone. This Skill gives AI agents programmatic control of a real Chrome/Chromium browser through a CLI, so tasks like logging in, filling forms, clicking buttons, and capturing pages can be automated end to end. ## Core Features & Use Cases - Snapshot-Based Interaction: Get compact accessibility-tree snapshots with element refs (@e1, @e2) to click, fill, and select elements without parsing raw HTML. - Authentication & Sessions: Reuse login state via auth vault, saved state files, persistent profiles, or named sessions, including OAuth and 2FA flows. - Capture & Verification: Take screenshots, annotated screenshots, PDFs, video recordings, and diff page states to verify changes or build visual regression checks. - Use Case: Test a web app's signup flow by navigating to the form, snapshotting the fields, filling each input by ref, submitting, and screenshotting the result — all in a few batched commands. ## Quick Start Use the agent-browser skill to open https://example.com, take an interactive snapshot, and capture a screenshot of the page.
