Automates browser interactions for web testing, form filling, screenshots, and data extraction.
SkillScore100Maintained
Automatic
◆QA & Test Engineering pack
Last verified 8/18/2026
What it changes
Passed 22 of 22 test cases with the skill, and 9 of 22 without it.
Without skill41%
With skill100%
Checks it passed that the model alone missed
Uses set device subcommand for device emulation
Uses frame main to switch back to top-level context
Applies set media with dark and reduced-motion options
and 18 more in the full report
13 fixed9 passed either way0 still failing0 broke
Pass-rate lift
+59 pp
Tokens
+91%
Agent turns
0%
Response time
-67%
Model gemini-3.6-flashMeasured 8/18/2026v122 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 13
Prompt
How do I capture a full-page screenshot saved to 'full.png' and export the page as a PDF file named 'output.pdf' via browser automation CLI?
What was checked, without and with the skill
Checked
Without skill
With skill
Uses screenshot subcommand with --full flag and path target
Missed
Passed
Uses pdf subcommand specifying PDF output file path
Passed
Passed
case-18 · gemini-3.6-flash · 8/18/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md350 lines9 files
Browser Automation with agent-browser
Quick start
agent-browser open <url> # Navigate to page
agent-browser snapshot -i # Get interactive elements with refs
agent-browser click @e1 # Click element by ref
agent-browser fill @e2 "text" # Fill input by ref
agent-browser close # Close browser
Core workflow
Navigate: agent-browser open <url>
Snapshot: agent-browser snapshot -i (returns elements with refs like @e1, @e2)
Interact using refs from the snapshot
Re-snapshot after navigation or significant DOM changes
Commands
Navigation
agent-browser open <url> # Navigate to URL (aliases: goto, navigate)
# Supports: https://, http://, file://, about:, data://
# Auto-prepends https:// if no protocol given
agent-browser back # Go back
agent-browser forward # Go forward
agent-browser reload # Reload page
agent-browser close # Close browser (aliases: quit, exit)
agent-browser connect 9222 # Connect to browser via CDP port
Snapshot (page analysis)
agent-browser snapshot # Full accessibility tree
agent-browser snapshot -i # Interactive elements only (recommended)
agent-browser snapshot -c # Compact output