Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →majiayu000/core-agent-browser
For fetching Rust/crate information, use this priority order:
Passed 20 of 22 test cases with the skill, and 8 of 22 without it.
and 24 more in the full report
13 fixed7 passed either way1 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
I need CLI commands to retrieve the current web page title and extract the visible text content from element reference `@e1` without taking a visual screenshot or running JavaScript scripts.
| Checked | Without skill | With skill |
|---|---|---|
| Specifies agent-browser get title to fetch page title | Missed | Passed |
| Specifies agent-browser get text @e1 to extract element content | Missed | Passed |
The instructions your model reads when the skill loads.
For fetching Rust/crate information, use this priority order:
Use agent-browser directly only when:
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
agent-browser open <url>agent-browser snapshot -i (returns elements with refs like @e1, @e2)agent-browser open <url> # Navigate to URL
agent-browser back # Go back
agent-browser forward # Go forward
agent-browser reload # Reload page
agent-browser close # Close browser
test cases passed, vs 8 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.