browser-automation
Navigate the web, discover content, and interact with pages using a headless browser.
Installation
Follow the repository instructions for this skill and your agent. Review the files and dependencies before adding it to your workflow.
View source ↗GuidesSkill instructions
Browser Skill
Capabilities
- Navigate: Go to a URL and wait for it to load.
- Discover: Extract text content or data from the page.
- Screenshot: Capture visual proof of the page state.
- Interact: Click buttons, type text, and evaluate scripts.
Usage
- Use
browser.navigatefor simple "Go here and read this" tasks. - Use
browser.performfor complex multi-step workflows (e.g. Login -> Click -> Discover).
Constraints
- headless mode is always on.
- No audio/video playback.
- Heavy sites may timeout; usage of
waitsteps is encouraged.
Examples
Read the usage examples in the source repository.
View source ↗Source history
- Indexed on
- 2026-01-20
- Index updated
- 2026-01-26
- Branch
- main
Index and sync dates describe this directory. View the source repository for code history.
GitHub ↗chat Comments (0)
Sign in to join the discussion and leave a comment.
No comments yet. Be the first to share your thoughts!