From yutori
Automates browser tasks like form filling, data extraction, and multi-step web workflows using Yutori Navigator agent. Useful for website interactions requiring clicking, typing, or navigation.
How this skill is triggered — by the user, by Claude, or both
Slash command
/yutori:03-browse [task description] [starting URL][task description] [starting URL]The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Help the user automate browser-based tasks using Yutori's Navigator agent.
Help the user automate browser-based tasks using Yutori's Navigator agent.
Understand the task
Define the task clearly
Start the browsing task
Use run_browsing_task with:
task: Clear natural language instructionsstart_url: The URL to begin browsingmax_steps: 25 (default) to 100 for complex flowsrequire_auth: true: For login forms or other authenticated workflowsbrowser: "local": When the task should run through Yutori Local with the user's desktop sessionoutput_fields: For structured data extraction (e.g., ["name", "price", "url"])webhook_url: HTTPS URL for completion notificationwebhook_format: scout (default), slack, or zapierPoll for results
get_browsing_task_result to check statusReview and validate
$ARGUMENTS
npx claudepluginhub yutori-ai/yutori-mcp --plugin yutoriAutomates browser tasks with AI: navigate sites, fill forms, extract structured data, log in with credentials, and build reusable workflows. Use for web scraping, UI interactions without fixed selectors.
Drives a real browser for one-off tasks: navigate, click, fill, scrape, screenshot, and return results. Use for quick automation, scraping, form filling, or checking a site without recording.
Automates filling web forms, logins, registrations, checkouts, multi-step wizards using openbrowser-ai for browser control with indexed selectors for inputs, dropdowns, checkboxes.