browser-forms

Automates complex browser form interactions including selects, checkboxes, uploads, and validated submissions.

2|Updated May 12, 2026

Search Tags:#browser automation #web scraping #form filling #file upload #visual verification #checkbox #select option

Ready to run

npx skills add https://github.com/tajo9128/BioDockify-Pharma-AI --skill browser-forms-tajo9128

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: browser-forms
Source: https://github.com/tajo9128/BioDockify-Pharma-AI/tree/main/plugins/_browser/skills/browser-forms
Command: npx skills add https://github.com/tajo9128/BioDockify-Pharma-AI --skill browser-forms-tajo9128

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Complex web forms with selects, checkboxes, radios, file uploads, contenteditable fields, and multi-step validation are error-prone to automate, and blind submissions often fail silently without visual confirmation. ## Core Features & Use Cases - Ref-Based Form Actions: Uses select_option, set_checked, upload_file, type, type_submit, and submit against stable element refs captured via browser:content and browser:detail. - Visual Verification: Combines browser:screenshot with vision_load to handle captcha-like UI, canvas content, hidden state, and layout-dependent validation. - Post-Submission Verification: Confirms results with browser:content, browser:state, or a fresh screenshot instead of assuming success. - Use Case: Filling a multi-step pharmaceutical data entry form with dropdown selections, file attachments, and a final visually verified submission. ## Quick Start Fill out the multi-step registration form on the current page, upload the required file, and verify the submission succeeded with a screenshot.

Frequently Asked Questions about browser-forms

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I automate filling complex web forms with file uploads?▼

Capture element refs with browser:content, inspect ambiguous fields with browser:detail, then use select_option, set_checked, type, and upload_file against those refs. Verify every file path exists before calling upload_file, and confirm submission with browser:state or a screenshot.

Should I use ref-based actions or coordinates for browser form automation?▼

Prefer ref-based form actions because they are stable across layout changes. Use coordinates only when no stable ref exists or the UI is intentionally canvas-like, such as drawing surfaces or captcha-style widgets.

How do I verify a browser form submission actually succeeded?▼

Check the result with browser:content or browser:state after submitting, or take an explicit browser:screenshot and load it with vision_load. Browser screenshots are not automatically added to model-visible history, so verification must be requested explicitly.

Why does file upload fail in automated browser forms?▼

Uploads fail when the file path is guessed or does not exist on disk. Always verify that every path exists before calling upload_file, and target the file input by its ref rather than coordinates.

Can browser automation handle captcha-like or canvas-based form elements?▼

Yes, for visual inspection: use browser:screenshot plus vision_load when layout, canvas content, or hidden state matters. This lets the model see the rendered page, since screenshots are not loaded into history automatically.