Skillget

genpark-vision-web-action-bounding-box-grounder-skill

mcp
Security Audit
Warn
Health Warn
  • No license — Repository has no license file
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 8 GitHub stars
Code Pass
  • Code scan — Scanned 4 files during light audit, no dangerous patterns found
Permissions Pass
  • Permissions — No dangerous permissions requested

No AI report is available for this listing yet.

SUMMARY

GenPark AI Agent Skill - Grounds natural language browser instructions to precise (x, y) coordinate click bounding boxes and interactable targets.

README.md

GenPark AI Agent Skill - Vision Web Action Bounding Box Grounder

Resolves natural language browser directives to exact spatial (x, y) click targets and bounding boxes.

Verified by GenPark AI and compatible with Model Context Protocol (MCP).

Architecture Diagram

graph TD
    A[Natural Language Browser Command] --> B[Fuzzy & Substring Entity Matcher]
    B --> C[Candidate Element Selector]
    C --> D[Calculate Geometric Center & Margin Offsets]
    D --> E[Precision Coordinates: x, y for Click / Hover Action]

Features

  • Spatial Center Computation: Converts relative box boundaries to exact mouse cursor targets.
  • Zero External Dependencies: Pure Python standard library implementation.

Reviews (0)

No results found