Menu
Agentic Vision via Gemini's native Code Execution sandbox. Use for spatial grounding, visual math, and UI auditing.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Comprehensive guide for building AI workflows, agents, and workforce systems with AgenticFlow. Use when designing workflows with various node types, configuring single agents, or orchestrating workforce collaboration patterns.
Navigate and understand codebases using agentlens hierarchical documentation. Use when exploring new projects, finding modules, locating symbols in large files, finding TODOs/warnings, or understanding code structure.
Expert guide for designing iOS, macOS, watchOS, tvOS, and visionOS apps following Apple Human Interface Guidelines. Use when building Apple platform apps or interfaces, implementing SF Symbols, designing with iOS components, following accessibility guidelines, or creating native Apple experiences. Covers design principles, patterns, components, typography, color, layout, navigation, and platform-specific conventions.
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
Complete guide for AI agents to participate in BotBowl Party — a virtual Super Bowl party for bots
A guide to build AI bots with Botpress's Agent Development Kit (ADK)
| name | Vision Sandbox |
| slug | vision-sandbox |
| version | 1.1.0 |
| description | Agentic Vision via Gemini's native Code Execution sandbox. Use for spatial grounding, visual math, and UI auditing. |
| metadata | {"openclaw":{"emoji":"🔭","primaryEnv":"GEMINI_API_KEY","requires":{"bins":["uv"],"env":["GEMINI_API_KEY"]}}} |
Leverage Gemini's native code execution to analyze images with high precision. The model writes and runs Python code in a Google-hosted sandbox to verify visual data, perfect for UI auditing, spatial grounding, and visual reasoning.
clawhub install vision-sandbox
uv run vision-sandbox --image "path/to/image.png" --prompt "Identify all buttons and provide [x, y] coordinates."
Ask the model to find specific items and return coordinates.
Ask the model to count or calculate based on the image.
Check layout and readability.
Solve visual counting tasks with code verification.
This skill is designed to provide Visual Grounding for automated coding agents like OpenCode.
vision-sandbox to extract UI metadata (coordinates, sizes, colors).gemini-3-flash-preview.