Agentic Vision via Gemini's native Code Execution sandbox. Use for spatial grounding, visual math, and UI auditing.
Data sourced from ClawHub. View on ClawSkills
Select your agent
Option 1: Install via CLI (recommended)
Recommended (no pre-install needed)
npx clawhub@latest --dir ~/.claude/skills install vision-sandboxOr via clawhub CLI (if already installed)
clawhub --dir ~/.claude/skills install vision-sandboxβ οΈ Requires Node.js 18+. No Node? Use Option 2 below to download the ZIP instead. Install Node.js β
Option 2: Manual install (no Node required)
Download the ZIP, extract it, and place the folder at the path below. Restart your agent to activate.
Install path
~/.claude/skills/vision-sandbox/π‘Extract and place the folder at the path above, then restart your agent.
Category
π»Developer & DevOpsPlatforms
What Vision Sandbox can do for your AI workflow
Agentic vision via gemini's directly from your Claude conversation
Works across Claude, Cursor, OpenClaw β install once, use everywhere
Trusted by 5,658+ developers worldwide
One-command installation β no complex setup required
Combine with other skills to build powerful multi-step AI workflows
Try these prompts with your AI agent after installing Vision Sandbox
Help me get started with Vision Sandbox
Explains what Vision Sandbox does, walks through the setup, and runs a quick demo based on your current project
Use Vision Sandbox to agentic Vision via Gemini's native Code Execution sandbox
Invokes Vision Sandbox with the right parameters and returns the result directly in the conversation
What can I do with Vision Sandbox in my developer & devops workflow?
Lists the top use cases for Vision Sandbox, with example commands for each scenario
Guides & tutorials for AI skills
The 7 AI Skills Every Software Developer Should Have Installed in 2026
After testing dozens of developer-focused AI skills, these are the seven that have proven genuinely useful across different tech stacks and workflows β not just impressive demos, but tools that hold up under daily use.
MCP Skills vs Native Claude Tools: What's the Difference and When to Use Each
Claude comes with built-in capabilities, but MCP skills extend it in ways the base model can't. Here's a clear breakdown of what each type of tool is good for, with real examples of when to reach for a skill versus relying on Claude's native abilities.
Vision Sandbox extends your AI assistant with the ability to agentic Vision via Gemini's native Code Execution sandbox. Use for spatial grounding, visual math, and UI auditing. Rather than leaving your conversation to handle this manually, you can ask your Claude agent directly β and it will take care of the task end-to-end, using Vision Sandbox as its underlying capability.
Vision Sandbox works across Claude, Cursor, OpenClaw through the Model Context Protocol (MCP) β an open standard that lets AI clients share tools and skills without lock-in. Because MCP is platform-agnostic by design, you install Vision Sandbox once and it becomes available across all your AI clients. Whether you're working in Claude for focused sessions or Cursor for integrated workflows, the skill behaves consistently.
Vision Sandbox installs like any other MCP skill: drop the folder into `~/.claude/skills/vision-sandbox/` for global access, or `.claude/skills/vision-sandbox/` to keep it scoped to one project. After a quick restart of Claude, you can trigger it explicitly with `/vision-sandbox`, or let the AI decide when it's the right tool for your request.
Vision Sandbox has been installed 5,658 times, making it one of the more actively used skills in the Developer & DevOps category. The install rate suggests it solves a real, recurring need rather than a niche edge case. Like all skills on DiscoverAISkills, it is free to install and use. The broader AI skills ecosystem continues to expand as developers contribute new capabilities across categories like developer tools, data analysis, writing, automation, and more.
Place the skill folder at ~/.claude/skills/vision-sandbox/ for personal use (all projects), or .claude/skills/vision-sandbox/ for project-specific use. Restart your AI client, then invoke with /vision-sandbox or let the AI discover it automatically.
Vision Sandbox supports Claude, Cursor, OpenClaw. It integrates seamlessly with these AI platforms to extend their capabilities.
Vision Sandbox is free to install. Check the repository for licensing information.
Agentic Vision via Gemini's native Code Execution sandbox. Use for spatial grounding, visual math, and UI auditing.
Vision
Resize, crop, convert, and optimize images using ImageMagick. Use when processing photos, converting formats (PNG/WebP), compressing size, or adding watermarks.
Vision Tagger
Tag and annotate images using Apple Vision framework (macOS only). Detects faces, bodies, hands, text (OCR), barcodes, objects, scene labels, and saliency re...
Vision Bot
Describe images, detect objects, extract text, and analyze webpages. Pass any image URL directly in your task. Responds in your language.
Automate my developer & devops tasks using Vision Sandbox
Identifies repetitive steps in your workflow and sets up Vision Sandbox to handle them automatically
Vision Sandbox is categorized under Developer & DevOps. These skills help AI agents perform specialized tasks in this domain.
Vision Recognition Ocr
Vehicle/animal/plant recognition plus OCR for screenshots, photos, invoices, and tables. Use when users ask Vehicle/animal/plant recognition plus OCR for screenshots, photos, invoices, and tables. Supports local path, URL, and...