{ "schemaVersion": "1.0", "item": { "slug": "vision-sandbox", "name": "Vision Sandbox", "source": "tencent", "type": "skill", "category": "AI ę™ŗčƒ½", "sourceUrl": "https://clawhub.ai/johanesalxd/vision-sandbox", "canonicalUrl": "https://clawhub.ai/johanesalxd/vision-sandbox", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/vision-sandbox", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=vision-sandbox", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "AGENTS.md", "CONTRIBUTING.md", "README.md", "SKILL.md", "main.py", "pyproject.toml" ], "primaryDoc": "SKILL.md", "quickSetup": [ "Download the package from Yavira.", "Extract the archive and review SKILL.md first.", "Import or place the package into your OpenClaw setup." ], "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-30T16:55:25.780Z", "expiresAt": "2026-05-07T16:55:25.780Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/vision-sandbox" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] }, "downloadPageUrl": "https://openagent3.xyz/downloads/vision-sandbox", "agentPageUrl": "https://openagent3.xyz/skills/vision-sandbox/agent", "manifestUrl": "https://openagent3.xyz/skills/vision-sandbox/agent.json", "briefUrl": "https://openagent3.xyz/skills/vision-sandbox/agent.md" }, "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "Vision Sandbox šŸ”­", "body": "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." }, { "title": "Installation", "body": "clawhub install vision-sandbox" }, { "title": "Usage", "body": "uv run vision-sandbox --image \"path/to/image.png\" --prompt \"Identify all buttons and provide [x, y] coordinates.\"" }, { "title": "šŸ“ Spatial Grounding", "body": "Ask the model to find specific items and return coordinates.\n\nPrompt: \"Locate the 'Submit' button in this screenshot. Use code execution to verify its center point and return the [x, y] coordinates in a [0, 1000] scale.\"" }, { "title": "šŸ§® Visual Math", "body": "Ask the model to count or calculate based on the image.\n\nPrompt: \"Count the number of items in the list. Use Python to sum their values if prices are visible.\"" }, { "title": "šŸ–„ļø UI Audit", "body": "Check layout and readability.\n\nPrompt: \"Check if the header text overlaps with any icons. Use the sandbox to calculate the bounding box intersections.\"" }, { "title": "šŸ–ļø Counting & Logic", "body": "Solve visual counting tasks with code verification.\n\nPrompt: \"Count the number of fingers on this hand. Use code execution to identify the bounding box for each finger and return the total count.\"" }, { "title": "Integration with OpenCode", "body": "This skill is designed to provide Visual Grounding for automated coding agents like OpenCode.\n\nStep 1: Use vision-sandbox to extract UI metadata (coordinates, sizes, colors).\nStep 2: Pass the JSON output to OpenCode to generate or fix CSS/HTML." }, { "title": "Configuration", "body": "GEMINI_API_KEY: Required environment variable.\nModel: Defaults to gemini-3-flash-preview." } ], "body": "Vision Sandbox šŸ”­\n\nLeverage 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.\n\nInstallation\nclawhub install vision-sandbox\n\nUsage\nuv run vision-sandbox --image \"path/to/image.png\" --prompt \"Identify all buttons and provide [x, y] coordinates.\"\n\nPattern Library\nšŸ“ Spatial Grounding\n\nAsk the model to find specific items and return coordinates.\n\nPrompt: \"Locate the 'Submit' button in this screenshot. Use code execution to verify its center point and return the [x, y] coordinates in a [0, 1000] scale.\"\nšŸ§® Visual Math\n\nAsk the model to count or calculate based on the image.\n\nPrompt: \"Count the number of items in the list. Use Python to sum their values if prices are visible.\"\nšŸ–„ļø UI Audit\n\nCheck layout and readability.\n\nPrompt: \"Check if the header text overlaps with any icons. Use the sandbox to calculate the bounding box intersections.\"\nšŸ–ļø Counting & Logic\n\nSolve visual counting tasks with code verification.\n\nPrompt: \"Count the number of fingers on this hand. Use code execution to identify the bounding box for each finger and return the total count.\"\nIntegration with OpenCode\n\nThis skill is designed to provide Visual Grounding for automated coding agents like OpenCode.\n\nStep 1: Use vision-sandbox to extract UI metadata (coordinates, sizes, colors).\nStep 2: Pass the JSON output to OpenCode to generate or fix CSS/HTML.\nConfiguration\nGEMINI_API_KEY: Required environment variable.\nModel: Defaults to gemini-3-flash-preview." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/johanesalxd/vision-sandbox", "publisherUrl": "https://clawhub.ai/johanesalxd/vision-sandbox", "owner": "johanesalxd", "version": "1.1.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/vision-sandbox", "downloadUrl": "https://openagent3.xyz/downloads/vision-sandbox", "agentUrl": "https://openagent3.xyz/skills/vision-sandbox/agent", "manifestUrl": "https://openagent3.xyz/skills/vision-sandbox/agent.json", "briefUrl": "https://openagent3.xyz/skills/vision-sandbox/agent.md" } }