{
  "schemaVersion": "1.0",
  "item": {
    "slug": "cad-agent",
    "name": "CAD Agent",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/clawd-maf/cad-agent",
    "canonicalUrl": "https://clawhub.ai/clawd-maf/cad-agent",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/cad-agent",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=cad-agent",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md"
    ],
    "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. 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. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-23T16:43:11.935Z",
      "expiresAt": "2026-04-30T16:43:11.935Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
        "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.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/cad-agent"
    },
    "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/cad-agent",
    "agentPageUrl": "https://openagent3.xyz/skills/cad-agent/agent",
    "manifestUrl": "https://openagent3.xyz/skills/cad-agent/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/cad-agent/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. 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. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "CAD Agent",
        "body": "Give your AI agent eyes for CAD work."
      },
      {
        "title": "Description",
        "body": "CAD Agent is a rendering server that lets AI agents see what they're building. Send modeling commands → receive rendered images → iterate visually.\n\nUse when: designing 3D-printable parts, parametric CAD, mechanical design, build123d modeling"
      },
      {
        "title": "Architecture",
        "body": "Critical: All CAD logic runs inside the container. You (the agent) only:\n\nSend commands via HTTP\nView the returned images\nDecide what to do next\n\nYOU (agent)                     CAD AGENT CONTAINER\n─────────────                   ───────────────────\nSend build123d code      →      Executes modeling\n                         ←      Returns JSON status\nRequest render           →      VTK renders the model\n                         ←      Returns PNG image\n*Look at the image*\nDecide: iterate or done\n\nNever do STL manipulation, mesh processing, or rendering outside the container. The container handles everything — you just command and observe."
      },
      {
        "title": "1. Clone the Repository",
        "body": "git clone https://github.com/clawd-maf/cad-agent.git\ncd cad-agent"
      },
      {
        "title": "2. Build the Docker Image",
        "body": "docker build -t cad-agent:latest .\n\nOr using docker-compose:\n\ndocker-compose build"
      },
      {
        "title": "3. Run the Server",
        "body": "# Using docker-compose (recommended)\ndocker-compose up -d\n\n# Or using docker directly\ndocker run -d --name cad-agent -p 8123:8123 cad-agent:latest serve"
      },
      {
        "title": "4. Verify Installation",
        "body": "curl http://localhost:8123/health\n# Should return: {\"status\": \"healthy\", ...}\n\nDocker-in-Docker caveat: In nested container environments (e.g., Clawdbot sandbox), host networking may not work—curl localhost:8123 will fail even though the server binds to 0.0.0.0:8123. Use docker exec cad-agent python3 -c \"...\" commands instead. On a normal Docker host, localhost access works fine."
      },
      {
        "title": "1. Create Model",
        "body": "curl -X POST http://localhost:8123/model/create \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"name\": \"my_part\",\n    \"code\": \"from build123d import *\\nresult = Box(60, 40, 30)\"\n  }'"
      },
      {
        "title": "2. Render & View",
        "body": "# Get multi-view (front/right/top/iso)\ncurl -X POST http://localhost:8123/render/multiview \\\n  -d '{\"model_name\": \"my_part\"}' -o views.png\n\n# Or 3D isometric\ncurl -X POST http://localhost:8123/render/3d \\\n  -d '{\"model_name\": \"my_part\", \"view\": \"isometric\"}' -o iso.png\n\nLook at the image. Does it look right? If not, modify and re-render."
      },
      {
        "title": "3. Iterate",
        "body": "curl -X POST http://localhost:8123/model/modify \\\n  -d '{\n    \"name\": \"my_part\", \n    \"code\": \"result = result - Cylinder(5, 50).locate(Pos(20, 10, 0))\"\n  }'\n\n# Re-render to check\ncurl -X POST http://localhost:8123/render/3d \\\n  -d '{\"model_name\": \"my_part\"}' -o updated.png"
      },
      {
        "title": "4. Export",
        "body": "curl -X POST http://localhost:8123/export \\\n  -d '{\"model_name\": \"my_part\", \"format\": \"stl\"}' -o part.stl"
      },
      {
        "title": "Endpoints",
        "body": "EndpointWhat it doesPOST /model/createRun build123d code, create modelPOST /model/modifyModify existing modelGET /model/listList models in sessionGET /model/{name}/measureGet dimensionsPOST /render/3d3D shaded render (VTK)POST /render/2d2D technical drawingPOST /render/multiview4-view compositePOST /exportExport STL/STEP/3MFPOST /analyze/printabilityCheck if printable"
      },
      {
        "title": "build123d Cheatsheet",
        "body": "from build123d import *\n\n# Primitives\nBox(width, depth, height)\nCylinder(radius, height)\nSphere(radius)\n\n# Boolean\na + b   # union\na - b   # subtract\na & b   # intersect\n\n# Position\npart.locate(Pos(x, y, z))\npart.rotate(Axis.Z, 45)\n\n# Edges\nfillet(part.edges(), radius)\nchamfer(part.edges(), length)"
      },
      {
        "title": "Important",
        "body": "Don't bypass the container. No matplotlib, no external STL libraries, no mesh hacking.\nRenders are your eyes. Always request a render after changes.\nIterate visually. The whole point is you can see what you're building."
      },
      {
        "title": "Design File Safety",
        "body": "The project has safeguards against accidentally committing CAD outputs:\n\n.gitignore blocks *.stl, *.step, *.3mf, etc.\nPre-commit hook rejects design files\nUser's designs stay local, never versioned"
      },
      {
        "title": "Links",
        "body": "Repository\nbuild123d docs\nVTK"
      }
    ],
    "body": "CAD Agent\n\nGive your AI agent eyes for CAD work.\n\nDescription\n\nCAD Agent is a rendering server that lets AI agents see what they're building. Send modeling commands → receive rendered images → iterate visually.\n\nUse when: designing 3D-printable parts, parametric CAD, mechanical design, build123d modeling\n\nArchitecture\n\nCritical: All CAD logic runs inside the container. You (the agent) only:\n\nSend commands via HTTP\nView the returned images\nDecide what to do next\nYOU (agent)                     CAD AGENT CONTAINER\n─────────────                   ───────────────────\nSend build123d code      →      Executes modeling\n                         ←      Returns JSON status\nRequest render           →      VTK renders the model\n                         ←      Returns PNG image\n*Look at the image*\nDecide: iterate or done\n\n\nNever do STL manipulation, mesh processing, or rendering outside the container. The container handles everything — you just command and observe.\n\nSetup\n1. Clone the Repository\ngit clone https://github.com/clawd-maf/cad-agent.git\ncd cad-agent\n\n2. Build the Docker Image\ndocker build -t cad-agent:latest .\n\n\nOr using docker-compose:\n\ndocker-compose build\n\n3. Run the Server\n# Using docker-compose (recommended)\ndocker-compose up -d\n\n# Or using docker directly\ndocker run -d --name cad-agent -p 8123:8123 cad-agent:latest serve\n\n4. Verify Installation\ncurl http://localhost:8123/health\n# Should return: {\"status\": \"healthy\", ...}\n\n\nDocker-in-Docker caveat: In nested container environments (e.g., Clawdbot sandbox), host networking may not work—curl localhost:8123 will fail even though the server binds to 0.0.0.0:8123. Use docker exec cad-agent python3 -c \"...\" commands instead. On a normal Docker host, localhost access works fine.\n\nWorkflow\n1. Create Model\ncurl -X POST http://localhost:8123/model/create \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"name\": \"my_part\",\n    \"code\": \"from build123d import *\\nresult = Box(60, 40, 30)\"\n  }'\n\n2. Render & View\n# Get multi-view (front/right/top/iso)\ncurl -X POST http://localhost:8123/render/multiview \\\n  -d '{\"model_name\": \"my_part\"}' -o views.png\n\n# Or 3D isometric\ncurl -X POST http://localhost:8123/render/3d \\\n  -d '{\"model_name\": \"my_part\", \"view\": \"isometric\"}' -o iso.png\n\n\nLook at the image. Does it look right? If not, modify and re-render.\n\n3. Iterate\ncurl -X POST http://localhost:8123/model/modify \\\n  -d '{\n    \"name\": \"my_part\", \n    \"code\": \"result = result - Cylinder(5, 50).locate(Pos(20, 10, 0))\"\n  }'\n\n# Re-render to check\ncurl -X POST http://localhost:8123/render/3d \\\n  -d '{\"model_name\": \"my_part\"}' -o updated.png\n\n4. Export\ncurl -X POST http://localhost:8123/export \\\n  -d '{\"model_name\": \"my_part\", \"format\": \"stl\"}' -o part.stl\n\nEndpoints\nEndpoint\tWhat it does\nPOST /model/create\tRun build123d code, create model\nPOST /model/modify\tModify existing model\nGET /model/list\tList models in session\nGET /model/{name}/measure\tGet dimensions\nPOST /render/3d\t3D shaded render (VTK)\nPOST /render/2d\t2D technical drawing\nPOST /render/multiview\t4-view composite\nPOST /export\tExport STL/STEP/3MF\nPOST /analyze/printability\tCheck if printable\nbuild123d Cheatsheet\nfrom build123d import *\n\n# Primitives\nBox(width, depth, height)\nCylinder(radius, height)\nSphere(radius)\n\n# Boolean\na + b   # union\na - b   # subtract\na & b   # intersect\n\n# Position\npart.locate(Pos(x, y, z))\npart.rotate(Axis.Z, 45)\n\n# Edges\nfillet(part.edges(), radius)\nchamfer(part.edges(), length)\n\nImportant\nDon't bypass the container. No matplotlib, no external STL libraries, no mesh hacking.\nRenders are your eyes. Always request a render after changes.\nIterate visually. The whole point is you can see what you're building.\nDesign File Safety\n\nThe project has safeguards against accidentally committing CAD outputs:\n\n.gitignore blocks *.stl, *.step, *.3mf, etc.\nPre-commit hook rejects design files\nUser's designs stay local, never versioned\nLinks\nRepository\nbuild123d docs\nVTK"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/clawd-maf/cad-agent",
    "publisherUrl": "https://clawhub.ai/clawd-maf/cad-agent",
    "owner": "clawd-maf",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/cad-agent",
    "downloadUrl": "https://openagent3.xyz/downloads/cad-agent",
    "agentUrl": "https://openagent3.xyz/skills/cad-agent/agent",
    "manifestUrl": "https://openagent3.xyz/skills/cad-agent/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/cad-agent/agent.md"
  }
}