{
  "schemaVersion": "1.0",
  "item": {
    "slug": "vision-tagger",
    "name": "Vision Tagger",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/sagarjhaa/vision-tagger",
    "canonicalUrl": "https://clawhub.ai/sagarjhaa/vision-tagger",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/vision-tagger",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=vision-tagger",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "scripts/setup.sh",
      "scripts/image_tagger.swift",
      "scripts/annotate_image.py"
    ],
    "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": "2026-04-30T16:55:25.780Z",
      "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-tagger"
    },
    "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-tagger",
    "agentPageUrl": "https://openagent3.xyz/skills/vision-tagger/agent",
    "manifestUrl": "https://openagent3.xyz/skills/vision-tagger/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/vision-tagger/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": "Vision Tagger",
        "body": "macOS-native image analysis using Apple's Vision framework. All processing is local — no cloud APIs, no API keys needed."
      },
      {
        "title": "Requirements",
        "body": "macOS 12+ (Monterey or later)\nXcode Command Line Tools\nPython 3 with Pillow"
      },
      {
        "title": "Setup (one-time)",
        "body": "# Install Xcode CLI tools if needed\nxcode-select --install\n\n# Install Pillow\npip3 install Pillow\n\n# Compile the Swift binary\ncd scripts/\nswiftc -O -o image_tagger image_tagger.swift"
      },
      {
        "title": "Analyze image → JSON",
        "body": "./scripts/image_tagger /path/to/photo.jpg\n\nOutput includes:\n\nfaces — bounding boxes, roll/yaw/pitch, landmarks (eyes, nose, mouth)\nbodies — 18 skeleton joints with confidence scores\nhands — 21 joints per hand (left/right)\ntext — OCR results with bounding boxes\nlabels — scene classification (desk, outdoor, clothing, etc.)\nbarcodes — QR codes, UPC, etc.\nsaliency — attention and objectness regions"
      },
      {
        "title": "Annotate image with boxes",
        "body": "python3 scripts/annotate_image.py photo.jpg output.jpg\n\nDraws colored boxes:\n\n🟢 Green: faces\n🟠 Orange: body skeleton\n🟣 Magenta: hands\n🔵 Cyan: text regions\n🟡 Yellow: rectangles/objects\nScene labels at bottom"
      },
      {
        "title": "Python integration",
        "body": "import subprocess, json\n\ndef analyze(path):\n    r = subprocess.run(['./scripts/image_tagger', path], capture_output=True, text=True)\n    return json.loads(r.stdout[r.stdout.find('{'):])\n\ntags = analyze('photo.jpg')\nprint(tags['labels'])  # [{'label': 'desk', 'confidence': 0.85}, ...]\nprint(tags['faces'])   # [{'bbox': {...}, 'confidence': 0.99, 'yaw': 5.2}]"
      },
      {
        "title": "Example JSON Output",
        "body": "{\n  \"dimensions\": {\"width\": 1920, \"height\": 1080},\n  \"faces\": [{\"bbox\": {\"x\": 0.3, \"y\": 0.4, \"width\": 0.15, \"height\": 0.2}, \"confidence\": 0.99, \"roll\": -2, \"yaw\": 5}],\n  \"bodies\": [{\"joints\": {\"head_joint\": {\"x\": 0.5, \"y\": 0.7, \"confidence\": 0.9}, \"left_shoulder\": {...}}, \"confidence\": 1}],\n  \"hands\": [{\"chirality\": \"left\", \"joints\": {\"VNHLKWRI\": {\"x\": 0.4, \"y\": 0.3, \"confidence\": 0.85}}}],\n  \"text\": [{\"text\": \"HELLO\", \"confidence\": 0.95, \"bbox\": {...}}],\n  \"labels\": [{\"label\": \"outdoor\", \"confidence\": 0.88}, {\"label\": \"sky\", \"confidence\": 0.75}],\n  \"saliency\": {\"attentionBased\": [{\"x\": 0.2, \"y\": 0.1, \"width\": 0.6, \"height\": 0.8}]}\n}"
      },
      {
        "title": "Detection Capabilities",
        "body": "FeatureDetailsFacesBounding box, confidence, roll/yaw/pitch angles, 76-point landmarksBodies18 joints: head, neck, shoulders, elbows, wrists, hips, knees, anklesHands21 joints per hand, left/right chiralityText (OCR)Recognized text with confidence and bounding boxesLabels1000+ scene/object categories (clothing, furniture, outdoor, etc.)BarcodesQR, UPC, EAN, Code128, PDF417, Aztec, DataMatrixSaliencyAttention-based and objectness-based regions"
      },
      {
        "title": "Use Cases",
        "body": "Photo tagging — Auto-tag photos with detected objects/scenes\nPosture monitoring — Track face/body position for ergonomics\nDocument scanning — Extract text from images\nSecurity — Detect people in camera feeds\nAccessibility — Describe image contents"
      }
    ],
    "body": "Vision Tagger\n\nmacOS-native image analysis using Apple's Vision framework. All processing is local — no cloud APIs, no API keys needed.\n\nRequirements\nmacOS 12+ (Monterey or later)\nXcode Command Line Tools\nPython 3 with Pillow\nSetup (one-time)\n# Install Xcode CLI tools if needed\nxcode-select --install\n\n# Install Pillow\npip3 install Pillow\n\n# Compile the Swift binary\ncd scripts/\nswiftc -O -o image_tagger image_tagger.swift\n\nUsage\nAnalyze image → JSON\n./scripts/image_tagger /path/to/photo.jpg\n\n\nOutput includes:\n\nfaces — bounding boxes, roll/yaw/pitch, landmarks (eyes, nose, mouth)\nbodies — 18 skeleton joints with confidence scores\nhands — 21 joints per hand (left/right)\ntext — OCR results with bounding boxes\nlabels — scene classification (desk, outdoor, clothing, etc.)\nbarcodes — QR codes, UPC, etc.\nsaliency — attention and objectness regions\nAnnotate image with boxes\npython3 scripts/annotate_image.py photo.jpg output.jpg\n\n\nDraws colored boxes:\n\n🟢 Green: faces\n🟠 Orange: body skeleton\n🟣 Magenta: hands\n🔵 Cyan: text regions\n🟡 Yellow: rectangles/objects\nScene labels at bottom\nPython integration\nimport subprocess, json\n\ndef analyze(path):\n    r = subprocess.run(['./scripts/image_tagger', path], capture_output=True, text=True)\n    return json.loads(r.stdout[r.stdout.find('{'):])\n\ntags = analyze('photo.jpg')\nprint(tags['labels'])  # [{'label': 'desk', 'confidence': 0.85}, ...]\nprint(tags['faces'])   # [{'bbox': {...}, 'confidence': 0.99, 'yaw': 5.2}]\n\nExample JSON Output\n{\n  \"dimensions\": {\"width\": 1920, \"height\": 1080},\n  \"faces\": [{\"bbox\": {\"x\": 0.3, \"y\": 0.4, \"width\": 0.15, \"height\": 0.2}, \"confidence\": 0.99, \"roll\": -2, \"yaw\": 5}],\n  \"bodies\": [{\"joints\": {\"head_joint\": {\"x\": 0.5, \"y\": 0.7, \"confidence\": 0.9}, \"left_shoulder\": {...}}, \"confidence\": 1}],\n  \"hands\": [{\"chirality\": \"left\", \"joints\": {\"VNHLKWRI\": {\"x\": 0.4, \"y\": 0.3, \"confidence\": 0.85}}}],\n  \"text\": [{\"text\": \"HELLO\", \"confidence\": 0.95, \"bbox\": {...}}],\n  \"labels\": [{\"label\": \"outdoor\", \"confidence\": 0.88}, {\"label\": \"sky\", \"confidence\": 0.75}],\n  \"saliency\": {\"attentionBased\": [{\"x\": 0.2, \"y\": 0.1, \"width\": 0.6, \"height\": 0.8}]}\n}\n\nDetection Capabilities\nFeature\tDetails\nFaces\tBounding box, confidence, roll/yaw/pitch angles, 76-point landmarks\nBodies\t18 joints: head, neck, shoulders, elbows, wrists, hips, knees, ankles\nHands\t21 joints per hand, left/right chirality\nText (OCR)\tRecognized text with confidence and bounding boxes\nLabels\t1000+ scene/object categories (clothing, furniture, outdoor, etc.)\nBarcodes\tQR, UPC, EAN, Code128, PDF417, Aztec, DataMatrix\nSaliency\tAttention-based and objectness-based regions\nUse Cases\nPhoto tagging — Auto-tag photos with detected objects/scenes\nPosture monitoring — Track face/body position for ergonomics\nDocument scanning — Extract text from images\nSecurity — Detect people in camera feeds\nAccessibility — Describe image contents"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/sagarjhaa/vision-tagger",
    "publisherUrl": "https://clawhub.ai/sagarjhaa/vision-tagger",
    "owner": "sagarjhaa",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/vision-tagger",
    "downloadUrl": "https://openagent3.xyz/downloads/vision-tagger",
    "agentUrl": "https://openagent3.xyz/skills/vision-tagger/agent",
    "manifestUrl": "https://openagent3.xyz/skills/vision-tagger/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/vision-tagger/agent.md"
  }
}