{
  "schemaVersion": "1.0",
  "item": {
    "slug": "image2prompt",
    "name": "Image2Prompt",
    "source": "tencent",
    "type": "skill",
    "category": "数据分析",
    "sourceUrl": "https://clawhub.ai/Zhang-Shubo/image2prompt",
    "canonicalUrl": "https://clawhub.ai/Zhang-Shubo/image2prompt",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/image2prompt",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=image2prompt",
    "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/image2prompt"
    },
    "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/image2prompt",
    "agentPageUrl": "https://openagent3.xyz/skills/image2prompt/agent",
    "manifestUrl": "https://openagent3.xyz/skills/image2prompt/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/image2prompt/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": "Image to Prompt",
        "body": "Analyze images and generate detailed, reproduction-quality prompts for AI image generation."
      },
      {
        "title": "Workflow",
        "body": "Step 1: Category Detection\nFirst, classify the image into one of these categories:\n\nportrait — People as main subject (photos, artwork, digital art)\nlandscape — Natural scenery, cityscapes, architecture, outdoor environments\nproduct — Commercial product photos, merchandise\nanimal — Animals as main subject\nillustration — Diagrams, infographics, UI mockups, technical drawings\nother — Images that don't fit above categories\n\nStep 2: Category-Specific Analysis\nGenerate a detailed prompt based on the detected category."
      },
      {
        "title": "Basic Analysis",
        "body": "# Analyze an image (auto-detect category)\nopenclaw message send --image /path/to/image.jpg \"Analyze this image and generate a detailed prompt for reproduction\""
      },
      {
        "title": "Specify Output Format",
        "body": "Natural Language (default):\n\nAnalyze this image and write a detailed, flowing prompt description (600-1000 words for portraits, 400-600 for others).\n\nStructured JSON:\n\nAnalyze this image and output a structured JSON description with all visual elements categorized."
      },
      {
        "title": "With Dimensions Extraction",
        "body": "Request dimension highlights to get tagged phrases for each visual aspect:\n\nAnalyze this image with dimension extraction. Tag phrases for: backgrounds, objects, characters, styles, actions, colors, moods, lighting, compositions, themes."
      },
      {
        "title": "Portrait Analysis Covers:",
        "body": "Model/Style: Photography type, quality level, visual style\nSubject: Gender, age, ethnicity, skin tone, body type\nFacial Features: Eyes, lips, face shape, expression\nHair: Color, length, style, part\nPose: Body position, orientation, leg/hand positions, gaze\nClothing: Type, color, pattern, fit, material, style\nAccessories: Jewelry, bags, hats, etc.\nEnvironment: Location, ground, background, atmosphere\nLighting: Type, time of day, shadows, contrast, color temperature\nCamera: Angle, height, shot type, lens, depth of field, perspective\nTechnical: Realism, post-processing, resolution"
      },
      {
        "title": "Landscape Analysis Covers:",
        "body": "Terrain and water features\nSky and atmospheric elements\nForeground/background composition\nNatural lighting and atmosphere\nColor palette and photography style"
      },
      {
        "title": "Product Analysis Covers:",
        "body": "Product features and materials\nDesign elements and shape\nStaging and background\nStudio lighting setup\nCommercial photography style"
      },
      {
        "title": "Animal Analysis Covers:",
        "body": "Species identification and markings\nPose and behavior\nExpression and character\nHabitat and setting\nWildlife/pet photography style"
      },
      {
        "title": "Illustration Analysis Covers:",
        "body": "Diagram type (flowchart, infographic, UI, etc.)\nVisual elements (icons, shapes, connectors)\nLayout and hierarchy\nDesign style (flat, isometric, etc.)\nColor scheme and meaning"
      },
      {
        "title": "Natural Language Output (Portrait)",
        "body": "{\n  \"prompt\": \"A stunning photorealistic portrait of a young woman in her mid-20s with fair porcelain skin and warm pink undertones. She has striking emerald green almond-shaped eyes with long dark lashes, full rose-colored lips curved in a subtle confident smile, and an oval face with high cheekbones...\"\n}"
      },
      {
        "title": "Structured Output (Portrait)",
        "body": "{\n  \"structured\": {\n    \"model\": \"photorealistic\",\n    \"quality\": \"ultra high\",\n    \"style\": \"cinematic natural light photography\",\n    \"subject\": {\n      \"identity\": \"young beautiful woman\",\n      \"gender\": \"female\",\n      \"age\": \"mid 20s\",\n      \"ethnicity\": \"European\",\n      \"skin_tone\": \"fair porcelain with pink undertones\",\n      \"body_type\": \"slim athletic\",\n      \"facial_features\": {\n        \"eyes\": \"emerald green, almond-shaped, intense gaze\",\n        \"lips\": \"full, rose pink, subtle smile\",\n        \"face_shape\": \"oval with high cheekbones\",\n        \"expression\": \"confident and serene\"\n      },\n      \"hair\": {\n        \"color\": \"warm honey blonde\",\n        \"length\": \"long\",\n        \"style\": \"soft waves\",\n        \"part\": \"center\"\n      }\n    },\n    \"pose\": {\n      \"position\": \"standing\",\n      \"body_orientation\": \"three-quarter turn to camera\",\n      \"legs\": \"weight on right leg, relaxed stance\",\n      \"hands\": {\n        \"right_hand\": \"resting on hip\",\n        \"left_hand\": \"hanging naturally at side\"\n      },\n      \"gaze\": \"direct eye contact with camera\"\n    },\n    \"clothing\": {\n      \"type\": \"flowing maxi dress\",\n      \"color\": \"dusty rose\",\n      \"pattern\": \"solid\",\n      \"details\": \"V-neckline, cinched waist, silk material\",\n      \"style\": \"romantic feminine\"\n    },\n    \"accessories\": [\"delicate gold necklace\", \"small hoop earrings\"],\n    \"environment\": {\n      \"location\": \"outdoor garden\",\n      \"ground\": \"cobblestone path\",\n      \"background\": \"blooming roses, soft bokeh\",\n      \"atmosphere\": \"dreamy and romantic\"\n    },\n    \"lighting\": {\n      \"type\": \"natural sunlight\",\n      \"time\": \"golden hour\",\n      \"shadow_quality\": \"soft diffused shadows\",\n      \"contrast\": \"medium\",\n      \"color_temperature\": \"warm\"\n    },\n    \"camera\": {\n      \"angle\": \"slightly below eye level\",\n      \"camera_height\": \"chest height\",\n      \"shot_type\": \"medium shot\",\n      \"lens\": \"85mm\",\n      \"depth_of_field\": \"shallow\",\n      \"perspective\": \"slight compression, flattering\"\n    },\n    \"mood\": \"romantic, confident, ethereal\",\n    \"realism\": \"highly photorealistic\",\n    \"post_processing\": \"soft color grading, subtle glow\",\n    \"resolution\": \"8k\"\n  }\n}"
      },
      {
        "title": "With Dimensions",
        "body": "{\n  \"prompt\": \"...\",\n  \"dimensions\": {\n    \"backgrounds\": [\"outdoor garden\", \"blooming roses\", \"soft bokeh\"],\n    \"objects\": [\"delicate gold necklace\", \"small hoop earrings\"],\n    \"characters\": [\"young beautiful woman\", \"mid 20s\", \"European\"],\n    \"styles\": [\"photorealistic\", \"cinematic natural light photography\"],\n    \"actions\": [\"standing\", \"three-quarter turn\", \"direct eye contact\"],\n    \"colors\": [\"dusty rose\", \"honey blonde\", \"emerald green\"],\n    \"moods\": [\"romantic\", \"confident\", \"ethereal\", \"dreamy\"],\n    \"lighting\": [\"golden hour\", \"natural sunlight\", \"soft diffused shadows\"],\n    \"compositions\": [\"medium shot\", \"85mm\", \"shallow depth of field\"],\n    \"themes\": [\"romantic feminine\", \"portrait photography\"]\n  }\n}"
      },
      {
        "title": "Tips for Best Results",
        "body": "High-resolution images produce more detailed prompts\nClear, well-lit images yield better category detection\nRequest structured output when you need programmatic access to individual elements\nUse dimensions extraction when building prompt databases or training data\nSpecify word count expectations for natural language output if needed"
      },
      {
        "title": "Integration",
        "body": "This skill works with any vision-capable model. For best results, use:\n\nGPT-4 Vision\nClaude 3 (Opus/Sonnet)\nGemini Pro Vision"
      }
    ],
    "body": "Image to Prompt\n\nAnalyze images and generate detailed, reproduction-quality prompts for AI image generation.\n\nWorkflow\n\nStep 1: Category Detection First, classify the image into one of these categories:\n\nportrait — People as main subject (photos, artwork, digital art)\nlandscape — Natural scenery, cityscapes, architecture, outdoor environments\nproduct — Commercial product photos, merchandise\nanimal — Animals as main subject\nillustration — Diagrams, infographics, UI mockups, technical drawings\nother — Images that don't fit above categories\n\nStep 2: Category-Specific Analysis Generate a detailed prompt based on the detected category.\n\nUsage\nBasic Analysis\n# Analyze an image (auto-detect category)\nopenclaw message send --image /path/to/image.jpg \"Analyze this image and generate a detailed prompt for reproduction\"\n\nSpecify Output Format\n\nNatural Language (default):\n\nAnalyze this image and write a detailed, flowing prompt description (600-1000 words for portraits, 400-600 for others).\n\n\nStructured JSON:\n\nAnalyze this image and output a structured JSON description with all visual elements categorized.\n\nWith Dimensions Extraction\n\nRequest dimension highlights to get tagged phrases for each visual aspect:\n\nAnalyze this image with dimension extraction. Tag phrases for: backgrounds, objects, characters, styles, actions, colors, moods, lighting, compositions, themes.\n\nCategory-Specific Elements\nPortrait Analysis Covers:\nModel/Style: Photography type, quality level, visual style\nSubject: Gender, age, ethnicity, skin tone, body type\nFacial Features: Eyes, lips, face shape, expression\nHair: Color, length, style, part\nPose: Body position, orientation, leg/hand positions, gaze\nClothing: Type, color, pattern, fit, material, style\nAccessories: Jewelry, bags, hats, etc.\nEnvironment: Location, ground, background, atmosphere\nLighting: Type, time of day, shadows, contrast, color temperature\nCamera: Angle, height, shot type, lens, depth of field, perspective\nTechnical: Realism, post-processing, resolution\nLandscape Analysis Covers:\nTerrain and water features\nSky and atmospheric elements\nForeground/background composition\nNatural lighting and atmosphere\nColor palette and photography style\nProduct Analysis Covers:\nProduct features and materials\nDesign elements and shape\nStaging and background\nStudio lighting setup\nCommercial photography style\nAnimal Analysis Covers:\nSpecies identification and markings\nPose and behavior\nExpression and character\nHabitat and setting\nWildlife/pet photography style\nIllustration Analysis Covers:\nDiagram type (flowchart, infographic, UI, etc.)\nVisual elements (icons, shapes, connectors)\nLayout and hierarchy\nDesign style (flat, isometric, etc.)\nColor scheme and meaning\nOutput Examples\nNatural Language Output (Portrait)\n{\n  \"prompt\": \"A stunning photorealistic portrait of a young woman in her mid-20s with fair porcelain skin and warm pink undertones. She has striking emerald green almond-shaped eyes with long dark lashes, full rose-colored lips curved in a subtle confident smile, and an oval face with high cheekbones...\"\n}\n\nStructured Output (Portrait)\n{\n  \"structured\": {\n    \"model\": \"photorealistic\",\n    \"quality\": \"ultra high\",\n    \"style\": \"cinematic natural light photography\",\n    \"subject\": {\n      \"identity\": \"young beautiful woman\",\n      \"gender\": \"female\",\n      \"age\": \"mid 20s\",\n      \"ethnicity\": \"European\",\n      \"skin_tone\": \"fair porcelain with pink undertones\",\n      \"body_type\": \"slim athletic\",\n      \"facial_features\": {\n        \"eyes\": \"emerald green, almond-shaped, intense gaze\",\n        \"lips\": \"full, rose pink, subtle smile\",\n        \"face_shape\": \"oval with high cheekbones\",\n        \"expression\": \"confident and serene\"\n      },\n      \"hair\": {\n        \"color\": \"warm honey blonde\",\n        \"length\": \"long\",\n        \"style\": \"soft waves\",\n        \"part\": \"center\"\n      }\n    },\n    \"pose\": {\n      \"position\": \"standing\",\n      \"body_orientation\": \"three-quarter turn to camera\",\n      \"legs\": \"weight on right leg, relaxed stance\",\n      \"hands\": {\n        \"right_hand\": \"resting on hip\",\n        \"left_hand\": \"hanging naturally at side\"\n      },\n      \"gaze\": \"direct eye contact with camera\"\n    },\n    \"clothing\": {\n      \"type\": \"flowing maxi dress\",\n      \"color\": \"dusty rose\",\n      \"pattern\": \"solid\",\n      \"details\": \"V-neckline, cinched waist, silk material\",\n      \"style\": \"romantic feminine\"\n    },\n    \"accessories\": [\"delicate gold necklace\", \"small hoop earrings\"],\n    \"environment\": {\n      \"location\": \"outdoor garden\",\n      \"ground\": \"cobblestone path\",\n      \"background\": \"blooming roses, soft bokeh\",\n      \"atmosphere\": \"dreamy and romantic\"\n    },\n    \"lighting\": {\n      \"type\": \"natural sunlight\",\n      \"time\": \"golden hour\",\n      \"shadow_quality\": \"soft diffused shadows\",\n      \"contrast\": \"medium\",\n      \"color_temperature\": \"warm\"\n    },\n    \"camera\": {\n      \"angle\": \"slightly below eye level\",\n      \"camera_height\": \"chest height\",\n      \"shot_type\": \"medium shot\",\n      \"lens\": \"85mm\",\n      \"depth_of_field\": \"shallow\",\n      \"perspective\": \"slight compression, flattering\"\n    },\n    \"mood\": \"romantic, confident, ethereal\",\n    \"realism\": \"highly photorealistic\",\n    \"post_processing\": \"soft color grading, subtle glow\",\n    \"resolution\": \"8k\"\n  }\n}\n\nWith Dimensions\n{\n  \"prompt\": \"...\",\n  \"dimensions\": {\n    \"backgrounds\": [\"outdoor garden\", \"blooming roses\", \"soft bokeh\"],\n    \"objects\": [\"delicate gold necklace\", \"small hoop earrings\"],\n    \"characters\": [\"young beautiful woman\", \"mid 20s\", \"European\"],\n    \"styles\": [\"photorealistic\", \"cinematic natural light photography\"],\n    \"actions\": [\"standing\", \"three-quarter turn\", \"direct eye contact\"],\n    \"colors\": [\"dusty rose\", \"honey blonde\", \"emerald green\"],\n    \"moods\": [\"romantic\", \"confident\", \"ethereal\", \"dreamy\"],\n    \"lighting\": [\"golden hour\", \"natural sunlight\", \"soft diffused shadows\"],\n    \"compositions\": [\"medium shot\", \"85mm\", \"shallow depth of field\"],\n    \"themes\": [\"romantic feminine\", \"portrait photography\"]\n  }\n}\n\nTips for Best Results\nHigh-resolution images produce more detailed prompts\nClear, well-lit images yield better category detection\nRequest structured output when you need programmatic access to individual elements\nUse dimensions extraction when building prompt databases or training data\nSpecify word count expectations for natural language output if needed\nIntegration\n\nThis skill works with any vision-capable model. For best results, use:\n\nGPT-4 Vision\nClaude 3 (Opus/Sonnet)\nGemini Pro Vision"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/Zhang-Shubo/image2prompt",
    "publisherUrl": "https://clawhub.ai/Zhang-Shubo/image2prompt",
    "owner": "Zhang-Shubo",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/image2prompt",
    "downloadUrl": "https://openagent3.xyz/downloads/image2prompt",
    "agentUrl": "https://openagent3.xyz/skills/image2prompt/agent",
    "manifestUrl": "https://openagent3.xyz/skills/image2prompt/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/image2prompt/agent.md"
  }
}