{
  "schemaVersion": "1.0",
  "item": {
    "slug": "image-cog",
    "name": "image-cog",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/nitishgargiitd/image-cog",
    "canonicalUrl": "https://clawhub.ai/nitishgargiitd/image-cog",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/image-cog",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=image-cog",
    "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": "2026-04-30T16:55:25.780Z",
      "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/image-cog"
    },
    "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/image-cog",
    "agentPageUrl": "https://openagent3.xyz/skills/image-cog/agent",
    "manifestUrl": "https://openagent3.xyz/skills/image-cog/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/image-cog/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 Cog - AI Image Generation Powered by CellCog",
        "body": "Create professional images with AI - from single images to consistent character sets to product photography."
      },
      {
        "title": "Prerequisites",
        "body": "This skill requires the cellcog skill for SDK setup and API calls.\n\nclawhub install cellcog\n\nRead the cellcog skill first for SDK setup. This skill shows you what's possible.\n\nQuick pattern (v1.0+):\n\n# Fire-and-forget - returns immediately\nresult = client.create_chat(\n    prompt=\"[your image request]\",\n    notify_session_key=\"agent:main:main\",\n    task_label=\"image-task\",\n    chat_mode=\"agent\"  # Use \"agent\" for simple images, \"agent team\" for complex\n)\n# Daemon notifies you when complete - do NOT poll"
      },
      {
        "title": "Single Image Creation",
        "body": "Generate any image from a text description:\n\nScenes: \"A cozy coffee shop interior with morning light streaming through windows\"\nPortraits: \"Professional headshot of a confident woman in business attire\"\nProducts: \"Minimalist product shot of a white sneaker on a marble surface\"\nAbstract: \"Geometric abstract art in navy and gold\"\nNature: \"Misty mountain landscape at sunrise with a lone hiker\""
      },
      {
        "title": "Image Editing",
        "body": "Transform existing images:\n\nStyle Transfer: \"Transform this photo into a watercolor painting\"\nBackground Removal: \"Remove the background and place on a clean white backdrop\"\nEnhancement: \"Enhance the colors and add dramatic lighting\"\nModification: \"Change the person's outfit to a red dress\""
      },
      {
        "title": "Consistent Characters",
        "body": "Create multiple images of the same character in different scenarios:\n\nCharacter Series: \"Create a tech entrepreneur character, then show them: 1) At their desk coding, 2) Presenting to investors, 3) Celebrating a product launch\"\nMascot Variations: \"Design a friendly robot mascot, then create versions for: welcome page, error page, success message, loading screen\"\nStory Sequences: \"Create a main character, then illustrate them in 5 scenes of a journey\"\n\nThis is powerful for:\n\nComic strips and storyboards\nMarketing campaigns with consistent characters\nVideo frame generation\nBrand mascots across contexts"
      },
      {
        "title": "Product Photography Style",
        "body": "Professional product visuals:\n\nHero Shots: \"Product hero shot of a smartwatch on a gradient background\"\nLifestyle Shots: \"Smartphone being used by a person in a modern living room\"\nFlat Lays: \"Flat lay of skincare products with botanical elements\"\n360 Views: \"Multiple angles of a leather handbag - front, side, back, detail\""
      },
      {
        "title": "Sets of Related Images",
        "body": "Multiple cohesive images for campaigns or collections:\n\nSocial Media Sets: \"5 Instagram post images for a fitness brand - consistent style, varied content\"\nWebsite Heroes: \"3 hero images for a SaaS landing page - professional, modern, tech-focused\"\nAd Variations: \"4 versions of a product ad with different backgrounds and moods\"\nBlog Illustrations: \"Set of 6 illustrations for a blog post about productivity tips\""
      },
      {
        "title": "Reference-Based Generation",
        "body": "Use existing images as references for style, character, or composition:\n\nStyle Matching: \"Create a new image in the same artistic style as this reference\"\nCharacter Consistency: \"Using this person as reference, create a new scene with them hiking\"\nBrand Alignment: \"Create product images matching this brand's visual style\"\nComposition Reference: \"Create a similar composition but with different subjects\""
      },
      {
        "title": "Image Specifications",
        "body": "AspectOptionsAspect Ratios1:1 (square), 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9Sizes1K (~1024px), 2K (~2048px), 4K (~4096px)StylesPhotorealistic, illustration, watercolor, oil painting, anime, digital art, vectorFormatsPNG (default)\n\nSize recommendations:\n\n1K: Quick iterations, thumbnails, social media posts, drafts\n2K: Standard web content, presentations, marketing materials\n4K: Hero images, print materials, final deliverables where detail matters"
      },
      {
        "title": "When to Use Agent Team Mode",
        "body": "For image generation, chat_mode=\"agent team\" is recommended for:\n\nComplex scenes requiring multiple elements\nConsistent character series\nReference-based generation requiring analysis\nSets of related images\n\nFor simple single images, chat_mode=\"agent\" can work faster."
      },
      {
        "title": "Example Image Prompts",
        "body": "Professional headshot:\n\n\"Create a professional headshot of a friendly Asian woman in her 30s, wearing a navy blazer, soft studio lighting, neutral gray background, confident but approachable expression. 1:1 square, 2K quality, photorealistic.\"\n\nProduct photography:\n\n\"Product shot of a premium wireless earbuds case, matte black finish, on a reflective dark surface with subtle blue accent lighting. Minimalist, high-end tech aesthetic. 4:3 landscape, 4K for hero image.\"\n\nConsistent character set:\n\n\"Create a character: young Black male software developer, casual style with glasses, friendly demeanor. Then create 4 images:\n\nWorking at a standing desk with multiple monitors\nIn a video call meeting, explaining something\nAt a coffee shop with laptop, thinking\nCelebrating with team, high-fiving\nKeep the character exactly consistent across all images.\"\n\nSocial media set:\n\n\"Create 5 Instagram posts for a plant-based meal delivery service:\n\nColorful Buddha bowl from above\nHappy person unpacking delivery\nMeal prep containers arranged neatly\nClose-up of fresh ingredients\nBefore/after showing ingredients to finished dish\nStyle: bright, fresh, appetizing, consistent warm color grading. 1:1 square format.\"\n\nStyle transfer:\n\n\"Transform this uploaded photo of a city street into a Studio Ghibli anime style illustration. Keep the composition and elements but apply the characteristic Ghibli warmth, soft clouds, and whimsical details.\""
      },
      {
        "title": "Tips for Better Images",
        "body": "Be descriptive: \"Woman in office\" is vague. \"Confident woman in her 40s, silver blazer, modern glass-walled office, warm afternoon light\" is better.\n\n\nSpecify style: \"Photorealistic\", \"digital illustration\", \"watercolor\", \"minimalist vector\".\n\n\nDescribe lighting: \"Soft natural light\", \"dramatic side lighting\", \"golden hour glow\", \"studio lighting\".\n\n\nInclude mood: \"Professional and confident\", \"warm and inviting\", \"energetic and vibrant\".\n\n\nMention composition: \"Rule of thirds\", \"centered symmetry\", \"close-up\", \"wide establishing shot\".\n\n\nFor consistency: When creating character series, describe the character in detail first, then reference \"the same character\" in subsequent prompts."
      }
    ],
    "body": "Image Cog - AI Image Generation Powered by CellCog\n\nCreate professional images with AI - from single images to consistent character sets to product photography.\n\nPrerequisites\n\nThis skill requires the cellcog skill for SDK setup and API calls.\n\nclawhub install cellcog\n\n\nRead the cellcog skill first for SDK setup. This skill shows you what's possible.\n\nQuick pattern (v1.0+):\n\n# Fire-and-forget - returns immediately\nresult = client.create_chat(\n    prompt=\"[your image request]\",\n    notify_session_key=\"agent:main:main\",\n    task_label=\"image-task\",\n    chat_mode=\"agent\"  # Use \"agent\" for simple images, \"agent team\" for complex\n)\n# Daemon notifies you when complete - do NOT poll\n\nWhat Images You Can Create\nSingle Image Creation\n\nGenerate any image from a text description:\n\nScenes: \"A cozy coffee shop interior with morning light streaming through windows\"\nPortraits: \"Professional headshot of a confident woman in business attire\"\nProducts: \"Minimalist product shot of a white sneaker on a marble surface\"\nAbstract: \"Geometric abstract art in navy and gold\"\nNature: \"Misty mountain landscape at sunrise with a lone hiker\"\nImage Editing\n\nTransform existing images:\n\nStyle Transfer: \"Transform this photo into a watercolor painting\"\nBackground Removal: \"Remove the background and place on a clean white backdrop\"\nEnhancement: \"Enhance the colors and add dramatic lighting\"\nModification: \"Change the person's outfit to a red dress\"\nConsistent Characters\n\nCreate multiple images of the same character in different scenarios:\n\nCharacter Series: \"Create a tech entrepreneur character, then show them: 1) At their desk coding, 2) Presenting to investors, 3) Celebrating a product launch\"\nMascot Variations: \"Design a friendly robot mascot, then create versions for: welcome page, error page, success message, loading screen\"\nStory Sequences: \"Create a main character, then illustrate them in 5 scenes of a journey\"\n\nThis is powerful for:\n\nComic strips and storyboards\nMarketing campaigns with consistent characters\nVideo frame generation\nBrand mascots across contexts\nProduct Photography Style\n\nProfessional product visuals:\n\nHero Shots: \"Product hero shot of a smartwatch on a gradient background\"\nLifestyle Shots: \"Smartphone being used by a person in a modern living room\"\nFlat Lays: \"Flat lay of skincare products with botanical elements\"\n360 Views: \"Multiple angles of a leather handbag - front, side, back, detail\"\nSets of Related Images\n\nMultiple cohesive images for campaigns or collections:\n\nSocial Media Sets: \"5 Instagram post images for a fitness brand - consistent style, varied content\"\nWebsite Heroes: \"3 hero images for a SaaS landing page - professional, modern, tech-focused\"\nAd Variations: \"4 versions of a product ad with different backgrounds and moods\"\nBlog Illustrations: \"Set of 6 illustrations for a blog post about productivity tips\"\nReference-Based Generation\n\nUse existing images as references for style, character, or composition:\n\nStyle Matching: \"Create a new image in the same artistic style as this reference\"\nCharacter Consistency: \"Using this person as reference, create a new scene with them hiking\"\nBrand Alignment: \"Create product images matching this brand's visual style\"\nComposition Reference: \"Create a similar composition but with different subjects\"\nImage Specifications\nAspect\tOptions\nAspect Ratios\t1:1 (square), 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9\nSizes\t1K (~1024px), 2K (~2048px), 4K (~4096px)\nStyles\tPhotorealistic, illustration, watercolor, oil painting, anime, digital art, vector\nFormats\tPNG (default)\n\nSize recommendations:\n\n1K: Quick iterations, thumbnails, social media posts, drafts\n2K: Standard web content, presentations, marketing materials\n4K: Hero images, print materials, final deliverables where detail matters\nWhen to Use Agent Team Mode\n\nFor image generation, chat_mode=\"agent team\" is recommended for:\n\nComplex scenes requiring multiple elements\nConsistent character series\nReference-based generation requiring analysis\nSets of related images\n\nFor simple single images, chat_mode=\"agent\" can work faster.\n\nExample Image Prompts\n\nProfessional headshot:\n\n\"Create a professional headshot of a friendly Asian woman in her 30s, wearing a navy blazer, soft studio lighting, neutral gray background, confident but approachable expression. 1:1 square, 2K quality, photorealistic.\"\n\nProduct photography:\n\n\"Product shot of a premium wireless earbuds case, matte black finish, on a reflective dark surface with subtle blue accent lighting. Minimalist, high-end tech aesthetic. 4:3 landscape, 4K for hero image.\"\n\nConsistent character set:\n\n\"Create a character: young Black male software developer, casual style with glasses, friendly demeanor. Then create 4 images:\n\nWorking at a standing desk with multiple monitors\nIn a video call meeting, explaining something\nAt a coffee shop with laptop, thinking\nCelebrating with team, high-fiving Keep the character exactly consistent across all images.\"\n\nSocial media set:\n\n\"Create 5 Instagram posts for a plant-based meal delivery service:\n\nColorful Buddha bowl from above\nHappy person unpacking delivery\nMeal prep containers arranged neatly\nClose-up of fresh ingredients\nBefore/after showing ingredients to finished dish Style: bright, fresh, appetizing, consistent warm color grading. 1:1 square format.\"\n\nStyle transfer:\n\n\"Transform this uploaded photo of a city street into a Studio Ghibli anime style illustration. Keep the composition and elements but apply the characteristic Ghibli warmth, soft clouds, and whimsical details.\"\n\nTips for Better Images\n\nBe descriptive: \"Woman in office\" is vague. \"Confident woman in her 40s, silver blazer, modern glass-walled office, warm afternoon light\" is better.\n\nSpecify style: \"Photorealistic\", \"digital illustration\", \"watercolor\", \"minimalist vector\".\n\nDescribe lighting: \"Soft natural light\", \"dramatic side lighting\", \"golden hour glow\", \"studio lighting\".\n\nInclude mood: \"Professional and confident\", \"warm and inviting\", \"energetic and vibrant\".\n\nMention composition: \"Rule of thirds\", \"centered symmetry\", \"close-up\", \"wide establishing shot\".\n\nFor consistency: When creating character series, describe the character in detail first, then reference \"the same character\" in subsequent prompts."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/nitishgargiitd/image-cog",
    "publisherUrl": "https://clawhub.ai/nitishgargiitd/image-cog",
    "owner": "nitishgargiitd",
    "version": "1.0.2",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/image-cog",
    "downloadUrl": "https://openagent3.xyz/downloads/image-cog",
    "agentUrl": "https://openagent3.xyz/skills/image-cog/agent",
    "manifestUrl": "https://openagent3.xyz/skills/image-cog/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/image-cog/agent.md"
  }
}