{
  "schemaVersion": "1.0",
  "item": {
    "slug": "nanobanana-skill",
    "name": "Nanobanana Skill",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/feiskyer/nanobanana-skill",
    "canonicalUrl": "https://clawhub.ai/feiskyer/nanobanana-skill",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/nanobanana-skill",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=nanobanana-skill",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "nanobanana.py",
      "requirements.txt"
    ],
    "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/nanobanana-skill"
    },
    "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/nanobanana-skill",
    "agentPageUrl": "https://openagent3.xyz/skills/nanobanana-skill/agent",
    "manifestUrl": "https://openagent3.xyz/skills/nanobanana-skill/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/nanobanana-skill/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": "Nanobanana Image Generation Skill",
        "body": "Generate or edit images using Google Gemini API through the nanobanana tool."
      },
      {
        "title": "Requirements",
        "body": "GEMINI_API_KEY: Must be configured in ~/.nanobanana.env or export GEMINI_API_KEY=<your-api-key>\nPython3 with depedent packages installed: google-genai, Pillow, python-dotenv. They could be installed via python3 -m pip install -r ${CLAUDE_PLUGIN_ROOT}/skills/nanobanana-skill/requirements.txt if not installed yet.\nExecutable: ${CLAUDE_PLUGIN_ROOT}/skills/nanobanana-skill/nanobanana.py"
      },
      {
        "title": "For image generation",
        "body": "Ask the user for:\n\nWhat they want to create (the prompt)\nDesired aspect ratio/size (optional, defaults to 9:16 portrait)\nOutput filename (optional, auto-generates UUID if not specified)\nModel preference (optional, defaults to gemini-3-pro-image-preview)\nResolution (optional, defaults to 1K)\n\n\n\nRun the nanobanana script with appropriate parameters:\npython3 ${CLAUDE_PLUGIN_ROOT}/skills/nanobanana-skill/nanobanana.py --prompt \"description of image\" --output \"filename.png\"\n\n\n\nShow the user the saved image path when complete"
      },
      {
        "title": "For image editing",
        "body": "Ask the user for:\n\nInput image file(s) to edit\nWhat changes they want (the prompt)\nOutput filename (optional)\n\n\n\nRun with input images:\npython3 ${CLAUDE_PLUGIN_ROOT}/skills/nanobanana-skill/nanobanana.py --prompt \"editing instructions\" --input image1.png image2.png --output \"edited.png\""
      },
      {
        "title": "Aspect Ratios (--size)",
        "body": "1024x1024 (1:1) - Square\n832x1248 (2:3) - Portrait\n1248x832 (3:2) - Landscape\n864x1184 (3:4) - Portrait\n1184x864 (4:3) - Landscape\n896x1152 (4:5) - Portrait\n1152x896 (5:4) - Landscape\n768x1344 (9:16) - Portrait (default)\n1344x768 (16:9) - Landscape\n1536x672 (21:9) - Ultra-wide"
      },
      {
        "title": "Models (--model)",
        "body": "gemini-3-pro-image-preview (default) - Higher quality\ngemini-2.5-flash-image - Faster generation"
      },
      {
        "title": "Resolution (--resolution)",
        "body": "1K (default)\n2K\n4K"
      },
      {
        "title": "Generate a simple image",
        "body": "python3 ${CLAUDE_PLUGIN_ROOT}/skills/nanobanana-skill/nanobanana.py --prompt \"A serene mountain landscape at sunset with a lake\""
      },
      {
        "title": "Generate with specific size and output",
        "body": "python3 ${CLAUDE_PLUGIN_ROOT}/skills/nanobanana-skill/nanobanana.py \\\n  --prompt \"Modern minimalist logo for a tech startup\" \\\n  --size 1024x1024 \\\n  --output \"logo.png\""
      },
      {
        "title": "Generate landscape image with high resolution",
        "body": "python3 ${CLAUDE_PLUGIN_ROOT}/skills/nanobanana-skill/nanobanana.py \\\n  --prompt \"Futuristic cityscape with flying cars\" \\\n  --size 1344x768 \\\n  --resolution 2K \\\n  --output \"cityscape.png\""
      },
      {
        "title": "Edit existing images",
        "body": "python3 ${CLAUDE_PLUGIN_ROOT}/skills/nanobanana-skill/nanobanana.py \\\n  --prompt \"Add a rainbow in the sky\" \\\n  --input photo.png \\\n  --output \"photo-with-rainbow.png\""
      },
      {
        "title": "Use faster model",
        "body": "python3 ${CLAUDE_PLUGIN_ROOT}/skills/nanobanana-skill/nanobanana.py \\\n  --prompt \"Quick sketch of a cat\" \\\n  --model gemini-2.5-flash-image \\\n  --output \"cat-sketch.png\""
      },
      {
        "title": "Error Handling",
        "body": "If the script fails:\n\nCheck that GEMINI_API_KEY is exported or set in ~/.nanobanana.env\nVerify input image files exist and are readable\nEnsure the output directory is writable\nIf no image is generated, try making the prompt more specific about wanting an image"
      },
      {
        "title": "Best Practices",
        "body": "Be descriptive in prompts - include style, mood, colors, composition\nFor logos/graphics, use square aspect ratio (1024x1024)\nFor social media posts, use 9:16 for stories or 1:1 for posts\nFor wallpapers, use 16:9 or 21:9\nStart with 1K resolution for testing, upgrade to 2K/4K for final output\nUse gemini-3-pro-image-preview for best quality, gemini-2.5-flash-image for speed"
      }
    ],
    "body": "Nanobanana Image Generation Skill\n\nGenerate or edit images using Google Gemini API through the nanobanana tool.\n\nRequirements\nGEMINI_API_KEY: Must be configured in ~/.nanobanana.env or export GEMINI_API_KEY=<your-api-key>\nPython3 with depedent packages installed: google-genai, Pillow, python-dotenv. They could be installed via python3 -m pip install -r ${CLAUDE_PLUGIN_ROOT}/skills/nanobanana-skill/requirements.txt if not installed yet.\nExecutable: ${CLAUDE_PLUGIN_ROOT}/skills/nanobanana-skill/nanobanana.py\nInstructions\nFor image generation\n\nAsk the user for:\n\nWhat they want to create (the prompt)\nDesired aspect ratio/size (optional, defaults to 9:16 portrait)\nOutput filename (optional, auto-generates UUID if not specified)\nModel preference (optional, defaults to gemini-3-pro-image-preview)\nResolution (optional, defaults to 1K)\n\nRun the nanobanana script with appropriate parameters:\n\npython3 ${CLAUDE_PLUGIN_ROOT}/skills/nanobanana-skill/nanobanana.py --prompt \"description of image\" --output \"filename.png\"\n\n\nShow the user the saved image path when complete\n\nFor image editing\n\nAsk the user for:\n\nInput image file(s) to edit\nWhat changes they want (the prompt)\nOutput filename (optional)\n\nRun with input images:\n\npython3 ${CLAUDE_PLUGIN_ROOT}/skills/nanobanana-skill/nanobanana.py --prompt \"editing instructions\" --input image1.png image2.png --output \"edited.png\"\n\nAvailable Options\nAspect Ratios (--size)\n1024x1024 (1:1) - Square\n832x1248 (2:3) - Portrait\n1248x832 (3:2) - Landscape\n864x1184 (3:4) - Portrait\n1184x864 (4:3) - Landscape\n896x1152 (4:5) - Portrait\n1152x896 (5:4) - Landscape\n768x1344 (9:16) - Portrait (default)\n1344x768 (16:9) - Landscape\n1536x672 (21:9) - Ultra-wide\nModels (--model)\ngemini-3-pro-image-preview (default) - Higher quality\ngemini-2.5-flash-image - Faster generation\nResolution (--resolution)\n1K (default)\n2K\n4K\nExamples\nGenerate a simple image\npython3 ${CLAUDE_PLUGIN_ROOT}/skills/nanobanana-skill/nanobanana.py --prompt \"A serene mountain landscape at sunset with a lake\"\n\nGenerate with specific size and output\npython3 ${CLAUDE_PLUGIN_ROOT}/skills/nanobanana-skill/nanobanana.py \\\n  --prompt \"Modern minimalist logo for a tech startup\" \\\n  --size 1024x1024 \\\n  --output \"logo.png\"\n\nGenerate landscape image with high resolution\npython3 ${CLAUDE_PLUGIN_ROOT}/skills/nanobanana-skill/nanobanana.py \\\n  --prompt \"Futuristic cityscape with flying cars\" \\\n  --size 1344x768 \\\n  --resolution 2K \\\n  --output \"cityscape.png\"\n\nEdit existing images\npython3 ${CLAUDE_PLUGIN_ROOT}/skills/nanobanana-skill/nanobanana.py \\\n  --prompt \"Add a rainbow in the sky\" \\\n  --input photo.png \\\n  --output \"photo-with-rainbow.png\"\n\nUse faster model\npython3 ${CLAUDE_PLUGIN_ROOT}/skills/nanobanana-skill/nanobanana.py \\\n  --prompt \"Quick sketch of a cat\" \\\n  --model gemini-2.5-flash-image \\\n  --output \"cat-sketch.png\"\n\nError Handling\n\nIf the script fails:\n\nCheck that GEMINI_API_KEY is exported or set in ~/.nanobanana.env\nVerify input image files exist and are readable\nEnsure the output directory is writable\nIf no image is generated, try making the prompt more specific about wanting an image\nBest Practices\nBe descriptive in prompts - include style, mood, colors, composition\nFor logos/graphics, use square aspect ratio (1024x1024)\nFor social media posts, use 9:16 for stories or 1:1 for posts\nFor wallpapers, use 16:9 or 21:9\nStart with 1K resolution for testing, upgrade to 2K/4K for final output\nUse gemini-3-pro-image-preview for best quality, gemini-2.5-flash-image for speed"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/feiskyer/nanobanana-skill",
    "publisherUrl": "https://clawhub.ai/feiskyer/nanobanana-skill",
    "owner": "feiskyer",
    "version": "0.1.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/nanobanana-skill",
    "downloadUrl": "https://openagent3.xyz/downloads/nanobanana-skill",
    "agentUrl": "https://openagent3.xyz/skills/nanobanana-skill/agent",
    "manifestUrl": "https://openagent3.xyz/skills/nanobanana-skill/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/nanobanana-skill/agent.md"
  }
}