{
  "schemaVersion": "1.0",
  "item": {
    "slug": "gemini-image-proxy",
    "name": "Gemini Image Proxy",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/YspCoder/gemini-image-proxy",
    "canonicalUrl": "https://clawhub.ai/YspCoder/gemini-image-proxy",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/gemini-image-proxy",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=gemini-image-proxy",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "scripts/generate.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",
      "slug": "gemini-image-proxy",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-03T14:15:23.646Z",
      "expiresAt": "2026-05-10T14:15:23.646Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=gemini-image-proxy",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=gemini-image-proxy",
        "contentDisposition": "attachment; filename=\"gemini-image-proxy-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "gemini-image-proxy"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/gemini-image-proxy"
    },
    "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/gemini-image-proxy",
    "agentPageUrl": "https://openagent3.xyz/skills/gemini-image-proxy/agent",
    "manifestUrl": "https://openagent3.xyz/skills/gemini-image-proxy/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/gemini-image-proxy/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": "Gemini Image Simple",
        "body": "Generate and edit images using Gemini 3 Pro Image via the OpenAI Python SDK and an OpenAI-compatible API endpoint."
      },
      {
        "title": "Why This Skill",
        "body": "FeatureThis SkillOthers (nano-banana-pro, etc.)Dependenciesopenai (SDK)google-genai, pillow, etc.Requires pip/uv✅ Yes✅ YesWorks on Fly.io free✅ Yes (with pip)❌ FailsWorks in containers✅ Yes (with pip)❌ Often failsImage generation✅ Full✅ FullImage editing✅ Yes✅ YesSetup complexityInstall SDK + set API keyInstall packages first\n\nBottom line: This skill uses the OpenAI SDK, so you must install openai once with pip."
      },
      {
        "title": "Install",
        "body": "python3 -m pip install openai"
      },
      {
        "title": "Quick Start",
        "body": "# Set env\nexport GOOGLE_PROXY_API_KEY=\"your_api_key\"\nexport GOOGLE_PROXY_BASE_URL=\"https://example.com/v1\"\n\n# Generate\npython3 /data/clawd/skills/gemini-image-simple/scripts/generate.py \"A cat wearing a tiny hat\" cat.png\n\n# Edit existing image\npython3 /data/clawd/skills/gemini-image-simple/scripts/generate.py \"Make it sunset lighting\" edited.png --input original.png"
      },
      {
        "title": "Generate new image",
        "body": "python3 {baseDir}/scripts/generate.py \"your prompt\" output.png"
      },
      {
        "title": "Edit existing image",
        "body": "python3 {baseDir}/scripts/generate.py \"edit instructions\" output.png --input source.png\n\nSupported input formats: PNG, JPG, JPEG, GIF, WEBP"
      },
      {
        "title": "Environment",
        "body": "Set these environment variables:\n\nGOOGLE_PROXY_API_KEY (your API key)\nGOOGLE_PROXY_BASE_URL (OpenAI-compatible base URL, e.g. https://example.com/v1)"
      },
      {
        "title": "How It Works",
        "body": "Uses Gemini 3 Pro Image (gemini-3-pro-image) via the OpenAI Python SDK:\n\nclient.images.generate(...) for new images\nclient.images.edits(...) for edits\nRequires the openai package\n\nThat's it. Works on any Python 3.10+ installation with openai installed."
      },
      {
        "title": "Model",
        "body": "Currently using: gemini-3-pro-image\n\nOther available models (can be changed in generate.py if needed):\n\ngemini-3-pro-image-preview - Preview variant\nimagen-4.0-ultra-generate-001 - Imagen 4.0 Ultra\nimagen-4.0-generate-001 - Imagen 4.0\ngemini-2.5-flash-image - Gemini 2.5 Flash with image gen"
      },
      {
        "title": "Examples",
        "body": "# Landscape\npython3 {baseDir}/scripts/generate.py \"Misty mountains at sunrise, photorealistic\" mountains.png\n\n# Product shot\npython3 {baseDir}/scripts/generate.py \"Minimalist product photo of a coffee cup, white background\" coffee.png\n\n# Edit: change style\npython3 {baseDir}/scripts/generate.py \"Convert to watercolor painting style\" watercolor.png --input photo.jpg\n\n# Edit: add element\npython3 {baseDir}/scripts/generate.py \"Add a rainbow in the sky\" rainbow.png --input landscape.png"
      }
    ],
    "body": "Gemini Image Simple\n\nGenerate and edit images using Gemini 3 Pro Image via the OpenAI Python SDK and an OpenAI-compatible API endpoint.\n\nWhy This Skill\nFeature\tThis Skill\tOthers (nano-banana-pro, etc.)\nDependencies\topenai (SDK)\tgoogle-genai, pillow, etc.\nRequires pip/uv\t✅ Yes\t✅ Yes\nWorks on Fly.io free\t✅ Yes (with pip)\t❌ Fails\nWorks in containers\t✅ Yes (with pip)\t❌ Often fails\nImage generation\t✅ Full\t✅ Full\nImage editing\t✅ Yes\t✅ Yes\nSetup complexity\tInstall SDK + set API key\tInstall packages first\n\nBottom line: This skill uses the OpenAI SDK, so you must install openai once with pip.\n\nInstall\npython3 -m pip install openai\n\nQuick Start\n# Set env\nexport GOOGLE_PROXY_API_KEY=\"your_api_key\"\nexport GOOGLE_PROXY_BASE_URL=\"https://example.com/v1\"\n\n# Generate\npython3 /data/clawd/skills/gemini-image-simple/scripts/generate.py \"A cat wearing a tiny hat\" cat.png\n\n# Edit existing image\npython3 /data/clawd/skills/gemini-image-simple/scripts/generate.py \"Make it sunset lighting\" edited.png --input original.png\n\nUsage\nGenerate new image\npython3 {baseDir}/scripts/generate.py \"your prompt\" output.png\n\nEdit existing image\npython3 {baseDir}/scripts/generate.py \"edit instructions\" output.png --input source.png\n\n\nSupported input formats: PNG, JPG, JPEG, GIF, WEBP\n\nEnvironment\n\nSet these environment variables:\n\nGOOGLE_PROXY_API_KEY (your API key)\nGOOGLE_PROXY_BASE_URL (OpenAI-compatible base URL, e.g. https://example.com/v1)\nHow It Works\n\nUses Gemini 3 Pro Image (gemini-3-pro-image) via the OpenAI Python SDK:\n\nclient.images.generate(...) for new images\nclient.images.edits(...) for edits\nRequires the openai package\n\nThat's it. Works on any Python 3.10+ installation with openai installed.\n\nModel\n\nCurrently using: gemini-3-pro-image\n\nOther available models (can be changed in generate.py if needed):\n\ngemini-3-pro-image-preview - Preview variant\nimagen-4.0-ultra-generate-001 - Imagen 4.0 Ultra\nimagen-4.0-generate-001 - Imagen 4.0\ngemini-2.5-flash-image - Gemini 2.5 Flash with image gen\nExamples\n# Landscape\npython3 {baseDir}/scripts/generate.py \"Misty mountains at sunrise, photorealistic\" mountains.png\n\n# Product shot\npython3 {baseDir}/scripts/generate.py \"Minimalist product photo of a coffee cup, white background\" coffee.png\n\n# Edit: change style\npython3 {baseDir}/scripts/generate.py \"Convert to watercolor painting style\" watercolor.png --input photo.jpg\n\n# Edit: add element\npython3 {baseDir}/scripts/generate.py \"Add a rainbow in the sky\" rainbow.png --input landscape.png"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/YspCoder/gemini-image-proxy",
    "publisherUrl": "https://clawhub.ai/YspCoder/gemini-image-proxy",
    "owner": "YspCoder",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/gemini-image-proxy",
    "downloadUrl": "https://openagent3.xyz/downloads/gemini-image-proxy",
    "agentUrl": "https://openagent3.xyz/skills/gemini-image-proxy/agent",
    "manifestUrl": "https://openagent3.xyz/skills/gemini-image-proxy/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/gemini-image-proxy/agent.md"
  }
}