{
  "schemaVersion": "1.0",
  "item": {
    "slug": "pony-image",
    "name": "pony-image",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/lirule007/pony-image",
    "canonicalUrl": "https://clawhub.ai/lirule007/pony-image",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/pony-image",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=pony-image",
    "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/pony-image"
    },
    "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/pony-image",
    "agentPageUrl": "https://openagent3.xyz/skills/pony-image/agent",
    "manifestUrl": "https://openagent3.xyz/skills/pony-image/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/pony-image/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": "Pony Image Agent — AI 商业图片生成",
        "body": "版本: v2.0 | 最后更新: 2026-02-23"
      },
      {
        "title": "环境配置",
        "body": "本技能需要以下环境变量：\n\nPONY_SUPABASE_ANON_KEY — Supabase anon 公钥（JWT 格式，以 eyJ 开头）\n\nAPI 基础地址（固定）：\n\nBASE_URL=https://vecarpahagopuqbwxbjh.supabase.co/functions/v1\n\n所有请求需携带以下 Header：\n\nAuthorization: Bearer $PONY_SUPABASE_ANON_KEY\nContent-Type: application/json"
      },
      {
        "title": "快速决策",
        "body": "🤔 不知道选哪个功能？按以下决策树选择：\n\n有参考图片想复制风格吗？ → 风格复刻 (/image replicate)\n需要多张主题统一的图片？ → 套图生成 (/image suite)\n只需要一张新图片？ → 单图生成 (/image generate)"
      },
      {
        "title": "🎨 场景1：单图生成",
        "body": "何时使用：只需要一张新图片，无需参考图\n\n对话示例：\n\n用户：帮我生成一张产品图\n助手：好的！请告诉我：\n  1. 产品描述是什么？\n  2. 想要什么风格？（product/lifestyle/minimalist/vintage/dark）\n  3. 图片比例？（默认 1:1）\n\n执行方式：收集完信息后，执行以下命令：\n\ncurl -s -X POST \"$BASE_URL/generate-image\" \\\n  -H \"Authorization: Bearer $PONY_SUPABASE_ANON_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"prompt\": \"用户描述的内容\",\n    \"style\": \"minimalist\",\n    \"ratio\": \"1:1\"\n  }'\n\n返回格式：\n\n{\n  \"imageUrl\": \"data:image/png;base64,...\",\n  \"prompt\": \"增强后的完整 prompt\"\n}\n\n将 imageUrl 展示给用户即可。"
      },
      {
        "title": "🖼️ 场景2：风格复刻（两步流程）",
        "body": "何时使用：有参考图片，想让新图片保持相同视觉风格\n\n对话示例：\n\n用户：我想复刻这张图的风格\n助手：收到参考图！正在分析风格...\n\n（执行 Step 1）\n\n助手：✅ 风格分析完成：\n  - 主色调：暖金色\n  - 光影：柔和侧光\n  - 构图：居中对称\n  \n  请上传你的产品图，我将按此风格生成新图。\n\nStep 1 — 分析参考图风格：\n\ncurl -s -X POST \"$BASE_URL/replicate-image\" \\\n  -H \"Authorization: Bearer $PONY_SUPABASE_ANON_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"action\": \"analyze\",\n    \"referenceImages\": [\"参考图URL或Base64\"]\n  }'\n\n返回 plan 对象，包含 styleAnalysisSummary、colorSystem、photographyStyle 等。\n\nStep 2 — 用风格生成新图：\n\ncurl -s -X POST \"$BASE_URL/replicate-image\" \\\n  -H \"Authorization: Bearer $PONY_SUPABASE_ANON_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"productImages\": [\"产品图URL或Base64\"],\n    \"plan\": { \"...Step1返回的plan对象...\" },\n    \"ratio\": \"1:1\"\n  }'\n\n返回 imageUrl（生成的图片）。"
      },
      {
        "title": "📦 场景3：套图生成（两步流程）",
        "body": "何时使用：需要一组视觉统一的系列图片（如电商主图+详情图）\n\n对话示例：\n\n用户：帮我生成一组电商产品图\n助手：好的！我需要了解：\n  1. 产品名称和描述？\n  2. 需要哪些场景？（主图/场景图/细节图/对比图）\n  3. 整体风格偏好？\n  \n  我会先生成统一设计方案，确认后再逐张生成。\n\nStep 1 — 生成统一设计方案：\n\ncurl -s -X POST \"$BASE_URL/generate-suite-plan\" \\\n  -H \"Authorization: Bearer $PONY_SUPABASE_ANON_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"productName\": \"产品名称\",\n    \"productDesc\": \"产品描述\",\n    \"scenes\": [\"主图\", \"场景图\", \"细节图\"],\n    \"style\": \"minimalist\",\n    \"ratio\": \"1:1\"\n  }'\n\n返回 plan 对象，包含 overallDesign（配色、字体、光影）和每张图的 images 数组。\n\nStep 2 — 逐张生成：对 plan.images 中每张图，将 overallDesign + 该图信息合并到 prompt，调用：\n\ncurl -s -X POST \"$BASE_URL/generate-image\" \\\n  -H \"Authorization: Bearer $PONY_SUPABASE_ANON_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"prompt\": \"合并 overallDesign 和 images[i] 信息的完整描述\",\n    \"style\": \"minimalist\",\n    \"ratio\": \"1:1\"\n  }'"
      },
      {
        "title": "风格预设 (style)",
        "body": "值说明适用场景product专业产品摄影，干净背景，影棚灯光电商主图、产品展示lifestyle生活场景，自然环境，温暖氛围社交媒体、品牌故事minimalist极简风格，白色背景，现代感官网、品牌手册vintage复古美学，暖色调，怀旧感文艺品牌、咖啡/手工艺dark暗调高级感，戏剧性灯光，高对比科技产品、奢侈品"
      },
      {
        "title": "宽高比预设 (ratio)",
        "body": "值适用场景1:1Instagram 帖子、电商主图3:4产品详情页4:5Instagram 竖版帖子9:16手机竖屏、TikTok/抖音4:3横版展示16:9网页横幅、YouTube 封面2:3海报、杂志21:9超宽电影画幅"
      },
      {
        "title": "AI 模型 (model)",
        "body": "值说明google/gemini-2.5-flash-image默认，快速生成，仅 1Kgoogle/gemini-3-pro-image-preview高质量，支持 2K/4K"
      },
      {
        "title": "错误处理",
        "body": "HTTP 状态错误信息解决方案401Unauthorized检查 PONY_SUPABASE_ANON_KEY 是否已配置429请求频率超限等待几秒后重试402AI 额度不足充值后继续使用500图片生成失败简化 prompt 描述，避免过长内容"
      },
      {
        "title": "限制",
        "body": "单次请求超时 60 秒\nBase64 图片大小建议 < 4MB\n生成结果为 Base64 格式\n2K/4K 分辨率仅限 Pro 模型"
      }
    ],
    "body": "Pony Image Agent — AI 商业图片生成\n\n版本: v2.0 | 最后更新: 2026-02-23\n\n环境配置\n\n本技能需要以下环境变量：\n\nPONY_SUPABASE_ANON_KEY — Supabase anon 公钥（JWT 格式，以 eyJ 开头）\n\nAPI 基础地址（固定）：\n\nBASE_URL=https://vecarpahagopuqbwxbjh.supabase.co/functions/v1\n\n\n所有请求需携带以下 Header：\n\nAuthorization: Bearer $PONY_SUPABASE_ANON_KEY\nContent-Type: application/json\n\n快速决策\n\n🤔 不知道选哪个功能？按以下决策树选择：\n\n有参考图片想复制风格吗？ → 风格复刻 (/image replicate)\n需要多张主题统一的图片？ → 套图生成 (/image suite)\n只需要一张新图片？ → 单图生成 (/image generate)\n对话式交互指南\n🎨 场景1：单图生成\n\n何时使用：只需要一张新图片，无需参考图\n\n对话示例：\n\n用户：帮我生成一张产品图\n助手：好的！请告诉我：\n  1. 产品描述是什么？\n  2. 想要什么风格？（product/lifestyle/minimalist/vintage/dark）\n  3. 图片比例？（默认 1:1）\n\n\n执行方式：收集完信息后，执行以下命令：\n\ncurl -s -X POST \"$BASE_URL/generate-image\" \\\n  -H \"Authorization: Bearer $PONY_SUPABASE_ANON_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"prompt\": \"用户描述的内容\",\n    \"style\": \"minimalist\",\n    \"ratio\": \"1:1\"\n  }'\n\n\n返回格式：\n\n{\n  \"imageUrl\": \"data:image/png;base64,...\",\n  \"prompt\": \"增强后的完整 prompt\"\n}\n\n\n将 imageUrl 展示给用户即可。\n\n🖼️ 场景2：风格复刻（两步流程）\n\n何时使用：有参考图片，想让新图片保持相同视觉风格\n\n对话示例：\n\n用户：我想复刻这张图的风格\n助手：收到参考图！正在分析风格...\n\n（执行 Step 1）\n\n助手：✅ 风格分析完成：\n  - 主色调：暖金色\n  - 光影：柔和侧光\n  - 构图：居中对称\n  \n  请上传你的产品图，我将按此风格生成新图。\n\n\nStep 1 — 分析参考图风格：\n\ncurl -s -X POST \"$BASE_URL/replicate-image\" \\\n  -H \"Authorization: Bearer $PONY_SUPABASE_ANON_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"action\": \"analyze\",\n    \"referenceImages\": [\"参考图URL或Base64\"]\n  }'\n\n\n返回 plan 对象，包含 styleAnalysisSummary、colorSystem、photographyStyle 等。\n\nStep 2 — 用风格生成新图：\n\ncurl -s -X POST \"$BASE_URL/replicate-image\" \\\n  -H \"Authorization: Bearer $PONY_SUPABASE_ANON_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"productImages\": [\"产品图URL或Base64\"],\n    \"plan\": { \"...Step1返回的plan对象...\" },\n    \"ratio\": \"1:1\"\n  }'\n\n\n返回 imageUrl（生成的图片）。\n\n📦 场景3：套图生成（两步流程）\n\n何时使用：需要一组视觉统一的系列图片（如电商主图+详情图）\n\n对话示例：\n\n用户：帮我生成一组电商产品图\n助手：好的！我需要了解：\n  1. 产品名称和描述？\n  2. 需要哪些场景？（主图/场景图/细节图/对比图）\n  3. 整体风格偏好？\n  \n  我会先生成统一设计方案，确认后再逐张生成。\n\n\nStep 1 — 生成统一设计方案：\n\ncurl -s -X POST \"$BASE_URL/generate-suite-plan\" \\\n  -H \"Authorization: Bearer $PONY_SUPABASE_ANON_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"productName\": \"产品名称\",\n    \"productDesc\": \"产品描述\",\n    \"scenes\": [\"主图\", \"场景图\", \"细节图\"],\n    \"style\": \"minimalist\",\n    \"ratio\": \"1:1\"\n  }'\n\n\n返回 plan 对象，包含 overallDesign（配色、字体、光影）和每张图的 images 数组。\n\nStep 2 — 逐张生成：对 plan.images 中每张图，将 overallDesign + 该图信息合并到 prompt，调用：\n\ncurl -s -X POST \"$BASE_URL/generate-image\" \\\n  -H \"Authorization: Bearer $PONY_SUPABASE_ANON_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"prompt\": \"合并 overallDesign 和 images[i] 信息的完整描述\",\n    \"style\": \"minimalist\",\n    \"ratio\": \"1:1\"\n  }'\n\n参数参考\n风格预设 (style)\n值\t说明\t适用场景\nproduct\t专业产品摄影，干净背景，影棚灯光\t电商主图、产品展示\nlifestyle\t生活场景，自然环境，温暖氛围\t社交媒体、品牌故事\nminimalist\t极简风格，白色背景，现代感\t官网、品牌手册\nvintage\t复古美学，暖色调，怀旧感\t文艺品牌、咖啡/手工艺\ndark\t暗调高级感，戏剧性灯光，高对比\t科技产品、奢侈品\n宽高比预设 (ratio)\n值\t适用场景\n1:1\tInstagram 帖子、电商主图\n3:4\t产品详情页\n4:5\tInstagram 竖版帖子\n9:16\t手机竖屏、TikTok/抖音\n4:3\t横版展示\n16:9\t网页横幅、YouTube 封面\n2:3\t海报、杂志\n21:9\t超宽电影画幅\nAI 模型 (model)\n值\t说明\ngoogle/gemini-2.5-flash-image\t默认，快速生成，仅 1K\ngoogle/gemini-3-pro-image-preview\t高质量，支持 2K/4K\n错误处理\nHTTP 状态\t错误信息\t解决方案\n401\tUnauthorized\t检查 PONY_SUPABASE_ANON_KEY 是否已配置\n429\t请求频率超限\t等待几秒后重试\n402\tAI 额度不足\t充值后继续使用\n500\t图片生成失败\t简化 prompt 描述，避免过长内容\n限制\n单次请求超时 60 秒\nBase64 图片大小建议 < 4MB\n生成结果为 Base64 格式\n2K/4K 分辨率仅限 Pro 模型"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/lirule007/pony-image",
    "publisherUrl": "https://clawhub.ai/lirule007/pony-image",
    "owner": "lirule007",
    "version": "1.2.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/pony-image",
    "downloadUrl": "https://openagent3.xyz/downloads/pony-image",
    "agentUrl": "https://openagent3.xyz/skills/pony-image/agent",
    "manifestUrl": "https://openagent3.xyz/skills/pony-image/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/pony-image/agent.md"
  }
}