{
  "schemaVersion": "1.0",
  "item": {
    "slug": "phoenixclaw-image-gen",
    "name": "phoenixclaw image gen",
    "source": "tencent",
    "type": "skill",
    "category": "内容创作",
    "sourceUrl": "https://clawhub.ai/goforu/phoenixclaw-image-gen",
    "canonicalUrl": "https://clawhub.ai/goforu/phoenixclaw-image-gen",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/phoenixclaw-image-gen",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=phoenixclaw-image-gen",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "scripts/generate.js",
      "scripts/adapters/openrouter.js",
      "scripts/cli/openrouter.js",
      "references/resolution-guide.md",
      "references/extension-guide.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/phoenixclaw-image-gen"
    },
    "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/phoenixclaw-image-gen",
    "agentPageUrl": "https://openagent3.xyz/skills/phoenixclaw-image-gen/agent",
    "manifestUrl": "https://openagent3.xyz/skills/phoenixclaw-image-gen/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/phoenixclaw-image-gen/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": "图像生成辅助",
        "body": "为 OpenClaw 提供原生的图像生成能力，通过文字描述词快速生成高质量图像。"
      },
      {
        "title": "工作流程",
        "body": "用户提示词 (Prompt)\n    ↓\n┌─────────────────────────────────────┐\n│  识别参数：模型、尺寸、比例、路径   │\n└─────────────────────────────────────┘\n    ↓\n┌─────────────────────────────────────┐\n│  调用 OpenRouter 接口 (OpenClaw)    │\n└─────────────────────────────────────┘\n    ↓\n┌─────────────────────────────────────┐\n│  默认模型：seedream-4.5 (Text-to-Image) & Gemini 2.5 (Image-to-Image) │\n└─────────────────────────────────────┘\n    ↓\n┌─────────────────────────────────────┐\n│  原子化写入本地存储 (Safety First)  │\n└─────────────────────────────────────┘\n    ↓\n返回结构化 JSON (Success Payload)"
      },
      {
        "title": "1. 获取 API Key",
        "body": "本技能需要 OpenRouter API Key 才能调用图像生成服务。\n\n访问 OpenRouter 控制台 创建 API Key\n请根据下方指引手动配置环境变量"
      },
      {
        "title": "2. 配置到环境变量",
        "body": "根据 OpenClaw 官方最佳实践，请通过 ~/.openclaw/openclaw.json 配置环境变量：\n\n{\n  skills: {\n    entries: {\n      \"image-generation\": {\n        enabled: true,\n        env: {\n          OPENROUTER_API_KEY: \"sk-or-v1-xxxxxxxx...\"\n        }\n      }\n    }\n  }\n}\n\n或使用 primaryEnv 快捷配置：\n\n{\n  skills: {\n    entries: {\n      \"image-generation\": {\n        enabled: true,\n        apiKey: \"sk-or-v1-xxxxxxxx...\"\n      }\n    }\n  }\n}\n\n配置完成后无需重启，新配置会在下次运行 OpenClaw 时自动生效。"
      },
      {
        "title": "3. 选择默认模型（可选）",
        "body": "本技能默认使用 bytedance-seed/seedream-4.5 作为文本生图模型，google/gemini-2.5-flash-image 作为图生图模型。你可以通过以下方式更改：\n\n方式一：环境变量配置\n在 ~/.openclaw/openclaw.json 中添加：\n\n{\n  skills: {\n    entries: {\n      \"image-generation\": {\n        enabled: true,\n        env: {\n          OPENROUTER_API_KEY: \"sk-or-v1-xxx\",\n          IMAGE_GEN_TEXT_TO_IMAGE_MODEL: \"bytedance-seed/seedream-4.5\",\n          IMAGE_GEN_IMAGE_TO_IMAGE_MODEL: \"google/gemini-2.5-flash-image\"\n        }\n      }\n    }\n  }\n}\n\n本技能默认使用 bytedance-seed/seedream-4.5 模型，你可以通过以下方式更改：\n\n方式一：环境变量配置\n在 ~/.openclaw/openclaw.json 中添加：\n\n{\n  skills: {\n    entries: {\n      \"image-generation\": {\n        enabled: true,\n        env: {\n          OPENROUTER_API_KEY: \"sk-or-v1-xxx\",\n          IMAGE_GEN_IMAGE_TO_IMAGE_MODEL: \"google/gemini-2.5-flash-image\",\n          IMAGE_GEN_TEXT_TO_IMAGE_MODEL: \"bytedance-seed/seedream-4.5\"\n      }\n    }\n  }\n}\n\n方式二：查看可用模型\n\nnode skills/image-generation/scripts/cli/openrouter.js --list-models\n\n方式三：生成时指定模型\n\nnode skills/image-generation/scripts/generate.js \\\n  --prompt \"a futuristic city\" \\\n  --model \"bytedance-seed/seedream-4.5\" \\\n  --i2i-model \"google/gemini-2.5-flash-image\"\n\nnode skills/image-generation/scripts/generate.js \\\n  --prompt \"a futuristic city\" \\\n  --image \"bytedance-seed/seedream-4.5\" \\\n  --model \"google/gemini-2.5-flash-image\"\n\n推荐模型：\n\nbytedance-seed/seedream-4.5 - 默认，高质量图像生成\nanthropic/claude-3.5-sonnet-image - Claude 图像生成\nopenai/dall-e-3 - DALL-E 3"
      },
      {
        "title": "4. 验证配置",
        "body": "node skills/image-generation/scripts/cli/openrouter.js --test\n\n预期输出：\n\n{\n  \"success\": true,\n  \"message\": \"OpenRouter API key is configured. Test passed.\"\n}"
      },
      {
        "title": "仅限 OpenRouter (v1)",
        "body": "本技能在 v1 版本中仅支持通过 OpenRouter 提供商进行图像生成。目前不原生支持 Anthropic、Replicate 或 Stability AI 等直接接口。所有生图请求均通过 OpenRouter 统一中转。"
      },
      {
        "title": "默认模型",
        "body": "文本生图模型 (Text-to-Image): bytedance-seed/seedream-4.5\n图生图模型 (Image-to-Image): google/gemini-2.5-flash-image\n获取地址: OpenRouter | bytedance-seed/seedream-4.5"
      },
      {
        "title": "命令调用",
        "body": "OpenClaw 会通过以下 CLI 方式触发图像生成：\n\n# 基础生成\nnode skills/image-generation/scripts/generate.js \\\n  --prompt \"a futuristic city at sunset\" \\\n  --output \"outputs/city.png\"\n\n# 指定模型、尺寸与比例 (OpenRouter 默认)\nnode skills/image-generation/scripts/generate.js \\\n  --prompt \"cyberpunk landscape\" \\\n  --model \"bytedance-seed/seedream-4.5\" \\\n  --i2i-model \"google/gemini-2.5-flash-image\" \\\n  --size \"2K\" \\\n  --aspect \"16:9\"\n\nnode skills/image-generation/scripts/generate.js \\\n  --prompt \"cyberpunk landscape\" \\\n  --image \"bytedance-seed/seedream-4.5\" \\\n  --model \"google/gemini-2.5-flash-image\" \\\n  --size \"2K\" \\\n  --aspect \"16:9\"\n\n# 通过 OpenClaw 包装器调用\nnode skills/image-generation/scripts/cli/openrouter.js \\\n  --prompt \"abstract oil painting\" \\\n  --size \"1K\"\n\n### 预检测 (Connectivity Check)\n\nOpenClaw 在启动时可运行以下脚本检查 API 连通性：\n\n```bash\nnode skills/image-generation/scripts/cli/openrouter.js --test"
      },
      {
        "title": "参数详解",
        "body": "参数说明必填默认值--prompt图像描述词是---model文本生图模型 ID否bytedance-seed/seedream-4.5--i2i-model图生图模型 ID否google/gemini-2.5-flash-image--input-image图生图输入图片路径否---list-models列出所有可用模型否---size分辨率等级 (1K|2K|4K)否模型默认--aspect宽高比 (如 1:1, 16:9)否1:1--output输出文件路径否.sisyphus/generated/image_<ts>.png\n\n|------|------|------|--------|\n| --prompt | 图像描述词 | 是 | - |\n|| --model | 图生图模型 ID | 否 | google/gemini-2.5-flash-image |\n|| --image | 文本生图模型 ID | 否 | bytedance-seed/seedream-4.5 |\n| --list-models | 列出所有可用模型 | 否 | - |\n| --size | 分辨率等级 (1K|2K|4K) | 否 | 模型默认 |\n| --aspect | 宽高比 (如 1:1, 16:9) | 否 | 1:1 |\n| --output | 输出文件路径 | 否 | .sisyphus/generated/image_<ts>.png |\n| --output | 输出文件路径 | 否 | .sisyphus/generated/image_<ts>.png |"
      },
      {
        "title": "分辨率与尺寸说明",
        "body": "--size 参数格式：\n\n只接受三个字符串值：\"1K\"、\"2K\"、\"4K\"\n不要 使用像素格式如 \"1024x1024\" 或 \"3840x2160\"（OpenRouter API 不接受）\n\n实际输出像素尺寸（由 size 和 aspect 共同决定）：\n\nsizeaspect实际像素说明1K1:11024×1024默认，约 1MP1K16:9~1280×720约 0.9MP2K1:12048×2048约 4MP2K16:9~2560×1440约 3.7MP4K1:14096×4096约 16MP4K16:93840×2160标准 4K UHD\n\n重要限制：\n\n并非所有模型都支持 4K，部分模型最高只支持到 2K\n4K 生成成本更高（约 2 倍于 1K/2K）\n推荐：日常使用 2K（与 1K 同价，质量显著提升）\n\n支持的宽高比：1:1（默认）、2:3、3:2、3:4、4:3、4:5、5:4、9:16、16:9、21:9"
      },
      {
        "title": "退出码说明 (Exit Codes)",
        "body": "符合 cli-contract.md 规范：\n\n代码标签描述0SUCCESS生成成功并已保存到本地1CONFIG_ERROR参数缺失、格式错误或鉴权失败2API_ERROROpenRouter API 调用失败（限流、超时等）3FS_ERROR本地文件系统错误（目录权限、磁盘空间等）"
      },
      {
        "title": "验证与证据 (Verification)",
        "body": "在交付前，请确保通过以下冒烟测试：\n\n环境检查: node skills/image-generation/scripts/cli/openrouter.js --test (返回 success: true)\n基础生成: node skills/image-generation/scripts/generate.js --prompt \"test\" --output \"test.png\"\n路径安全: 确保生成的图片位于 .sisyphus/generated/ 或指定的安全路径下。"
      },
      {
        "title": "资源维护",
        "body": "扩展新 Provider: 参考 references/extension-guide.md\n配置详情: 参考 references/configuration.md\nCLI 规范: 参考 references/cli-contract.md"
      }
    ],
    "body": "图像生成辅助\n\n为 OpenClaw 提供原生的图像生成能力，通过文字描述词快速生成高质量图像。\n\n工作流程\n用户提示词 (Prompt)\n    ↓\n┌─────────────────────────────────────┐\n│  识别参数：模型、尺寸、比例、路径   │\n└─────────────────────────────────────┘\n    ↓\n┌─────────────────────────────────────┐\n│  调用 OpenRouter 接口 (OpenClaw)    │\n└─────────────────────────────────────┘\n    ↓\n┌─────────────────────────────────────┐\n│  默认模型：seedream-4.5 (Text-to-Image) & Gemini 2.5 (Image-to-Image) │\n└─────────────────────────────────────┘\n    ↓\n┌─────────────────────────────────────┐\n│  原子化写入本地存储 (Safety First)  │\n└─────────────────────────────────────┘\n    ↓\n返回结构化 JSON (Success Payload)\n\n安装与配置\n1. 获取 API Key\n\n本技能需要 OpenRouter API Key 才能调用图像生成服务。\n\n访问 OpenRouter 控制台 创建 API Key\n请根据下方指引手动配置环境变量\n2. 配置到环境变量\n\n根据 OpenClaw 官方最佳实践，请通过 ~/.openclaw/openclaw.json 配置环境变量：\n\n{\n  skills: {\n    entries: {\n      \"image-generation\": {\n        enabled: true,\n        env: {\n          OPENROUTER_API_KEY: \"sk-or-v1-xxxxxxxx...\"\n        }\n      }\n    }\n  }\n}\n\n\n或使用 primaryEnv 快捷配置：\n\n{\n  skills: {\n    entries: {\n      \"image-generation\": {\n        enabled: true,\n        apiKey: \"sk-or-v1-xxxxxxxx...\"\n      }\n    }\n  }\n}\n\n\n配置完成后无需重启，新配置会在下次运行 OpenClaw 时自动生效。\n\n3. 选择默认模型（可选）\n\n本技能默认使用 bytedance-seed/seedream-4.5 作为文本生图模型，google/gemini-2.5-flash-image 作为图生图模型。你可以通过以下方式更改：\n\n方式一：环境变量配置 在 ~/.openclaw/openclaw.json 中添加：\n\n{\n  skills: {\n    entries: {\n      \"image-generation\": {\n        enabled: true,\n        env: {\n          OPENROUTER_API_KEY: \"sk-or-v1-xxx\",\n          IMAGE_GEN_TEXT_TO_IMAGE_MODEL: \"bytedance-seed/seedream-4.5\",\n          IMAGE_GEN_IMAGE_TO_IMAGE_MODEL: \"google/gemini-2.5-flash-image\"\n        }\n      }\n    }\n  }\n}\n\n\n本技能默认使用 bytedance-seed/seedream-4.5 模型，你可以通过以下方式更改：\n\n方式一：环境变量配置 在 ~/.openclaw/openclaw.json 中添加：\n\n{\n  skills: {\n    entries: {\n      \"image-generation\": {\n        enabled: true,\n        env: {\n          OPENROUTER_API_KEY: \"sk-or-v1-xxx\",\n          IMAGE_GEN_IMAGE_TO_IMAGE_MODEL: \"google/gemini-2.5-flash-image\",\n          IMAGE_GEN_TEXT_TO_IMAGE_MODEL: \"bytedance-seed/seedream-4.5\"\n      }\n    }\n  }\n}\n\n\n方式二：查看可用模型\n\nnode skills/image-generation/scripts/cli/openrouter.js --list-models\n\n\n方式三：生成时指定模型\n\nnode skills/image-generation/scripts/generate.js \\\n  --prompt \"a futuristic city\" \\\n  --model \"bytedance-seed/seedream-4.5\" \\\n  --i2i-model \"google/gemini-2.5-flash-image\"\n\nnode skills/image-generation/scripts/generate.js \\\n  --prompt \"a futuristic city\" \\\n  --image \"bytedance-seed/seedream-4.5\" \\\n  --model \"google/gemini-2.5-flash-image\"\n\n\n推荐模型：\n\nbytedance-seed/seedream-4.5 - 默认，高质量图像生成\nanthropic/claude-3.5-sonnet-image - Claude 图像生成\nopenai/dall-e-3 - DALL-E 3\n4. 验证配置\nnode skills/image-generation/scripts/cli/openrouter.js --test\n\n\n预期输出：\n\n{\n  \"success\": true,\n  \"message\": \"OpenRouter API key is configured. Test passed.\"\n}\n\n核心配置\n仅限 OpenRouter (v1)\n\n本技能在 v1 版本中仅支持通过 OpenRouter 提供商进行图像生成。目前不原生支持 Anthropic、Replicate 或 Stability AI 等直接接口。所有生图请求均通过 OpenRouter 统一中转。\n\n默认模型\n文本生图模型 (Text-to-Image): bytedance-seed/seedream-4.5\n图生图模型 (Image-to-Image): google/gemini-2.5-flash-image\n获取地址: OpenRouter | bytedance-seed/seedream-4.5\nOpenClaw 调用方式\n命令调用\n\nOpenClaw 会通过以下 CLI 方式触发图像生成：\n\n# 基础生成\nnode skills/image-generation/scripts/generate.js \\\n  --prompt \"a futuristic city at sunset\" \\\n  --output \"outputs/city.png\"\n\n# 指定模型、尺寸与比例 (OpenRouter 默认)\nnode skills/image-generation/scripts/generate.js \\\n  --prompt \"cyberpunk landscape\" \\\n  --model \"bytedance-seed/seedream-4.5\" \\\n  --i2i-model \"google/gemini-2.5-flash-image\" \\\n  --size \"2K\" \\\n  --aspect \"16:9\"\n\nnode skills/image-generation/scripts/generate.js \\\n  --prompt \"cyberpunk landscape\" \\\n  --image \"bytedance-seed/seedream-4.5\" \\\n  --model \"google/gemini-2.5-flash-image\" \\\n  --size \"2K\" \\\n  --aspect \"16:9\"\n\n# 通过 OpenClaw 包装器调用\nnode skills/image-generation/scripts/cli/openrouter.js \\\n  --prompt \"abstract oil painting\" \\\n  --size \"1K\"\n\n### 预检测 (Connectivity Check)\n\nOpenClaw 在启动时可运行以下脚本检查 API 连通性：\n\n```bash\nnode skills/image-generation/scripts/cli/openrouter.js --test\n\n参数详解\n参数\t说明\t必填\t默认值\n--prompt\t图像描述词\t是\t-\n--model\t文本生图模型 ID\t否\tbytedance-seed/seedream-4.5\n--i2i-model\t图生图模型 ID\t否\tgoogle/gemini-2.5-flash-image\n--input-image\t图生图输入图片路径\t否\t-\n--list-models\t列出所有可用模型\t否\t-\n--size\t分辨率等级 (1K|2K|4K)\t否\t模型默认\n--aspect\t宽高比 (如 1:1, 16:9)\t否\t1:1\n--output\t输出文件路径\t否\t.sisyphus/generated/image_<ts>.png\n\n|------|------|------|--------| | --prompt | 图像描述词 | 是 | - | || --model | 图生图模型 ID | 否 | google/gemini-2.5-flash-image | || --image | 文本生图模型 ID | 否 | bytedance-seed/seedream-4.5 | | --list-models | 列出所有可用模型 | 否 | - | | --size | 分辨率等级 (1K|2K|4K) | 否 | 模型默认 | | --aspect | 宽高比 (如 1:1, 16:9) | 否 | 1:1 | | --output | 输出文件路径 | 否 | .sisyphus/generated/image_<ts>.png | | --output | 输出文件路径 | 否 | .sisyphus/generated/image_<ts>.png |\n\n分辨率与尺寸说明\n\n--size 参数格式：\n\n只接受三个字符串值：\"1K\"、\"2K\"、\"4K\"\n不要 使用像素格式如 \"1024x1024\" 或 \"3840x2160\"（OpenRouter API 不接受）\n\n实际输出像素尺寸（由 size 和 aspect 共同决定）：\n\nsize\taspect\t实际像素\t说明\n1K\t1:1\t1024×1024\t默认，约 1MP\n1K\t16:9\t~1280×720\t约 0.9MP\n2K\t1:1\t2048×2048\t约 4MP\n2K\t16:9\t~2560×1440\t约 3.7MP\n4K\t1:1\t4096×4096\t约 16MP\n4K\t16:9\t3840×2160\t标准 4K UHD\n\n重要限制：\n\n并非所有模型都支持 4K，部分模型最高只支持到 2K\n4K 生成成本更高（约 2 倍于 1K/2K）\n推荐：日常使用 2K（与 1K 同价，质量显著提升）\n\n支持的宽高比：1:1（默认）、2:3、3:2、3:4、4:3、4:5、5:4、9:16、16:9、21:9\n\n退出码说明 (Exit Codes)\n\n符合 cli-contract.md 规范：\n\n代码\t标签\t描述\n0\tSUCCESS\t生成成功并已保存到本地\n1\tCONFIG_ERROR\t参数缺失、格式错误或鉴权失败\n2\tAPI_ERROR\tOpenRouter API 调用失败（限流、超时等）\n3\tFS_ERROR\t本地文件系统错误（目录权限、磁盘空间等）\n验证与证据 (Verification)\n\n在交付前，请确保通过以下冒烟测试：\n\n环境检查: node skills/image-generation/scripts/cli/openrouter.js --test (返回 success: true)\n基础生成: node skills/image-generation/scripts/generate.js --prompt \"test\" --output \"test.png\"\n路径安全: 确保生成的图片位于 .sisyphus/generated/ 或指定的安全路径下。\n资源维护\n扩展新 Provider: 参考 references/extension-guide.md\n配置详情: 参考 references/configuration.md\nCLI 规范: 参考 references/cli-contract.md"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/goforu/phoenixclaw-image-gen",
    "publisherUrl": "https://clawhub.ai/goforu/phoenixclaw-image-gen",
    "owner": "goforu",
    "version": "0.2.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/phoenixclaw-image-gen",
    "downloadUrl": "https://openagent3.xyz/downloads/phoenixclaw-image-gen",
    "agentUrl": "https://openagent3.xyz/skills/phoenixclaw-image-gen/agent",
    "manifestUrl": "https://openagent3.xyz/skills/phoenixclaw-image-gen/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/phoenixclaw-image-gen/agent.md"
  }
}