[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77JFSEC2NS4PPKHD1DBBXFW":3,"skill-same:01M77JFSEC2NS4PPKHD1DBBXFW":52},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":29,"commitSha":30,"skillDirectory":31,"forksCount":32,"repositoryHtmlUrl":33,"repositoryHomepageUrl":34,"ownerHtmlUrl":35,"ownerBlogUrl":6,"ownerDescription":36,"updatedAt":37,"install":38,"resources":51},"01M77JFSEC2NS4PPKHD1DBBXFW","image_gen_coze",null,"Image Generation via Coze | 基于 Coze 的图像生成技能\nGenerate images using Coze workflows. 使用 Seedream 4.5 model.\nHandles parameter building and result parsing. 负责参数构建和结果解析。\nRequires coze-workflow skill. 需要 coze-workflow 技能。","Lord1Egypt\u002Fawesome-skill-forge","Lord1Egypt","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F99746359?v=4","01M7592YDNT0XK9WJ0T2MQVPDN","Mohamed Mounir Ali AL Keshita","01M75GRFNHC8VZNWEB8DKDE433",3,"MIT","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fi\u002Fimage-gen-coze\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: image_gen_coze\nversion: 1.1.3\ndescription: |\n  Image Generation via Coze | 基于 Coze 的图像生成技能\n  Generate images using Coze workflows. 使用 Seedream 4.5 model.\n  Handles parameter building and result parsing. 负责参数构建和结果解析。\n  Requires coze-workflow skill. 需要 coze-workflow 技能。\nhomepage: https:\u002F\u002Fwww.coze.cn\ndependencies: [\"coze_workflow v1.1.1+\"]\n---\n\n# Image Gen Coze | 图像生成技能\n\n基于 Coze 工作流的图像生成技能。使用 Seedream 4.5 模型。**依赖**: `coze-workflow` 技能（基础层）。\n\nImage generation skill based on Coze workflow. Uses Seedream 4.5 model. **Requires**: `coze-workflow` skill (base layer).\n\n---\n\n## 依赖关系 \u002F Dependencies\n\n**必需 \u002F Required**：\n- `coze-workflow` v1.1.1+ - Coze 工作流执行的基础技能 \u002F Base skill for Coze workflow execution\n\n**架构 \u002F Architecture**：\n- `coze-workflow`（基础层 \u002F base）→ `image-gen-coze`（业务层 \u002F business layer）\n\n---\n\n## 功能特性 \u002F Features\n\n| 特性 \u002F Feature | 说明 \u002F Description |\n|---------------|-------------------|\n| 模型 \u002F Model | Seedream 4.5 |\n| 输入 \u002F Input | 单一 Prompt \u002F Single prompt |\n| 输出 \u002F Output | 图片 URL \u002F Image URL |\n| 限制 \u002F Limit | 30秒\u002F次 \u002F 30 seconds per request |\n\n---\n\n## 配置 \u002F Configuration\n\n`~\u002F.openclaw\u002Fskills\u002Fimage_gen_coze\u002Fconfig.json`：\n\n```json\n{\n  \"workflow_id\": \"7613773741864550434\"\n}\n```\n\n依赖技能配置 \u002F Dependency config：`~\u002F.openclaw\u002Fskills\u002Fcoze_workflow\u002Fconfig.json`\n\n---\n\n## 使用方式 \u002F Usage\n\n### 输入 \u002F Input\n\n```json\n{\n  \"prompt\": \"一只可爱的橘猫在窗台上晒太阳，温暖的光线，写实摄影风格 --ar 1:1\"\n}\n```\n\n### 完整调用流程 \u002F Full Workflow\n\n```bash\n#!\u002Fbin\u002Fbash\n\n# 1. 读取配置 \u002F Read config\nWORKFLOW_ID=$(jq -r '.workflow_id' ~\u002F.openclaw\u002Fskills\u002Fimage_gen_coze\u002Fconfig.json)\nCOZE_CONFIG=~\u002F.openclaw\u002Fskills\u002Fcoze_workflow\u002Fconfig.json\nAPI_KEY=$(jq -r '.api_key' \"$COZE_CONFIG\")\nBASE_URL=$(jq -r '.base_url \u002F\u002F \"https:\u002F\u002Fapi.coze.cn\"' \"$COZE_CONFIG\")\n\n# 2. 构建 prompt \u002F Build prompt\nPROMPT=\"一只可爱的橘猫在窗台上晒太阳，温暖的光线，写实摄影风格 --ar 1:1\"\n\n# 3. 调用 coze_workflow 执行 \u002F Execute\nresult=$(curl -s -X POST \"${BASE_URL}\u002Fv1\u002Fworkflow\u002Fstream_run\" \\\n  -H \"Authorization: Bearer ${API_KEY}\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d \"{\n    \\\"workflow_id\\\": \\\"${WORKFLOW_ID}\\\",\n    \\\"parameters\\\": {\n      \\\"prompt\\\": \\\"${PROMPT}\\\"\n    }\n  }\" | grep -E \"^event: Message$\" -A1 | tail -1)\n\n# 4. 解析结果 \u002F Parse result\ndata=$(echo \"$result\" | sed 's\u002F^data: \u002F\u002F')\ncontent=$(echo \"$data\" | jq -r '.content')\nimage_url=$(echo \"$content\" | jq -r '.output \u002F\u002F empty')\n\n# 5. 下载并保存 \u002F Download and save\nif [ -n \"$image_url\" ]; then\n  SAVE_DIR=\".\u002Fgenerated_images\"\n  mkdir -p \"$SAVE_DIR\"\n  \n  TIMESTAMP=$(date +%Y%m%d_%H%M%S)\n  PREFIX=$(echo \"$PROMPT\" | sed 's\u002F[^a-zA-Z0-9\\u4e00-\\u9fa5]\u002F\u002Fg' | cut -c1-10)\n  FILENAME=\"${TIMESTAMP}_${PREFIX}.png\"\n  FILEPATH=\"${SAVE_DIR}\u002F${FILENAME}\"\n  \n  curl -s -L \"$image_url\" -o \"$FILEPATH\"\nfi\n```\n\n---\n\n## 文件保存约定 \u002F File Save Convention\n\n### 保存路径 \u002F Save Path\n\n```\n.\u002Fgenerated_images\u002F\n```\n\n**实际路径示例 \u002F Example paths**:\n- Agent A: `~\u002F.openclaw\u002Fworkspace-agentA\u002Fgenerated_images\u002F`\n- Agent B: `~\u002F.openclaw\u002Fworkspace-agentB\u002Fgenerated_images\u002F`\n\n### 命名规则 \u002F Naming Rule\n\n```\n{时间戳 \u002F Timestamp}_{prompt前缀 \u002F Prefix}.png\n\n示例 \u002F Example：\n20260305_233045_一只可爱的橘猫.png\n```\n\n| 参数 \u002F Parameter | 说明 \u002F Description | 示例 \u002F Example |\n|-----------------|-------------------|---------------|\n| `TIMESTAMP` | 生成时间 \u002F Generation time | 20260305_233045 |\n| `PREFIX` | Prompt 前10字符 \u002F First 10 chars | 一只可爱的橘猫 |\n\n---\n\n## 提示词写法 \u002F Prompt Writing\n\n### 尺寸 \u002F Aspect Ratio\n\n在 prompt 末尾添加 `--ar 比例`：\n\n| 标签 \u002F Tag | 尺寸 \u002F Size |\n|-----------|------------|\n| `--ar 1:1` | 1024×1024 |\n| `--ar 16:9` | 1024×576 |\n| `--ar 9:16` | 576×1024 |\n\n### 风格关键词 \u002F Style Keywords\n\n- `写实摄影风格` - 照片级真实 \u002F Photorealistic\n- `动漫风格` - 日式动漫 \u002F Anime style\n- `3D渲染` - 三维立体 \u002F 3D render\n- `赛博朋克` - 科幻霓虹 \u002F Cyberpunk\n\n---\n\n## 速率限制 \u002F Rate Limit\n\n**30秒\u002F次** - 建议实现调用间隔检查 \u002F Implement call interval checking.\n\n---\n\n## 版本历史 \u002F Changelog\n\n- **v1.1.3**: 添加中英文对照 \u002F Add bilingual support\n- **v1.1.1**: 明确职责，负责参数构建和结果解析 \u002F Clarify responsibilities\n- **v1.1.0**: Seedream 4.5 模型 \u002F Seedream 4.5 model\n- **v1.0.0**: 初始版本 \u002F Initial version\n","# Image Gen Coze | 图像生成技能\n\n基于 Coze 工作流的图像生成技能。使用 Seedream 4.5 模型。**依赖**: `coze-workflow` 技能（基础层）。\n\nImage generation skill based on Coze workflow. Uses Seedream 4.5 model. **Requires**: `coze-workflow` skill (base layer).\n\n---\n\n## 依赖关系 \u002F Dependencies\n\n**必需 \u002F Required**：\n- `coze-workflow` v1.1.1+ - Coze 工作流执行的基础技能 \u002F Base skill for Coze workflow execution\n\n**架构 \u002F Architecture**：\n- `coze-workflow`（基础层 \u002F base）→ `image-gen-coze`（业务层 \u002F business layer）\n\n---\n\n## 功能特性 \u002F Features\n\n| 特性 \u002F Feature | 说明 \u002F Description |\n|---------------|-------------------|\n| 模型 \u002F Model | Seedream 4.5 |\n| 输入 \u002F Input | 单一 Prompt \u002F Single prompt |\n| 输出 \u002F Output | 图片 URL \u002F Image URL |\n| 限制 \u002F Limit | 30秒\u002F次 \u002F 30 seconds per request |\n\n---\n\n## 配置 \u002F Configuration\n\n`~\u002F.openclaw\u002Fskills\u002Fimage_gen_coze\u002Fconfig.json`：\n\n```json\n{\n  \"workflow_id\": \"7613773741864550434\"\n}\n```\n\n依赖技能配置 \u002F Dependency config：`~\u002F.openclaw\u002Fskills\u002Fcoze_workflow\u002Fconfig.json`\n\n---\n\n## 使用方式 \u002F Usage\n\n### 输入 \u002F Input\n\n```json\n{\n  \"prompt\": \"一只可爱的橘猫在窗台上晒太阳，温暖的光线，写实摄影风格 --ar 1:1\"\n}\n```\n\n### 完整调用流程 \u002F Full Workflow\n\n```bash\n#!\u002Fbin\u002Fbash\n\n# 1. 读取配置 \u002F Read config\nWORKFLOW_ID=$(jq -r '.workflow_id' ~\u002F.openclaw\u002Fskills\u002Fimage_gen_coze\u002Fconfig.json)\nCOZE_CONFIG=~\u002F.openclaw\u002Fskills\u002Fcoze_workflow\u002Fconfig.json\nAPI_KEY=$(jq -r '.api_key' \"$COZE_CONFIG\")\nBASE_URL=$(jq -r '.base_url \u002F\u002F \"https:\u002F\u002Fapi.coze.cn\"' \"$COZE_CONFIG\")\n\n# 2. 构建 prompt \u002F Build prompt\nPROMPT=\"一只可爱的橘猫在窗台上晒太阳，温暖的光线，写实摄影风格 --ar 1:1\"\n\n# 3. 调用 coze_workflow 执行 \u002F Execute\nresult=$(curl -s -X POST \"${BASE_URL}\u002Fv1\u002Fworkflow\u002Fstream_run\" \\\n  -H \"Authorization: Bearer ${API_KEY}\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d \"{\n    \\\"workflow_id\\\": \\\"${WORKFLOW_ID}\\\",\n    \\\"parameters\\\": {\n      \\\"prompt\\\": \\\"${PROMPT}\\\"\n    }\n  }\" | grep -E \"^event: Message$\" -A1 | tail -1)\n\n# 4. 解析结果 \u002F Parse result\ndata=$(echo \"$result\" | sed 's\u002F^data: \u002F\u002F')\ncontent=$(echo \"$data\" | jq -r '.content')\nimage_url=$(echo \"$content\" | jq -r '.output \u002F\u002F empty')\n\n# 5. 下载并保存 \u002F Download and save\nif [ -n \"$image_url\" ]; then\n  SAVE_DIR=\".\u002Fgenerated_images\"\n  mkdir -p \"$SAVE_DIR\"\n  \n  TIMESTAMP=$(date +%Y%m%d_%H%M%S)\n  PREFIX=$(echo \"$PROMPT\" | sed 's\u002F[^a-zA-Z0-9\\u4e00-\\u9fa5]\u002F\u002Fg' | cut -c1-10)\n  FILENAME=\"${TIMESTAMP}_${PREFIX}.png\"\n  FILEPATH=\"${SAVE_DIR}\u002F${FILENAME}\"\n  \n  curl -s -L \"$image_url\" -o \"$FILEPATH\"\nfi\n```\n\n---\n\n## 文件保存约定 \u002F File Save Convention\n\n### 保存路径 \u002F Save Path\n\n```\n.\u002Fgenerated_images\u002F\n```\n\n**实际路径示例 \u002F Example paths**:\n- Agent A: `~\u002F.openclaw\u002Fworkspace-agentA\u002Fgenerated_images\u002F`\n- Agent B: `~\u002F.openclaw\u002Fworkspace-agentB\u002Fgenerated_images\u002F`\n\n### 命名规则 \u002F Naming Rule\n\n```\n{时间戳 \u002F Timestamp}_{prompt前缀 \u002F Prefix}.png\n\n示例 \u002F Example：\n20260305_233045_一只可爱的橘猫.png\n```\n\n| 参数 \u002F Parameter | 说明 \u002F Description | 示例 \u002F Example |\n|-----------------|-------------------|---------------|\n| `TIMESTAMP` | 生成时间 \u002F Generation time | 20260305_233045 |\n| `PREFIX` | Prompt 前10字符 \u002F First 10 chars | 一只可爱的橘猫 |\n\n---\n\n## 提示词写法 \u002F Prompt Writing\n\n### 尺寸 \u002F Aspect Ratio\n\n在 prompt 末尾添加 `--ar 比例`：\n\n| 标签 \u002F Tag | 尺寸 \u002F Size |\n|-----------|------------|\n| `--ar 1:1` | 1024×1024 |\n| `--ar 16:9` | 1024×576 |\n| `--ar 9:16` | 576×1024 |\n\n### 风格关键词 \u002F Style Keywords\n\n- `写实摄影风格` - 照片级真实 \u002F Photorealistic\n- `动漫风格` - 日式动漫 \u002F Anime style\n- `3D渲染` - 三维立体 \u002F 3D render\n- `赛博朋克` - 科幻霓虹 \u002F Cyberpunk\n\n---\n\n## 速率限制 \u002F Rate Limit\n\n**30秒\u002F次** - 建议实现调用间隔检查 \u002F Implement call interval checking.\n\n---\n\n## 版本历史 \u002F Changelog\n\n- **v1.1.3**: 添加中英文对照 \u002F Add bilingual support\n- **v1.1.1**: 明确职责，负责参数构建和结果解析 \u002F Clarify responsibilities\n- **v1.1.0**: Seedream 4.5 模型 \u002F Seedream 4.5 model\n- **v1.0.0**: 初始版本 \u002F Initial version\n",{"name":5,"version":24,"homepage":25,"description":26,"dependencies":27},"1.1.3","https:\u002F\u002Fwww.coze.cn","Image Generation via Coze | 基于 Coze 的图像生成技能\nGenerate images using Coze workflows. 使用 Seedream 4.5 model.\nHandles parameter building and result parsing. 负责参数构建和结果解析。\nRequires coze-workflow skill. 需要 coze-workflow 技能。\n",[28],"coze_workflow v1.1.1+","master","4aa004da461d820f4ea5499e58eb8d196cf99016","community\u002Fclawhub\u002Fi\u002Fimage-gen-coze",0,"https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge","https:\u002F\u002Fskill-explorer-rho.vercel.app","https:\u002F\u002Fgithub.com\u002FLord1Egypt","Unbreakable. Unstoppable. Unmatched⚡.\r\n Speaker of machine tongues 🤖  | World-builder of decentralized dreams 🌐 | Defender of the digital realm🛡️.","2026-06-10 08:21:01",{"source":8,"skillName":5,"commands":39,"prompt":49,"zipAvailable":50},[40,43,46],{"tool":41,"command":42},"npx","npx skills add Lord1Egypt\u002Fawesome-skill-forge --skill image_gen_coze",{"tool":44,"command":45},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill image_gen_coze",{"tool":47,"command":48},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill image_gen_coze","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fi\u002Fimage-gen-coze\u002FSKILL.md",true,[],[53,60,67,74,81,88],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M785WKJB99G3STR1NF9NRTJW","youtube-content","YouTube transcripts to summaries, threads, blogs.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fyoutube-content\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M785WEFHB0G2S9YA6EPR3H0E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fxurl\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M785W98EDN4EFJXJPMQEHCRC","touchdesigner-mcp","Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftouchdesigner-mcp\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M785W5S9FP3QBH2V191E025P","test-driven-development","TDD: enforce RED-GREEN-REFACTOR, tests before code.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M785W2AS08NSSH9YATCV6FJB","teams-meeting-pipeline","Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fteams-meeting-pipeline\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M785VXKW4T34BTP1SCHW1R7F","systematic-debugging","4-phase root cause debugging: understand bugs before fixing.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fsystematic-debugging\u002FSKILL.md",[],[]]