[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77PNRTXGDN814MCFXRHTD2S":3,"skill-same:01M77PNRTXGDN814MCFXRHTD2S":45},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":20,"frontMatter":21,"refName":22,"commitSha":23,"skillDirectory":24,"forksCount":25,"repositoryHtmlUrl":26,"repositoryHomepageUrl":27,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":29,"updatedAt":30,"install":31,"resources":44},"01M77PNRTXGDN814MCFXRHTD2S","openclaw-11-in-1-visual-automation-suite",null,"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\u002Fo\u002Fopenclaw-11-in-1-visual-automation-suite\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"# 通用电脑视觉自动化 Skill 体系\n\n这是一个完整的 **基于图像识别+OCR** 的电脑自动化技能框架，包含多个可独立调用的最小执行单元，也可以自由组合成复杂的自动化任务。**本技能包是合集，可以根据需求拆分使用单个单元**。\n\n## 目录结构\n```\ncomputer_skill\u002F\n├─ templates\u002F # 永久模板库（不删除）\n│  ├─ desktop\u002F # 桌面图标模板\n│  ├─ taskbar\u002F # 任务栏图标模板\n│  ├─ system\u002F # 系统通用按钮模板\n│  └─ wechat\u002F # 微信示例模板（以后可新增其他软件）\n└─ temp\u002F # 临时截图（用完立即删除）\n```\n\n## 核心特性\n\n- 🎯 **原子化设计**：所有功能拆分为最小可执行单元，按需组合\n- 🔍 **双重定位**：OCR文字识别优先，模板匹配兜底，兼顾准确性和灵活性\n- 🖱️ **全功能支持**：截图、识别、定位、点击、输入全流程支持\n- ♻️ **支持循环监控**：可以设置自动循环，实现持续监控和重复任务\n- 📝 **简单易扩展**：用 `call 单元名 参数` 格式即可编写新技能\n\n## 所有最小可执行单元清单\n\n| 单元名称 | 固定调用名 | 功能 | 单独调用方式 |\n|---------|-----------|------|------------|\n| 初始化环境 | `init_env` | 创建目录结构、清空 temp、检查模板目录 | `call init_env` |\n| 全屏截图 | `screenshot_full` | 截取整个屏幕保存为 temp\u002Fscreen.png | `call screenshot_full` |\n| 检查截图有效性 | `check_screenshot_valid` | 检查是否黑屏\u002F冻结，无效则唤醒界面 | `call check_screenshot_valid` |\n| 唤醒界面 | `wake_window` | 解决后台不渲染、截图黑屏问题 | `call wake_window` |\n| OCR识别 | `ocr_recognize` | 识别屏幕所有文字与对应坐标 | `call ocr_recognize` |\n| 模板匹配 | `template_match` | 用模板图匹配定位图标\u002F按钮 | `call template_match 分类 模板名称` |\n| 统一定位 | `locate_target` | OCR优先，找不到再用模板匹配，返回目标坐标 | `call locate_target 目标文字 或 分类+模板名` |\n| 鼠标点击 | `mouse_click` | 移动到指定坐标执行点击 | `call mouse_click X Y [点击类型，默认单击]` |\n| 键盘输入 | `keyboard_input` | 定位输入框后输入文字 | `call keyboard_input 目标坐标\u002F描述 输入内容` |\n| 清理临时文件 | `clean_temp` | 删除临时截图，释放空间 | `call clean_temp` |\n| 循环重启 | `loop_restart` | 等待2秒后回到截图重新开始 | `call loop_restart` |\n\n## 使用方法\n\n### 单独调用单元\n**格式**:\n```\ncall [单元调用名] [参数...]\n```\n\n**示例**:\n- 初始化环境：`call init_env`\n- 模板匹配微信图标：`call template_match desktop wechat`\n- 点击坐标(100,200)双击：`call mouse_click 100 200 双击`\n\n### 组合成新任务\n按执行顺序，每行写一个调用指令，即可组合成自定义新任务：\n\n**格式示例（打开微信）**:\n```\n# 任务名称：打开微信\ncall init_env\ncall screenshot_full\ncall check_screenshot_valid\ncall locate_target 微信 desktop wechat\ncall mouse_click {{定位结果X}} {{定位结果Y}} 双击\ncall clean_temp\n```\n\n**组合步骤**:\n1. 先写任务名称和说明（方便后续识别）\n2. 按执行顺序，每行一条 `call 单元名 参数` 指令\n3. 坐标可以用变量 `{{定位结果X}}` `{{定位结果Y}}` 承接上一个单元的输出\n4. 需要循环的话，最后加 `call loop_restart`\n5. 保存自定义技能后，后续直接 `call 技能名称` 调用\n\n## 完整主流程调用示例\n\n```\n# 通用主流程：vision_auto_main\ncall init_env\ncall screenshot_full\ncall check_screenshot_valid\ncall ocr_recognize\n# 如果需要模板匹配，加这行：call template_match 分类 名称\ncall locate_target 目标文字\ncall mouse_click {{X}} {{Y}}\n# 如果需要输入文字，替换上面一行为：call keyboard_input {{X}} {{Y}} 输入内容\ncall clean_temp\n# 需要循环就加：call loop_restart\n```\n\n## 完整主流程说明 (`vision_auto_main`)\n\n执行顺序（从上到下依次执行）：\n\n1.  `init_env`                → 初始化环境（创建目录+清空temp+检查模板目录）\n2.  `screenshot_full`         → 截取全屏保存为temp\u002Fscreen.png\n3.  `check_screenshot_valid`  → 检查截图是否有效\n    ├─ 有效 → 继续下一步\n    └─ 无效 → 调用 `wake_window` 后回到 step 2 重试\n4.  `ocr_recognize`           → OCR识别屏幕所有文字与坐标\n5.  `template_match`          → 如果需要，进行模板图匹配定位\n6.  `locate_target`           → 统一定位目标（OCR优先，模板补充）\n7.  分支执行：\n    ├─ 需要鼠标点击 → `mouse_click`   → 点击目标坐标\n    └─ 需要文字输入 → `keyboard_input` → 输入目标文字\n8.  `clean_temp`              → 删除临时截图，不保留任何临时文件\n9.  `loop_restart`（可选）    → 如果需要循环监控\u002F重复任务，执行循环重启\n    └─ 不需要循环 → 流程结束\n\n## 运行规则\n1. **temp目录**：只允许存在一张截图，每次运行前必须清空temp目录\n2. **templates目录**：目录内的图片永久保存，不删除\n\n## 依赖\n- Python 3.x\n- OpenCV (模板匹配)\n- pytesseract \u002F 其他OCR引擎\n- pyautogui (鼠标键盘控制)\n- PIL (图像处理)\n",{},"master","4aa004da461d820f4ea5499e58eb8d196cf99016","community\u002Fclawhub\u002Fo\u002Fopenclaw-11-in-1-visual-automation-suite",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":7,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add Lord1Egypt\u002Fawesome-skill-forge --skill openclaw-11-in-1-visual-automation-suite",{"tool":37,"command":38},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill openclaw-11-in-1-visual-automation-suite",{"tool":40,"command":41},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill openclaw-11-in-1-visual-automation-suite","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fo\u002Fopenclaw-11-in-1-visual-automation-suite\u002FSKILL.md",true,[],[46,53,60,67,74,81],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":18},"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":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":18},"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":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":18},"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":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":18},"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":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":18},"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":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":18},"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",[],[]]