{ "schemaVersion": "1.0", "item": { "slug": "wechat-auto-reply", "name": "wechat-auto-reply", "source": "tencent", "type": "skill", "category": "通讯协作", "sourceUrl": "https://clawhub.ai/bjdzliu/wechat-auto-reply", "canonicalUrl": "https://clawhub.ai/bjdzliu/wechat-auto-reply", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/wechat-auto-reply", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=wechat-auto-reply", "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/wechat-auto-reply" }, "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/wechat-auto-reply", "agentPageUrl": "https://openagent3.xyz/skills/wechat-auto-reply/agent", "manifestUrl": "https://openagent3.xyz/skills/wechat-auto-reply/agent.json", "briefUrl": "https://openagent3.xyz/skills/wechat-auto-reply/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": "WeChat Auto Reply Skill", "body": "半自动回复微信联系人消息（基于AI置信度智能判断），或主动发送指定内容。" }, { "title": "使用 Homebrew（推荐）", "body": "# 一行安装\nbrew install bjdzliu/openclaw/wechat-auto-reply\n\n# 或者两步安装\nbrew tap bjdzliu/openclaw\nbrew install wechat-auto-reply\n\n安装后会自动：\n\n安装所有依赖（cliclick, python@3, pyobjc）\n创建全局命令 wechat-auto-reply\n设置 OpenClaw skill 链接到 ~/.openclaw/workspace/skills/wechat-auto-reply" }, { "title": "💡 使用方式", "body": "# OCR 半自动回复（查看聊天记录，智能判断回复内容）\n# 置信度 > 85% 自动发送，否则弹窗确认\nwechat-auto-reply \"联系人名称\"\n\n# 主动发送（直接发送指定消息，不走 OCR）\nwechat-auto-reply \"联系人名称\" \"消息内容\"\n\n示例：\n\n# 半自动回复模式\nwechat-auto-reply \"小李\" # 如果是\"在吗\"等高置信场景，自动发送\nwechat-auto-reply \"小王\" # 如果是问题类，会弹窗让你确认或修改\n\n# 主动发送模式\nwechat-auto-reply \"小李\" \"什么时候下班\"\nwechat-auto-reply \"小王\" \"今天行情怎么样\"" }, { "title": "功能描述", "body": "两种模式：\n\n半自动回复模式：搜索联系人 → OCR 识别聊天内容 → AI 判断回复\n\n置信度 > 85% → 自动发送\n置信度 ≤ 85% → 弹窗确认（可修改回复内容）\n\n\n主动发送模式：搜索联系人 → 直接发送指定消息" }, { "title": "Homebrew 安装后", "body": "Skill 目录: $(brew --prefix)/share/openclaw/skills/wechat-auto-reply\n用户链接: ~/.openclaw/workspace/skills/wechat-auto-reply\n全局命令: $(brew --prefix)/bin/wechat-auto-reply\n配置文件: ~/.openclaw/workspace/skills/wechat-auto-reply/wechat-dm.applescript" }, { "title": "查看安装路径", "body": "which wechat-auto-reply\nls -la ~/.openclaw/workspace/skills/wechat-auto-reply" }, { "title": "通过 Homebrew 安装（推荐）", "body": "所有依赖会自动安装，无需手动配置。" }, { "title": "手动安装依赖", "body": "依赖工具\n\n工具安装方式用途cliclickbrew install cliclick稳定的鼠标点击screencapturemacOS 内置截图（可通过 /usr/sbin/screencapture 调用）Vision FrameworkmacOS 10.15+OCR 文本识别\n\nPython 依赖\n\npip3 install pyobjc" }, { "title": "1. 激活微信", "body": "tell application \"WeChat\" to activate" }, { "title": "2. 确保前台", "body": "tell app \"System Events\"\n tell process \"WeChat\"\n set frontmost to true\n end tell\nend tell" }, { "title": "3. 搜索联系人", "body": "使用 Cmd+F 打开搜索\n通过剪贴板粘贴联系人名称\n按回车进入聊天" }, { "title": "4. OCR 截图", "body": "使用 macOS Vision Framework 识别聊天内容：\n\nfrom Vision import VNRecognizeTextRequest, VNImageRequestHandler\n\ntheRequest.setRecognitionLanguages([\"zh-Hans\", \"en-US\"])\ntheRequest.setUsesLanguageCorrection(True)" }, { "title": "5. 智能回复判断（带置信度）", "body": "根据聊天内容自动生成回复，每个回复都附带置信度评分：\n\n场景关键词回复内容置信度询问在线\"在吗\"、\"忙吗\"\"在的，什么事？\"95%感谢回复\"谢谢\"、\"感谢\"\"不客气\"95%确认信息\"收到\"+\"好的\"\"好的\"90%投资讨论\"投资\"、\"抄底\"、\"行情\"\"不急，等稳一点\"85%问题咨询\"?\"、\"？\"\"我看看，稍等\"75%一般确认\"好\"、\"OK\"\"好的\"80%时间相关\"明天\"、\"几点\"\"我确认一下，回头告诉你\"70%默认回复其他\"收到\"60%\n\n置信度规则：\n\n≥ 85%：直接自动发送（高置信度场景）\n< 85%：弹窗显示建议回复，需用户确认\n\n可选择\"确认发送\"直接发送\n可选择\"修改回复\"手动编辑内容\n可选择\"取消\"不发送" }, { "title": "6. 发送消息", "body": "点击输入框获取焦点\n粘贴回复内容\n按回车发送" }, { "title": "注意事项", "body": "输入框坐标：默认 {1000, 832}，需根据实际屏幕调整\nOCR 识别：支持中文和英文，设置 [\"zh-Hans\", \"en-US\"]\n等待时间：每次操作后建议等待 0.5-1s\n剪贴板：使用 AppleScript set the clipboard 比 pbcopy 更可靠\n置信度阈值：默认 85%，可在脚本中调整 if confidence > 85 这一行\n确认弹窗：低置信度时会显示完整聊天内容和建议回复，支持手动修改" }, { "title": "修改输入框坐标", "body": "找到配置文件位置：\n\n# Homebrew 安装\nvim ~/.openclaw/workspace/skills/wechat-auto-reply/wechat-dm.applescript\n\n# 或使用 brew 路径\nvim $(brew --prefix)/share/openclaw/skills/wechat-auto-reply/wechat-dm.applescript\n\n修改坐标：\n\ncliclick c:1000,832 # 修改为你的坐标" }, { "title": "调整置信度阈值", "body": "编辑配置文件：\n\nif confidence > 85 then # 修改为你需要的阈值（0-100）\n set autoSend to true" }, { "title": "添加自定义回复规则", "body": "在智能回复判断部分添加：\n\nelse if ocrResult contains \"你的关键词\" then\n set replyText to \"你的回复内容\"\n set confidence to 90 -- 设置置信度" }, { "title": "更新", "body": "brew upgrade wechat-auto-reply" }, { "title": "卸载", "body": "brew uninstall wechat-auto-reply\n\n# 可选：删除 tap\nbrew untap bjdzliu/openclaw" }, { "title": "错误处理", "body": "微信未安装：提示安装微信\n搜索无结果：提示联系人不存在\nOCR 失败：重试截图或使用备用方案" } ], "body": "WeChat Auto Reply Skill\n\n半自动回复微信联系人消息（基于AI置信度智能判断），或主动发送指定内容。\n\n🚀 安装\n使用 Homebrew（推荐）\n# 一行安装\nbrew install bjdzliu/openclaw/wechat-auto-reply\n\n# 或者两步安装\nbrew tap bjdzliu/openclaw\nbrew install wechat-auto-reply\n\n\n安装后会自动：\n\n安装所有依赖（cliclick, python@3, pyobjc）\n创建全局命令 wechat-auto-reply\n设置 OpenClaw skill 链接到 ~/.openclaw/workspace/skills/wechat-auto-reply\n💡 使用方式\n# OCR 半自动回复（查看聊天记录，智能判断回复内容）\n# 置信度 > 85% 自动发送，否则弹窗确认\nwechat-auto-reply \"联系人名称\"\n\n# 主动发送（直接发送指定消息，不走 OCR）\nwechat-auto-reply \"联系人名称\" \"消息内容\"\n\n\n示例：\n\n# 半自动回复模式\nwechat-auto-reply \"小李\" # 如果是\"在吗\"等高置信场景，自动发送\nwechat-auto-reply \"小王\" # 如果是问题类，会弹窗让你确认或修改\n\n# 主动发送模式\nwechat-auto-reply \"小李\" \"什么时候下班\"\nwechat-auto-reply \"小王\" \"今天行情怎么样\"\n\n功能描述\n\n两种模式：\n\n半自动回复模式：搜索联系人 → OCR 识别聊天内容 → AI 判断回复\n置信度 > 85% → 自动发送\n置信度 ≤ 85% → 弹窗确认（可修改回复内容）\n主动发送模式：搜索联系人 → 直接发送指定消息\n📂 文件位置\nHomebrew 安装后\nSkill 目录: $(brew --prefix)/share/openclaw/skills/wechat-auto-reply\n用户链接: ~/.openclaw/workspace/skills/wechat-auto-reply\n全局命令: $(brew --prefix)/bin/wechat-auto-reply\n配置文件: ~/.openclaw/workspace/skills/wechat-auto-reply/wechat-dm.applescript\n查看安装路径\nwhich wechat-auto-reply\nls -la ~/.openclaw/workspace/skills/wechat-auto-reply\n\n环境准备\n通过 Homebrew 安装（推荐）\n\n所有依赖会自动安装，无需手动配置。\n\n手动安装依赖\n依赖工具\n工具\t安装方式\t用途\ncliclick\tbrew install cliclick\t稳定的鼠标点击\nscreencapture\tmacOS 内置\t截图（可通过 /usr/sbin/screencapture 调用）\nVision Framework\tmacOS 10.15+\tOCR 文本识别\nPython 依赖\npip3 install pyobjc\n\n实现原理\n1. 激活微信\ntell application \"WeChat\" to activate\n\n2. 确保前台\ntell app \"System Events\"\n tell process \"WeChat\"\n set frontmost to true\n end tell\nend tell\n\n3. 搜索联系人\n使用 Cmd+F 打开搜索\n通过剪贴板粘贴联系人名称\n按回车进入聊天\n4. OCR 截图\n\n使用 macOS Vision Framework 识别聊天内容：\n\nfrom Vision import VNRecognizeTextRequest, VNImageRequestHandler\n\ntheRequest.setRecognitionLanguages([\"zh-Hans\", \"en-US\"])\ntheRequest.setUsesLanguageCorrection(True)\n\n5. 智能回复判断（带置信度）\n\n根据聊天内容自动生成回复，每个回复都附带置信度评分：\n\n场景\t关键词\t回复内容\t置信度\n询问在线\t\"在吗\"、\"忙吗\"\t\"在的，什么事？\"\t95%\n感谢回复\t\"谢谢\"、\"感谢\"\t\"不客气\"\t95%\n确认信息\t\"收到\"+\"好的\"\t\"好的\"\t90%\n投资讨论\t\"投资\"、\"抄底\"、\"行情\"\t\"不急，等稳一点\"\t85%\n问题咨询\t\"?\"、\"？\"\t\"我看看，稍等\"\t75%\n一般确认\t\"好\"、\"OK\"\t\"好的\"\t80%\n时间相关\t\"明天\"、\"几点\"\t\"我确认一下，回头告诉你\"\t70%\n默认回复\t其他\t\"收到\"\t60%\n\n置信度规则：\n\n≥ 85%：直接自动发送（高置信度场景）\n< 85%：弹窗显示建议回复，需用户确认\n可选择\"确认发送\"直接发送\n可选择\"修改回复\"手动编辑内容\n可选择\"取消\"不发送\n6. 发送消息\n点击输入框获取焦点\n粘贴回复内容\n按回车发送\n注意事项\n输入框坐标：默认 {1000, 832}，需根据实际屏幕调整\nOCR 识别：支持中文和英文，设置 [\"zh-Hans\", \"en-US\"]\n等待时间：每次操作后建议等待 0.5-1s\n剪贴板：使用 AppleScript set the clipboard 比 pbcopy 更可靠\n置信度阈值：默认 85%，可在脚本中调整 if confidence > 85 这一行\n确认弹窗：低置信度时会显示完整聊天内容和建议回复，支持手动修改\n自定义配置\n修改输入框坐标\n\n找到配置文件位置：\n\n# Homebrew 安装\nvim ~/.openclaw/workspace/skills/wechat-auto-reply/wechat-dm.applescript\n\n# 或使用 brew 路径\nvim $(brew --prefix)/share/openclaw/skills/wechat-auto-reply/wechat-dm.applescript\n\n\n修改坐标：\n\ncliclick c:1000,832 # 修改为你的坐标\n\n调整置信度阈值\n\n编辑配置文件：\n\nif confidence > 85 then # 修改为你需要的阈值（0-100）\n set autoSend to true\n\n添加自定义回复规则\n\n在智能回复判断部分添加：\n\nelse if ocrResult contains \"你的关键词\" then\n set replyText to \"你的回复内容\"\n set confidence to 90 -- 设置置信度\n\n更新与卸载\n更新\nbrew upgrade wechat-auto-reply\n\n卸载\nbrew uninstall wechat-auto-reply\n\n# 可选：删除 tap\nbrew untap bjdzliu/openclaw\n\n错误处理\n微信未安装：提示安装微信\n搜索无结果：提示联系人不存在\nOCR 失败：重试截图或使用备用方案" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/bjdzliu/wechat-auto-reply", "publisherUrl": "https://clawhub.ai/bjdzliu/wechat-auto-reply", "owner": "bjdzliu", "version": "1.0.1", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/wechat-auto-reply", "downloadUrl": "https://openagent3.xyz/downloads/wechat-auto-reply", "agentUrl": "https://openagent3.xyz/skills/wechat-auto-reply/agent", "manifestUrl": "https://openagent3.xyz/skills/wechat-auto-reply/agent.json", "briefUrl": "https://openagent3.xyz/skills/wechat-auto-reply/agent.md" } }