wechat-auto-reply半自动回复微信联系人消息（置信度>85%自动发送，否则确认），或主动发送指定内容。使用方式：wechat-auto-reply "联系人名称" 或 wechat-auto-reply "联系人名称" "消息内容
Install via ClawdBot CLI:
clawdbot install bjdzliu/wechat-auto-reply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。
# 一行安装
brew install bjdzliu/openclaw/wechat-auto-reply
# 或者两步安装
brew tap bjdzliu/openclaw
brew install wechat-auto-reply安装后会自动：
cliclick, python@3, pyobjc）wechat-auto-reply~/.openclaw/workspace/skills/wechat-auto-reply# OCR 半自动回复（查看聊天记录，智能判断回复内容）
# 置信度 > 85% 自动发送，否则弹窗确认
wechat-auto-reply "联系人名称"
# 主动发送（直接发送指定消息，不走 OCR）
wechat-auto-reply "联系人名称" "消息内容"示例：
# 半自动回复模式
wechat-auto-reply "小李" # 如果是"在吗"等高置信场景，自动发送
wechat-auto-reply "小王" # 如果是问题类，会弹窗让你确认或修改
# 主动发送模式
wechat-auto-reply "小李" "什么时候下班"
wechat-auto-reply "小王" "今天行情怎么样"两种模式：
$(brew --prefix)/share/openclaw/skills/wechat-auto-reply~/.openclaw/workspace/skills/wechat-auto-reply$(brew --prefix)/bin/wechat-auto-reply~/.openclaw/workspace/skills/wechat-auto-reply/wechat-dm.applescriptwhich wechat-auto-reply
ls -la ~/.openclaw/workspace/skills/wechat-auto-reply所有依赖会自动安装，无需手动配置。
| 工具 | 安装方式 | 用途 |
|------|----------|------|
| cliclick | brew install cliclick | 稳定的鼠标点击 |
| screencapture | macOS 内置 | 截图（可通过 /usr/sbin/screencapture 调用） |
| Vision Framework | macOS 10.15+ | OCR 文本识别 |
pip3 install pyobjctell application "WeChat" to activatetell app "System Events"
tell process "WeChat"
set frontmost to true
end tell
end tellCmd+F 打开搜索使用 macOS Vision Framework 识别聊天内容：
from Vision import VNRecognizeTextRequest, VNImageRequestHandler
theRequest.setRecognitionLanguages(["zh-Hans", "en-US"])
theRequest.setUsesLanguageCorrection(True)根据聊天内容自动生成回复，每个回复都附带置信度评分：
| 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% |
置信度规则：
{1000, 832}，需根据实际屏幕调整["zh-Hans", "en-US"]set the clipboard 比 pbcopy 更可靠if confidence > 85 这一行找到配置文件位置：
# Homebrew 安装
vim ~/.openclaw/workspace/skills/wechat-auto-reply/wechat-dm.applescript
# 或使用 brew 路径
vim $(brew --prefix)/share/openclaw/skills/wechat-auto-reply/wechat-dm.applescript修改坐标：
cliclick c:1000,832 # 修改为你的坐标编辑配置文件：
if confidence > 85 then # 修改为你需要的阈值（0-100）
set autoSend to true在智能回复判断部分添加：
else if ocrResult contains "你的关键词" then
set replyText to "你的回复内容"
set confidence to 90 -- 设置置信度brew upgrade wechat-auto-replybrew uninstall wechat-auto-reply
# 可选：删除 tap
brew untap bjdzliu/openclawGenerated Mar 1, 2026
Businesses can use this skill to semi-automate responses to common customer inquiries on WeChat, such as order confirmations or thank-you messages, reducing manual effort while maintaining accuracy with confidence-based checks. It's ideal for e-commerce or service industries handling high message volumes.
Professionals like freelancers or small business owners can automate replies to routine messages, such as availability checks or appointment confirmations, allowing them to focus on core tasks. The OCR and AI features ensure context-aware responses without full automation risks.
Social media managers can use this skill to handle basic interactions on WeChat, like responding to common questions or sending scheduled updates, streamlining community engagement. The active send mode supports broadcasting messages to specific contacts efficiently.
Educational institutions or tutors can automate replies to student inquiries on WeChat, such as class schedules or assignment details, providing quick support while using confidence thresholds to avoid errors in complex queries.
Clinics or healthcare providers can send automated appointment reminders or basic health tips to patients via WeChat, with the semi-auto mode ensuring sensitive information is only sent after user confirmation for safety.
Offer this skill as part of a subscription-based service for businesses, providing regular updates, custom rule configurations, and premium support. Revenue can be generated through tiered pricing based on usage or features like higher confidence thresholds.
Provide a free basic version with limited features, such as lower confidence thresholds or fewer custom rules, and charge for advanced capabilities like bulk messaging or integration with other platforms. This model attracts individual users and upsells to enterprises.
Offer consulting services to businesses for customizing the skill, such as adjusting OCR settings, adding industry-specific reply rules, or integrating with existing CRM systems. Revenue comes from one-time project fees or ongoing maintenance contracts.
💬 Integration Tip
Ensure WeChat is installed and active on macOS, and adjust input box coordinates in the script to match your screen resolution for reliable operation.
iMessage/SMS CLI for listing chats, history, watch, and sending.
Use when you need to control Discord from Clawdbot via the discord tool: send messages, react, post or upload stickers, upload emojis, run polls, manage threads/pins/search, fetch permissions or member/role/channel info, or handle moderation actions in Discord DMs or channels.
Use when you need to control Slack from Clawdbot via the slack tool, including reacting to messages or pinning/unpinning items in Slack channels or DMs.
Send WhatsApp messages to other people or search/sync WhatsApp history via the wacli CLI (not for normal user chats).
Build or update the BlueBubbles external channel plugin for Clawdbot (extension package, REST send/probe, webhook inbound).
OpenClaw skill for designing Telegram Bot API workflows and command-driven conversations using direct HTTPS requests (no SDKs).