wechat-claude-code
- Repo stars 315
- Author updated Live
- Author repo wechat-claude-code
- Domain
- Other
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 88 / 100 · community maintained
- Author / version / license
- @Wechat-ggGitHub · no license declared
- Token usage
- Lean
- Setup complexity
- Plug-and-play
- External API key
- Not required
- Operating systems
- macOS
- Runtime requirements
- Node.js >=18
- Permissions
-
- Read-only
- Env read
- Write / modify
- Network behavior
- Local-only
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools，默认拥有全部工具权限。
---
name: wechat-claude-code
description: 通过个人微信与本地 Claude Code 进行对话。 cd ~/.claude/skills/wechat-claude-code 用户提到"微信桥接"、"微信聊天"、"wechat bri…
category: other
runtime: Node.js
---
# wechat-claude-code output preview
## PART A: Task fit
- Use case: 通过个人微信与本地 Claude Code 进行对话。 cd ~/.claude/skills/wechat-claude-code 用户提到"微信桥接"、"微信聊天"、"wechat bridge"、"连接微信"、"微信状态"、"停止微信"等与微信桥接相关的话题时触发。 ls ~/.wechat-claude-code/accounts/*.json 2>/dev/null | head -1 runs entirely locally; runs on Node.js >=18. Works with Claude Code, Cursor, Cline and 23 more..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “前置条件 / 安装 / 触发场景” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “通过个人微信与本地 Claude Code 进行对话。 cd ~/.claude/skills/wechat-claude-code 用户提到"微信桥接"、"微信聊天"、"wechat bridge"、"连接微信"、"微信状态"、"停止微信"等与微信桥接相关的话题时触发。 ls ~/.wechat-claude-code/accounts/*.json 2>/dev/null | head -1 runs entirely locally; runs on Node.js >=18. Works with Claude Code, Cursor, Cline and 23 more.”.
- **02** When the source has headings, the agent prioritizes “前置条件 / 安装 / 触发场景” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, read environment variables, write/modify files; mostly runs locally; usually needs no extra API key.
## Running Rules
- read files, read environment variables, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options. Choose the trigger
The source mentions slash commands such as `/help`, `/clear`, `/status`, `/model`, `/skills`; use them first when your agent supports command triggers.
Provide inputs and boundaries
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, read environment variables, write/modify files.
Validate with a small run
Start with a small task and check whether the result follows “前置条件 / 安装 / 触发场景”. Inspect diffs, logs, previews, or tests before expanding scope.
Review before delivery
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: wechat-claude-code
description: 通过个人微信与本地 Claude Code 进行对话。 cd ~/.claude/skills/wechat-claude-code 用户提到"微信桥接"、"微信聊天"、"wechat bri…
category: other
source: Wechat-ggGitHub/wechat-claude-code
---
# wechat-claude-code
## When to use
- 通过个人微信与本地 Claude Code 进行对话。 cd ~/.claude/skills/wechat-claude-code 用户提到"微信桥接"、"微信聊天"、"wechat bridge"、"连接微信"、"微信状态"、"停止…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “前置条件 / 安装 / 触发场景” and keep inference separate from source facts.
- read files, read environment variables, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies. Evidence boundary and execution chain
The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "wechat-claude-code" {
input -> user goal + target files + boundaries + acceptance criteria
context -> 前置条件 / 安装 / 触发场景
rules -> SKILL.md triggers / order / output contract
runtime -> Node.js | read files, read environment variables, write/modify files | mostly runs locally
guardrails -> usually needs no extra API key + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
}WeChat Claude Code Bridge
通过个人微信与本地 Claude Code 进行对话。
前置条件
- Node.js >= 18
- macOS（daemon 使用 launchd 管理）
- 个人微信账号（需扫码绑定）
- 已安装 Claude Code（
@anthropic-ai/claude-agent-sdk）
安装
cd ~/.claude/skills/wechat-claude-code
npm installpostinstall 脚本会自动执行 npm run build 编译 TypeScript。
触发场景
用户提到"微信桥接"、"微信聊天"、"wechat bridge"、"连接微信"、"微信状态"、"停止微信"等与微信桥接相关的话题时触发。
触发后的执行流程
被触发时，不要直接执行任何操作，先探查当前状态再给出可用操作。
按顺序检查以下状态：
第 1 步：检查是否已安装
cd ~/.claude/skills/wechat-claude-code && test -d node_modules && echo "installed" || echo "not_installed"- 如果
not_installed：提示用户运行cd ~/.claude/skills/wechat-claude-code && npm install安装依赖，然后停止。
第 2 步：检查是否已绑定微信账号
ls ~/.wechat-claude-code/accounts/*.json 2>/dev/null | head -1- 如果没有账号文件：提示用户需要先执行 setup 扫码绑定，询问是否现在执行。
- 如果有账号文件：继续下一步。
第 3 步：检查 daemon 运行状态
cd ~/.claude/skills/wechat-claude-code && npm run daemon -- status第 4 步：根据状态展示信息
如果 daemon 未运行：
微信桥接已绑定但未运行。
可用操作：
setup 重新扫码绑定（换号或过期时使用）
start 启动服务
logs 查看上次运行的日志如果 daemon 正在运行：
微信桥接正在运行（PID: xxx）。
可用操作：
stop 停止服务
restart 重启服务（代码更新后使用）
logs 查看运行日志
微信端命令（直接在微信中发送）：
/help 显示帮助
/clear 清除当前会话，开始新对话
/status 查看当前会话状态
/model 切换 Claude 模型
/skills 查看已安装的 skill如果用户明确指定了操作（如"启动微信"、"停止微信服务"、"看看日志"等），跳过状态展示直接执行对应命令。
子命令参考
所有命令的工作目录为 ~/.claude/skills/wechat-claude-code。
| 命令 | 执行 | 说明 |
|---|---|---|
| setup | npm run setup |
首次安装向导：生成 QR 码 → 微信扫码 → 配置工作目录 |
| start | npm run daemon -- start |
启动 launchd 守护进程（开机自启、自动重启） |
| stop | npm run daemon -- stop |
停止守护进程 |
| restart | npm run daemon -- restart |
重启守护进程 |
| status | npm run daemon -- status |
查看运行状态 |
| logs | npm run daemon -- logs |
查看最近日志（tail -100） |
权限审批
当 Claude 请求执行工具时，微信会收到权限请求消息：
- 回复
y或yes允许 - 回复
n或no拒绝 - 60 秒未回复自动拒绝并通知
数据目录
所有数据存储在 ~/.wechat-claude-code/：
~/.wechat-claude-code/
├── accounts/ # 绑定的微信账号数据（每个账号一个 JSON）
├── config.env # 全局配置（工作目录、模型、权限模式）
├── sessions/ # 会话数据（每个账号一个 JSON）
├── get_updates_buf # 消息轮询同步缓冲
└── logs/ # 运行日志（每日轮转，保留 30 天）
Decide Fit First
Design Intent
How To Use It
Boundaries And Review