Serial logo

Serial

Community
zhinkgit
serial

嵌入式串口调试工具,用于扫描串口、实时监控、发送数据、记录日志和 Hex 查看。 当用户提到串口、COM 口、UART、AT 命令调试、波特率、Hex 串流、串口抓日志、 串口监控、查看 MCU 输出、二进制协议联调时自动触发,也兼容 /serial 显式调用。 即使用户只是说"看看串口输出"、"发个 AT 命令"或"抓一下日志",只要上下文涉及 串口通信就应触发此 skill。

Overview

Publisherzhinkgit
Repositoryembeddedskills
Skill nameserial
Stars
739
Forks
94
Bundled files
9
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 9 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by zhinkgit on GitHub. Read the source before you install it.

Installation

Install the Serial AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/zhinkgit/embeddedskills/tree/main/serial
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/zhinkgit/embeddedskills.git /tmp/embeddedskills
mkdir -p .claude/skills
cp -r /tmp/embeddedskills/serial .claude/skills/serial
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Serial in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Serial on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Serial is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Serial — 嵌入式串口调试工具

统一封装端口发现、实时监控、数据发送、日志记录和 Hex 查看能力。

配置

环境级配置 (skill/config.json)

serial skill 的环境级配置目前为空对象 {},因为串口参数属于工程级配置,统一在工作区的 .embeddedskills/config.json 中管理。

工程级配置 (.embeddedskills/config.json)

工作区下的 .embeddedskills/config.json 存放工程级串口配置:

json
{
  "serial": {
    "port": "",
    "baudrate": 115200,
    "bytesize": 8,
    "parity": "none",
    "stopbits": 1,
    "encoding": "utf-8",
    "timeout_sec": 1.0,
    "log_dir": ".embeddedskills/logs/serial"
  }
}
字段说明默认值
port串口号,如 COM3""
baudrate波特率115200
bytesize数据位8
parity校验位:none/even/odd/mark/spacenone
stopbits停止位:1/1.5/21
encoding文本编码utf-8
timeout_sec读写超时(秒)1.0
log_dir日志输出目录.embeddedskills/logs/serial

参数解析优先级

  1. CLI 参数 (--port, --baudrate 等) - 最高优先级
  2. 工程级配置 (.embeddedskills/config.json 中的 serial 部分)
  3. 状态文件 (.embeddedskills/state.json 中的历史记录)
  4. 默认值 - 最低优先级

自动扫描行为

当未指定 port 时,脚本会自动扫描系统串口:

  • 若只找到一个串口,自动使用该端口并写入工程配置
  • 若找到多个串口,返回候选列表让用户选择(通过 --port 指定)
  • 若未找到串口,提示错误

子命令

子命令用途风险
scan扫描可用串口低
monitor实时查看文本输出低
send发送文本或 Hex 数据中
hex实时查看二进制流低
log保存串口日志到文件低

执行流程

  1. 检查 pyserial 是否可用,未安装时提示 pip install pyserial
  2. 按优先级解析参数:CLI > 工程级配置 > 状态文件 > 默认值
  3. 无子命令时默认执行 scan
  4. monitor / send / hex / log 使用解析后的连接参数
  5. 若未指定 port,自动扫描系统串口:
    • 唯一候选:自动使用并写入工程配置
    • 多候选:返回列表让用户选择
  6. 成功执行后,将确认的参数写回工程配置
  7. 运行对应脚本并输出结构化结果
  8. 失败时优先反馈端口占用、驱动、波特率和编码问题

脚本调用

所有脚本位于 skill 目录的 scripts/ 下,通过 python 直接调用。 脚本会按优先级从 CLI 参数、工程级配置、状态文件中读取参数。

bash
# 扫描串口
python scripts/serial_scan.py [--filter <关键词>] [--json]

# 实时监控
python scripts/serial_monitor.py [--port <串口>] [--baudrate <波特率>] [--timestamp] [--filter <regex>] [--timeout <秒>] [--json]

# 发送数据
python scripts/serial_send.py [--port <串口>] [--baudrate <波特率>] <data> [--hex] [--crlf] [--repeat <次>] [--wait-response] [--json]

# Hex 查看
python scripts/serial_hex.py [--port <串口>] [--baudrate <波特率>] [--width <列>] [--timeout <秒>] [--json]

# 日志记录
python scripts/serial_log.py [--port <串口>] [--baudrate <波特率>] [--output <文件>] [--duration <秒>] [--format text|csv|json] [--json]

输出格式

单次命令返回标准 JSON:

json
{
  "status": "ok",
  "action": "scan",
  "summary": "发现 2 个串口",
  "details": { ... }
}

持续命令(monitor --json、hex --json)输出 JSON Lines,结束摘要写入 stderr。

错误输出:

json
{
  "status": "error",
  "action": "monitor",
  "error": { "code": "port_busy", "message": "串口被其他程序占用" }
}

串口多路复用 (Mux)

当需要同时使用 minicom(或其他串口工具)和 skill 脚本访问同一个串口设备时,可以通过 mux 后台服务实现多路复用。

依赖

  • socat — apt install socat / pacman -S socat

架构

                   ┌──────────────────┐
                   │   Real Hardware   │
                   │   /dev/ttyUSB0    │
                   └────────┬─────────┘
                            │
                   ┌────────▼─────────┐
                   │ Python mux server │
                   │ TCP-LISTEN:20001  │  单串口读者 + 广播
                   └────────┬─────────┘
                            │
            ┌───────────────┼───────────────┐
            │               │               │
   ┌────────▼──────┐ ┌─────▼──────┐ ┌──────▼────────┐
   │  socat PTY    │ │ skill      │ │ skill         │
   │ /tmp/serial_  │ │ monitor    │ │ send/log/hex  │
   │ mux_vserial   │ │ socket://  │ │ socket://     │
   └───────┬───────┘ └────────────┘ └───────────────┘
           │
   ┌───────▼───────┐
   │   minicom     │
   │  (用户侧)      │
   └───────────────┘
  • Layer 1: Python mux 进程独占打开真实串口,暴露 TCP server,并把串口 RX 广播给所有客户端
  • Layer 2: socat 作为 TCP 客户端创建虚拟 PTY /tmp/serial_mux_vserial,供 minicom 使用
  • Skill 脚本: 自动检测 mux 状态,仅当本次串口配置与 mux 匹配时通过 socket:// 连接 TCP 端口
  • 数据流: 串口 RX → 广播到所有 TCP 客户端;任一客户端 TX → 转发到真实串口

Mux 管理命令

bash
# 启动多路复用
python scripts/serial_mux.py start --port /dev/ttyUSB0 [--baudrate 115200]

# 查询状态
python scripts/serial_mux.py status

# 停止多路复用
python scripts/serial_mux.py stop

启动后,skill 脚本(monitor/hex/log/send)自动通过多路复用连接,无需额外参数。若命令显式指定了不同串口或串口参数,则不会复用当前 mux。

使用流程

  1. python scripts/serial_mux.py start --port /dev/ttyUSB0
  2. minicom -D /tmp/serial_mux_vserial(用户侧交互)
  3. python scripts/serial_monitor.py(模型侧监控,自动走 mux)
  4. 两个终端同时看到串口数据
  5. python scripts/serial_mux.py stop 停止复用(终止 socat 进程并清理 /tmp/serial_mux_vserial 符号链接)

写入冲突警告

多客户端同时写入会导致串口数据错乱。 监控/hex/log 脚本在通过 mux 连接时输出警告到 stderr。send 脚本输出更强的冲突警告。如需直连真实串口(跳过 mux),使用 --direct 参数。

Mux 状态持久化

mux 进程 PID 保存到 .embeddedskills/state.json 的 serial_mux 段。脚本退出后下次调用 status 会检测进程是否仍存活,自动清理僵尸 PID。start 成功后会把已确认的串口配置写回 .embeddedskills/config.json,方便后续无参命令复用。stop 命令会终止 mux 与 socat PTY 进程,并删除残留的 /tmp/serial_mux_vserial 符号链接。

核心规则

  • 不自动猜测波特率;发现多个候选串口时不自动选择端口
  • 参数解析优先级:CLI > 工程级配置 > 状态文件 > 默认值
  • 未指定 port 时自动扫描,唯一候选自动写入配置,多候选需用户选择
  • 成功执行后,确认的参数自动写回 .embeddedskills/config.json
  • 未明确说明用途时不主动发送任何串口数据
  • --json 输出的持续流使用 JSON Lines,摘要写 stderr 不污染数据流
  • 正则过滤失败不应导致监控退出
  • Mux 运行中发送数据前提示用户避免同时写入

参考

  • references/common_devices.json:常见 USB 转串口芯片 VID/PID 映射

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Serial AI skill do?

嵌入式串口调试工具,用于扫描串口、实时监控、发送数据、记录日志和 Hex 查看。 当用户提到串口、COM 口、UART、AT 命令调试、波特率、Hex 串流、串口抓日志、 串口监控、查看 MCU 输出、二进制协议联调时自动触发,也兼容 /serial 显式调用。 即使用户只是说"看看串口输出"、"发个 AT 命令"或"抓一下日志",只要上下文涉及 串口通信就应触发此 skill。

Why use Serial on TypingMind?

Because you install it once and use it with any model. Serial is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Serial in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/zhinkgit/embeddedskills/tree/main/serial. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Serial?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Serial?

As many as you like. As long as a model supports skills, you can use Serial with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Serial AI skill free?

Yes. It is published on GitHub by zhinkgit under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇