Keil logo

Keil

Community
zhinkgit
keil

Keil MDK 工程构建工具,用于扫描 .uvprojx/.uvproj/.uvmpw 工程、枚举 Target、执行 build/rebuild/clean 并解析构建日志,返回可供 jlink/openocd 复用的产物路径。 flash 子命令仅作为兼容入口保留。当用户提到 Keil、MDK、uVision、UV4、 Target 枚举、编译、重建、清理、烧录、下载固件、flash 时自动触发,也兼容 /keil 显式调用。 即使用户只是说"编译一下"或"烧录到板子上",只要上下文涉及嵌入式 Keil 工程就应触发此 skill。

Overview

Publisherzhinkgit
Repositoryembeddedskills
Skill namekeil
Stars
739
Forks
94
Bundled files
5
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.

  • 5 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 Keil 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/keil
  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/keil .claude/skills/keil
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Keil 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 Keil 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 Keil 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.

Keil MDK 工程构建

本 skill 提供 Keil MDK 工程的发现、Target 枚举、构建、重建、清理能力,并返回可供 jlink/openocd 继续使用的固件产物路径。flash 仅作为兼容入口保留。

配置

环境级配置(skill/config.json)

skill 目录下的 config.json 包含环境级配置,首次使用前确认 uv4_exe 路径正确:

json
{
  "uv4_exe": "C:\\Keil_v5\\UV4\\UV4.exe",
  "operation_mode": 1
}
  • uv4_exe:UV4.exe 完整路径(必填)
  • operation_mode:1 直接执行 / 2 输出风险摘要但不阻塞 / 3 执行前确认

工程级配置(workspace/.embeddedskills/config.json)

工程级共享配置统一保存在工作区的 .embeddedskills/config.json 中:

json
{
  "keil": {
    "project": "",
    "target": "",
    "log_dir": ".embeddedskills/build"
  }
}
  • project:默认工程路径(相对 workspace),构建成功后会自动更新
  • target:默认 Target 名称,构建成功后会自动更新
  • log_dir:构建日志输出目录,默认 .embeddedskills/build

参数解析优先级

参数解析顺序(从高到低):

  1. CLI 显式参数
  2. 环境级配置(skill/config.json)
  3. 工程级配置(.embeddedskills/config.json)
  4. .embeddedskills/state.json(上次构建记录)
  5. 搜索/询问

子命令

子命令用途风险
scan搜索当前目录下的 .uvprojx/.uvproj/.uvmpw 工程低
targets枚举工程中的 Target低
build增量编译中
rebuild全量重建中
clean清理工程高
flash通过 Keil 烧录固件(兼容入口,优先建议使用 jlink/openocd)高

执行流程

  1. 读取 config.json,确认 uv4_exe 路径有效
  2. 未指定子命令时默认执行 scan
  3. 未提供工程路径时先执行 scan 搜索工程
  4. 同时发现多个工程或多个 Target 时,列出选项让用户选择,绝不自动猜测
  5. build/rebuild/clean 按 operation_mode 决定是否需要确认
  6. build/rebuild 成功后,尽量从工程配置中解析 flash_file / debug_file 等产物路径
  7. flash 仅在最近一次构建成功时允许执行
  8. 所有构建命令输出到日志文件后解析,返回结构化结果

脚本调用

skill 目录下有两个 Python 脚本,使用标准库实现,无额外依赖。

keil_project.py — 工程扫描与 Target 枚举

bash
# 扫描工程
python <skill-dir>/scripts/keil_project.py scan --root <搜索目录> --json

# 枚举 Target
python <skill-dir>/scripts/keil_project.py targets --project <工程路径> --json

keil_build.py — 构建 / 重建 / 清理 / 烧录

bash
python <skill-dir>/scripts/keil_build.py <build|rebuild|clean|flash> \
  --uv4 <UV4路径> \
  --project <工程路径> \
  --target <TargetName> \
  --log-dir <日志目录> \
  --json

rebuild 额外支持 --clean-first 使用 -cr 而非 -r。

输出格式

所有脚本以 JSON 格式返回,基础字段为 status(ok/error)、action、summary、details,并可能附带 context、artifacts、metrics、state、next_actions、timing。

成功示例:

json
{
  "status": "ok",
  "action": "build",
  "summary": "build 成功,errors=0 warnings=2",
  "details": {
    "project": "project.uvprojx",
    "target": "Debug",
    "log_file": ".build/project-Debug-build.log",
    "flash_file": "Objects/project.hex",
    "debug_file": "Objects/project.axf"
  },
  "metrics": { "errors": 0, "warnings": 2, "flash_bytes": 32768, "ram_bytes": 8192 }
}

错误示例:

json
{
  "status": "error",
  "action": "flash",
  "error": { "code": "build_not_clean", "message": "最近一次构建存在错误,禁止继续烧录" }
}

核心规则

  • 不修改工程配置文件(.uvprojx / .uvproj / .uvmpw / .uvoptx)
  • .uvproj(旧版 MDK4 工程)与 .uvprojx 共用同一套 XML 结构(Target/TargetOption/TargetCommonOption),产物解析、Target 枚举、扫描均已支持两种后缀
  • 不自动猜测工程路径或 Target,有歧义时必须询问用户
  • 参数解析优先级详见上方"参数解析优先级"章节
  • 构建成功后优先使用返回的 flash_file / debug_file 与 jlink/openocd 串联
  • flash 前必须确认最近一次构建成功(errors == 0)
  • clean 不在自动流程中隐式执行
  • 构建失败时优先展示首个错误和日志文件路径
  • 结果回显中始终包含工程名、Target 名、日志路径;若识别到产物路径也要回显

参考

遇到编译器相关问题时可查阅 references/compiler-notes.md。

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 Keil AI skill do?

Keil MDK 工程构建工具,用于扫描 .uvprojx/.uvproj/.uvmpw 工程、枚举 Target、执行 build/rebuild/clean 并解析构建日志,返回可供 jlink/openocd 复用的产物路径。 flash 子命令仅作为兼容入口保留。当用户提到 Keil、MDK、uVision、UV4、 Target 枚举、编译、重建、清理、烧录、下载固件、flash 时自动触发,也兼容 /keil 显式调用。 即使用户只是说"编译一下"或"烧录到板子上",只要上下文涉及嵌入式 Keil 工程就应触发此 skill。

Why use Keil on TypingMind?

Because you install it once and use it with any model. Keil 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 Keil in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/zhinkgit/embeddedskills/tree/main/keil. 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 Keil?

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 Keil?

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

Is the Keil 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 👇