AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Keil

skill-zhinkgit-embeddedskills-keil · by zhinkgit

>-

No reviews yet
0 installs
3 views
0.0% view→install

Install

$ agentstack add skill-zhinkgit-embeddedskills-keil

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-zhinkgit-embeddedskills-keil)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
1mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Keil? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

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:

{
  "uv4_exe": "C:\\Keil_v5\\UV4\\UV4.exe",
  "operation_mode": 1
}
  • uv4_exe:UV4.exe 完整路径(必填)
  • operation_mode1 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:

{
  "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/cleanoperation_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

# 扫描工程
python /scripts/keil_project.py scan --root  --json

# 枚举 Target
python /scripts/keil_project.py targets --project  --json

keil_build.py — 构建 / 重建 / 清理 / 烧录

python /scripts/keil_build.py  \
  --uv4  \
  --project  \
  --target  \
  --log-dir  \
  --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)、actionsummarydetails,并可能附带 contextartifactsmetricsstatenext_actionstiming

成功示例:

{
  "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:

{
  "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_filejlink/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

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.