New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Openocd

by zhinkgit in zhinkgit/embeddedskills

OpenOCD 下载与调试工具，用于探针探测、固件烧录、Flash 擦除、GDB Server 启动、目标复位控制、 Telnet 在线调试（halt/resume/step/寄存器/内存/断点）、GDB 源码级调试，以及 Semihosting/ITM 输出捕获和底层查询。

MITAuto-check passed

Install Openocd

skills CLI
$ npx skills add zhinkgit/embeddedskills --skill openocd -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install zhinkgit/embeddedskills openocd --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/zhinkgit/embeddedskills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/openocd .claude/skills/openocd && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
openocd
GitHub stars
733
Token cost
~2.7k tokens
SKILL.md length
396 words
Files
13 (incl. scripts, references)
Skills in repo
11
Repo updated
First seen
Licence
MIT

At a glance

OpenOCD 下载与调试工具，用于探针探测、固件烧录、Flash 擦除、GDB Server 启动、目标复位控制、 Telnet 在线调试（halt/resume/step/寄存器/内存/断点）、GDB 源码级调试，以及 Semihosting/ITM 输出捕获和底层查询。

  • Works in 10 steps: 读取 skill/config.json，确认 exe 路径有效 → 读取 .embeddedskills/config.json… → 读取 .embeddedskills/state.json 获取历史状态 → …
  • SKILL.md covers 配置, 子命令, 执行流程 and 脚本调用, plus 4 more sections
  • Runs Python scripts from its folder; calls python

What it does

Openocd is an agent skill from zhinkgit/embeddedskills. OpenOCD 下载与调试工具，用于探针探测、固件烧录、Flash 擦除、GDB Server 启动、目标复位控制、 Telnet 在线调试（halt/resume/step/寄存器/内存/断点）、GDB 源码级调试，以及 Semihosting/ITM 输出捕获和底层查询。 当用户提到 OpenOCD、ST-Link、CMSIS-DAP、DAPLink、FTDI、烧录固件、擦除 Flash、GDB Server、 reset、interface/target/board 配置、openocd.cfg、在线调试、单步、断点、寄存器查看、 内存读写、semihosting 时自动触发，也兼容 /openocd 显式调用。 即使用户只是说"烧录一下"、"启动 GDB Server"、"擦除芯片"、"看看寄存器"、"单步调试" 或"抓一下 semihosting"，只要上下文涉及 OpenOCD 支持的开源调试器就应触发此 skill。

Its SKILL.md is about 2.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 15 other files, including scripts and reference files (for example `README.md`, `config.example.json` and `references/common_targets.md`).

The repository describes itself as: An open-source collection of embedded development and debugging skills for Claude Code, Copilot, TRAE, and other AI coding assistants that support the Skill protocol. Once… The licence is MIT.

Example prompts

  • “启动 GDB Server”
  • “抓一下 semihosting”
  • “/openocd”

Requirements

  • Python 3

Workflow steps

10 steps, taken from the first numbered list in SKILL.md.

  1. 读取 skill/config.json，确认 exe 路径有效
  2. 读取 .embeddedskills/config.json 获取工程级配置（board/interface/target 等）
  3. 读取 .embeddedskills/state.json 获取历史状态
  4. 参数解析优先级：CLI 显式参数 > .embeddedskills/config.json（工程级）> skill/config.json（环境级）> .embeddedskills/state.json > 默认值/报错
  5. 已知 board 时优先使用 -f board/*.cfg，否则组合 -f interface/*.cfg -f target/*.cfg
  6. board、interface、target 同时缺失时，不自动拼接组合，直接要求用户补充
  7. 按 operation_mode 决定是否需要确认后执行
  8. 根据子命令调用对应脚本
  9. 统一解析输出中的 Info、Error 和就绪日志，返回结构化结果
  10. 成功执行后，将确认过的参数写回 .embeddedskills/config.json

What it can do on your machine

Read from SKILL.md and the folder at commit 536c1f9. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 7 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Openocd loads about 2.7k tokens when it runs, and up to ~3.4k if it reads all its reference files. Until then it costs about 107 tokens; SKILL.md has 396 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~107
When it runs · the whole SKILL.md, loaded when a task matches
~2.7k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from zhinkgit/embeddedskills at commit 536c1f9, republished under its MIT licence (© zhinkgit). 396 words, ~2,745 tokens.

Download SKILL.mdSave it as .claude/skills/openocd/SKILL.md (or your agent's skills folder). This skill also uses 12 other files; get the full folder from GitHub.
name
openocd
description
OpenOCD 下载与调试工具，用于探针探测、固件烧录、Flash 擦除、GDB Server 启动、目标复位控制、 Telnet 在线调试（halt/resume/step/寄存器/内存/断点）、GDB 源码级调试，以及 Semihosting/ITM 输出捕获和底层查询。 当用户提到 OpenOCD、ST-Link、CMSIS-DAP、DAPLink、FTDI、烧录固件、擦除 Flash、GDB Server、 reset、interface/target/board 配置、openocd.cfg、在线调试、单步、断点、寄存器查看、 内存读写、semihosting 时自动触发，也兼容 /openocd 显式调用。 即使用户只是说"烧录一下"、"启动 GDB Server"、"擦除芯片"、"看看寄存器"、"单步调试" 或"抓一下 semihosting"，只要上下文涉及 OpenOCD 支持的开源调试器就应触发此 skill。
argument-hint
[probe|flash|erase|reset|reset-init|targets|flash-banks|adapter-info|raw|gdb-server|gdb|halt|resume|step|reg|read-mem|write-mem|bp|rbp|run-to|semihosting|itm]…

OpenOCD 下载与调试

本 skill 提供 OpenOCD 的探针探测、固件烧录、Flash 擦除、GDB Server 启动、目标复位、 Telnet 在线调试、GDB 源码级调试和 Semihosting 输出捕获能力。

配置

环境级配置（skill/config.json）

skill 目录下的 config.json 包含环境级配置（工具路径、端口号等），首次使用前确认 exe 路径正确：

json
{
  "exe": "openocd",
  "scripts_dir": "",
  "gdb_port": 3333,
  "telnet_port": 4444,
  "gdb_exe": "",
  "operation_mode": 1
}
  • exe：openocd.exe 路径或命令名（必填）
  • scripts_dir：OpenOCD 配置脚本目录，为空时使用 OpenOCD 内置路径
  • gdb_port：GDB Server 端口，默认 3333
  • telnet_port：Telnet 端口，默认 4444
  • gdb_exe：arm-none-eabi-gdb 路径，GDB 调试子命令（run/backtrace/locals）需要
  • 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（.embeddedskills/config.json）

board/interface/target 等工程参数统一在工作区的 .embeddedskills/config.json 中管理：

json
{
  "openocd": {
    "board": "",
    "interface": "interface/stlink.cfg",
    "target": "target/stm32f4x.cfg",
    "adapter_speed": "4000",
    "transport": "swd",
    "tpiu_name": "stm32f4x.tpiu",
    "traceclk": "168000000",
    "pin_freq": "2000000"
  }
}
  • board：board 配置（如 board/stm32f4discovery.cfg），优先级高于 interface+target
  • interface：interface 配置（如 interface/stlink.cfg）
  • target：target 配置（如 target/stm32f4x.cfg）
  • adapter_speed：调试速率 kHz
  • transport：传输协议（swd/jtag）
  • tpiu_name / traceclk / pin_freq：ITM/SWO 观测所需的 TPIU 参数

参数解析优先级：CLI 显式参数 > .embeddedskills/config.json（工程级）> skill/config.json（环境级）> .embeddedskills/state.json > 默认值/报错

成功执行后，确认过的参数会自动写回工程配置。

子命令

基础操作
子命令用途风险
probe验证 board 或 interface+target 组合，探测目标连通性低
flash烧录固件（.elf / .hex / .bin）高
erase擦除目标 Flash高
reset / reset-init复位目标芯片高
targets / flash-banks / adapter-info查询底层 target / flash / adapter 信息低
raw执行受控 OpenOCD 原生命令高
GDB Server
子命令用途风险
gdb-server启动 GDB Server，保持运行等待 GDB 连接低
gdb backtrace/locals快捷获取调用栈和局部变量低
gdb break/continue/next/step/finish/untilone-shot 执行流控制低
gdb frame/print/watch/disassemble/threads/crash-reportone-shot 源码级诊断低
Telnet 在线调试
子命令用途风险
halt暂停 CPU，返回 PC/xPSR低
resume恢复 CPU 运行低
step单步执行（支持 --count N）低
reg查看所有 CPU 寄存器低
read-mem读内存（--width 8/16/32，--length N）低
write-mem写内存（--width 8/16/32）高
bp设置硬件断点低
rbp移除断点低
run-to运行到指定地址（设置断点 + resume + 等待命中）低
Semihosting
子命令用途风险
semihosting启用 ARM Semihosting 并捕获目标 printf 输出低
itm基于 TPIU/ITM 读取 SWO/ITM 观测数据低

执行流程

  1. 读取 skill/config.json，确认 exe 路径有效
  2. 读取 .embeddedskills/config.json 获取工程级配置（board/interface/target 等）
  3. 读取 .embeddedskills/state.json 获取历史状态
  4. 参数解析优先级：CLI 显式参数 > .embeddedskills/config.json（工程级）> skill/config.json（环境级）> .embeddedskills/state.json > 默认值/报错
  5. 已知 board 时优先使用 -f board/*.cfg，否则组合 -f interface/*.cfg -f target/*.cfg
  6. board、interface、target 同时缺失时，不自动拼接组合，直接要求用户补充
  7. 按 operation_mode 决定是否需要确认后执行
  8. 根据子命令调用对应脚本
  9. 统一解析输出中的 Info、Error 和就绪日志，返回结构化结果
  10. 成功执行后，将确认过的参数写回 .embeddedskills/config.json
Show full SKILL.md (143 more words)Show less

脚本调用

skill 目录下有五个 Python 脚本，使用标准库实现，无额外依赖。

openocd_run.py — 探测 / 烧录 / 擦除 / 复位
bash
# 探测连通性（使用 board）
python <skill-dir>/scripts/openocd_run.py probe --board board/stm32f4discovery.cfg --json

# 探测连通性（使用 interface + target）
python <skill-dir>/scripts/openocd_run.py probe --interface interface/stlink.cfg --target target/stm32f4x.cfg --json

# 烧录 ELF 固件
python <skill-dir>/scripts/openocd_run.py flash --file build/app.elf --interface interface/stlink.cfg --target target/stm32f4x.cfg --json

# 烧录 BIN 固件（必须提供地址）
python <skill-dir>/scripts/openocd_run.py flash --file build/app.bin --address 0x08000000 --interface interface/stlink.cfg --target target/stm32f4x.cfg --json

# 擦除 Flash（自动选择 mass/sector）
python <skill-dir>/scripts/openocd_run.py erase --mode auto --interface interface/stlink.cfg --target target/stm32f4x.cfg --json

# 复位目标
python <skill-dir>/scripts/openocd_run.py reset --mode halt --interface interface/stlink.cfg --target target/stm32f4x.cfg --json

# 查询 target 列表
python <skill-dir>/scripts/openocd_run.py targets --interface interface/stlink.cfg --target target/stm32f4x.cfg --json

# 查询 flash bank
python <skill-dir>/scripts/openocd_run.py flash-banks --interface interface/stlink.cfg --target target/stm32f4x.cfg --json

# 执行受控 raw 命令
python <skill-dir>/scripts/openocd_run.py raw --interface interface/stlink.cfg --target target/stm32f4x.cfg --command "init" "targets" --json

通用可选参数：--board <cfg>、--search <目录>、--adapter-speed <kHz>、--transport <swd|jtag>、--exe <openocd路径>

openocd_gdb.py — GDB Server 启动与调试
bash
# 启动 GDB Server（保持运行）
python <skill-dir>/scripts/openocd_gdb.py server --interface interface/stlink.cfg --target target/stm32f4x.cfg --json

# 无子命令时默认 server（向后兼容）
python <skill-dir>/scripts/openocd_gdb.py --interface interface/stlink.cfg --target target/stm32f4x.cfg --json

# 执行自定义 GDB 命令序列
python <skill-dir>/scripts/openocd_gdb.py run --gdb-exe arm-none-eabi-gdb --elf build/app.elf --interface interface/stlink.cfg --target target/stm32f4x.cfg --commands "break main" "continue" "backtrace" "info locals" --json

# 快捷获取调用栈
python <skill-dir>/scripts/openocd_gdb.py backtrace --gdb-exe arm-none-eabi-gdb --elf build/app.elf --interface interface/stlink.cfg --target target/stm32f4x.cfg --json

# 快捷查看局部变量
python <skill-dir>/scripts/openocd_gdb.py locals --gdb-exe arm-none-eabi-gdb --elf build/app.elf --interface interface/stlink.cfg --target target/stm32f4x.cfg --json

可选参数：--gdb-port、--telnet-port、--search、--adapter-speed、--transport、--board

openocd_telnet.py — Telnet 在线调试
bash
# 暂停 CPU
python <skill-dir>/scripts/openocd_telnet.py halt --interface interface/stlink.cfg --target target/stm32f4x.cfg --json

# 恢复运行
python <skill-dir>/scripts/openocd_telnet.py resume --interface interface/stlink.cfg --target target/stm32f4x.cfg --json

# 单步 5 次
python <skill-dir>/scripts/openocd_telnet.py step --count 5 --interface interface/stlink.cfg --target target/stm32f4x.cfg --json

# 查看寄存器
python <skill-dir>/scripts/openocd_telnet.py reg --interface interface/stlink.cfg --target target/stm32f4x.cfg --json

# 读内存（32bit x 16 个字）
python <skill-dir>/scripts/openocd_telnet.py read-mem --address 0x20000000 --length 16 --width 32 --interface interface/stlink.cfg --target target/stm32f4x.cfg --json

# 写内存
python <skill-dir>/scripts/openocd_telnet.py write-mem --address 0x20000000 --value 0xDEADBEEF --width 32 --interface interface/stlink.cfg --target target/stm32f4x.cfg --json

# 设置硬件断点
python <skill-dir>/scripts/openocd_telnet.py bp --address 0x08001234 --bp-length 2 --interface interface/stlink.cfg --target target/stm32f4x.cfg --json

# 移除断点
python <skill-dir>/scripts/openocd_telnet.py rbp --address 0x08001234 --interface interface/stlink.cfg --target target/stm32f4x.cfg --json

# 运行到指定地址（设置断点 + resume + 等待）
python <skill-dir>/scripts/openocd_telnet.py run-to --address 0x08001234 --timeout-ms 3000 --interface interface/stlink.cfg --target target/stm32f4x.cfg --json

通用可选参数：--board、--search、--adapter-speed、--transport、--gdb-port、--telnet-port

openocd_semihosting.py — Semihosting 输出捕获
bash
# 捕获 semihosting 输出（持续到 Ctrl+C）
python <skill-dir>/scripts/openocd_semihosting.py --interface interface/stlink.cfg --target target/stm32f4x.cfg --json

# 捕获 30 秒
python <skill-dir>/scripts/openocd_semihosting.py --timeout 30 --interface interface/stlink.cfg --target target/stm32f4x.cfg --json
openocd_itm.py — ITM/SWO 观测
bash
# 使用配置中的 TPIU 参数持续读取 ITM
python <skill-dir>/scripts/openocd_itm.py --interface interface/stlink.cfg --target target/stm32f4x.cfg --json

# 指定 TPIU 名称和端口
python <skill-dir>/scripts/openocd_itm.py \
  --interface interface/stlink.cfg --target target/stm32f4x.cfg \
  --tpiu-name stm32f4x.tpiu --traceclk 168000000 --pin-freq 2000000 \
  --itm-port 0 --itm-port 1 --json

openocd_itm.py 会启动独立 OpenOCD Server，打开 TPIU/ITM 配置后，把 trace 输出统一包装成 JSON Lines。

调试典型工作流

快速检查（Telnet）
halt -> reg -> read-mem 0x20000000 -> step -> resume

适合快速查看当前 CPU 状态和内存内容。

断点调试（Telnet）
run-to 0x08001234 -> reg -> read-mem -> resume

运行到指定地址后暂停，检查寄存器和内存。

源码级调试（GDB）
bash
gdb run --elf app.elf --commands "break main" "continue" "backtrace" "info locals"

使用 ELF 文件提供符号信息，进行函数级断点和变量查看。

Semihosting 输出
bash
semihosting

捕获目标通过 printf（SVC 指令）输出的调试信息，类似 J-Link RTT。

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。流式观测命令使用 JSON Lines，并统一输出 source、channel_type、stream_type。

成功示例：

json
{
  "status": "ok",
  "action": "halt",
  "summary": "已暂停，PC=0x08000298",
  "details": {
    "pc": "0x08000298",
    "xpsr": "0x01000000",
    "msp": "0x20020000",
    "halted": true
  }
}

GDB 调用栈示例：

json
{
  "status": "ok",
  "action": "backtrace",
  "summary": "GDB backtrace 执行成功",
  "details": {
    "gdb_port": 3333,
    "frames": [
      {"frame": 0, "function": "main", "location": "src/main.c:42"}
    ]
  }
}

错误示例：

json
{
  "status": "error",
  "action": "halt",
  "error": {
    "code": "server_failed",
    "message": "OpenOCD 启动失败或超时"
  }
}

核心规则

  • 不自动猜测 board、interface、target 的组合，缺失时必须询问用户
  • 已知 board 时优先使用 board 配置，不再需要 interface+target
  • 参数解析优先级为：CLI 显式参数 > .embeddedskills/config.json（工程级）> skill/config.json（环境级）> .embeddedskills/state.json > 默认值/报错
  • .bin 文件必须显式提供烧录地址，缺失时报错
  • STM32F4 等已映射 target 在 erase --mode auto 下会先 reset halt，再优先使用 mass erase
  • erase --mode mass 在未命中映射时直接返回 mass_erase_unsupported，避免误以为已做整片擦除
  • 检测到 Flash 锁保护时只提示，不自动解锁
  • 连接失败时给出排查建议（检查连线、供电、驱动、cfg 路径），不自动尝试更激进参数
  • 烧录、擦除、复位在参数完整且用户意图明确时直接执行
  • gdb-server 启动后返回端口和连接方式，进程保持运行
  • GDB 调试（run/backtrace/locals）需要配置 gdb_exe（arm-none-eabi-gdb 路径）
  • Telnet 调试命令每次启动独立的 OpenOCD Server，执行完自动关闭
  • Semihosting 通过 Telnet 启用后持续读取 OpenOCD stderr 输出
  • 结果回显中始终包含 cfg 组合、端口和执行动作
  • 产物路径（elf/file）不进入工程配置，仍只依赖 state.json
  • last_flash/last_debug/last_observe 等运行状态继续写入 state.json

参考

遇到 board/interface/target 配置问题时可查阅 references/common_targets.md。

© zhinkgit, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 12 other files (scripts, references) in openocd of zhinkgit/embeddedskills.

  • SKILL.md
  • README.md
  • config.example.json
  • references/common_targets.md
  • scripts/openocd_gdb.py
  • scripts/openocd_gdb_common.py
  • scripts/openocd_itm.py
  • scripts/openocd_run.py
  • scripts/openocd_runtime.py
  • scripts/openocd_semihosting.py
  • scripts/openocd_telnet.py
  • templates/flash.cfg
  • templates/gdb_server.cfg

Open the folder on GitHubat commit 536c1f9

Compare with similar skills

Openocd next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Openocd compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Openocd this skillzhinkgit/embeddedskills733—~2.7kAutomated safety check: PassMIT
Flash OpenocdLeoKemp223/embed-ai-tool984—~503Automated safety check: PassNone
Debug Gdb OpenocdLeoKemp223/embed-ai-tool984—~490Automated safety check: PassNone
Flashing Contentthedaviddias/Front-End-Checklist74k—~530Automated safety check: PassMIT
Gdb CLIsickn33/agentic-awesome-skills47k2 repos~1.4kAutomated safety check: PassMIT
Flashnodetool-ai/nodetool556—~2.2kAutomated safety check: PassAGPL-3.0

Similar skills

  • Flash Openocd

    LeoKemp223/embed-ai-tool

    当需要使用已探测或显式指定的产物与探针配置，调用自带脚本通过 OpenOCD 烧录嵌入式固件时使用. An agent skill from LeoKemp223/embed-ai-tool.

    984 GitHub stars~503 tokensUpdated 1 mo ago
    DevelopmentAuto-check passed

  • Debug Gdb Openocd

    LeoKemp223/embed-ai-tool

    当需要通过 OpenOCD 启动或附着 GDB 会话，调用自带脚本完成固件下载、在线调试或崩溃现场检查时使用. An agent skill from LeoKemp223/embed-ai-tool.

    984 GitHub stars~490 tokensUpdated 1 mo ago
    DevelopmentAuto-check passed

  • Flashing Content

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing rendered HTML, interactive components, or design-system patterns related to Prevent seizure-triggering flashing content.

    74k GitHub stars~530 tokensUpdated 2 days ago
    Frontend & DesignAuto-check passed

  • Gdb CLI

    sickn33/agentic-awesome-skills

    GDB debugging assistant for AI agents - analyze core dumps, debug live processes, investigate crashes and deadlocks with source code correlation

    47k GitHub starsUsed in 2 repos~1.4k tokens
    DevelopmentAuto-check passed

  • Flash

    nodetool-ai/nodetool

    Develop and deploy AI workloads with the runpod-flash SDK and CLI on Runpod serverless GPUs or CPUs.

    556 GitHub stars~2.2k tokensUpdated today
    Backend & APIsAuto-check passed

  • Optimizing Attention Flash

    Orchestra-Research/AI-Research-SKILLs

    Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction.

    13k GitHub starsUsed in 5 repos~2.5k tokens
    AI & LLM EngineeringAuto-check passed

More from zhinkgit/embeddedskills

All 11 skills in this repo

  • Can

    zhinkgit/embeddedskills

    嵌入式 CAN / CAN-FD 调试工具，用于扫描接口、监控报文、发送测试帧、记录日志、数据库文件解码和总线统计. An agent skill from zhinkgit/embeddedskills.

    733 GitHub stars~1k tokensUpdated 1 mo ago
    Auto-check passed

  • Eide

    zhinkgit/embeddedskills

    EIDE (Embedded IDE) 工程构建工具，用于扫描 .eide/eide.yml 工程、枚举构建 配置 (ConfigName)、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。当用户提到 EIDE、Embedded IDE、eide.yml、 unifybuilder、VS Code EIDE…

    733 GitHub stars~1.2k tokensUpdated 1 mo ago
    Auto-check passed

  • Jlink

    zhinkgit/embeddedskills

    J-Link 下载与在线调试工具，用于探测设备、烧录固件、读写内存、查看寄存器、复位目标、读取 RTT/SWO 日志， 以及在线调试（暂停/恢复/单步/断点运行/调用栈/变量查看）。

    733 GitHub stars~2k tokensUpdated 1 mo ago
    Auto-check passed

  • Keil

    zhinkgit/embeddedskills

    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。

    733 GitHub stars~883 tokensUpdated 1 mo ago
    Auto-check passed

  • Serial

    zhinkgit/embeddedskills

    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. An agent skill from zhinkgit/embeddedskills.

    733 GitHub stars~1.4k tokensUpdated 1 mo ago
    Auto-check passed

  • Gcc

    zhinkgit/embeddedskills

    GCC 嵌入式工程构建工具（CMake + arm-none-eabi-gcc），用于扫描 CMake 型嵌入式工程、 列出预设、配置、编译、重建、清理和分析 ELF 大小。当用户提到 GCC、arm-none-eabi、 CMake 嵌入式编译、Ninja 构建、ELF 大小分析、arm-gcc、交叉编译、cmake --build、 cmake --preset 时自动触发，也兼容…

    733 GitHub stars~993 tokensUpdated 1 mo ago
    Auto-check passed

Questions about Openocd

What does Openocd do?

OpenOCD 下载与调试工具，用于探针探测、固件烧录、Flash 擦除、GDB Server 启动、目标复位控制、 Telnet 在线调试（halt/resume/step/寄存器/内存/断点）、GDB 源码级调试，以及 Semihosting/ITM 输出捕获和底层查询。. Openocd is an agent skill from zhinkgit/embeddedskills.

How do I install Openocd in Claude Code?

Run `npx skills add zhinkgit/embeddedskills --skill openocd -a claude-code`. Or copy the skill folder (openocd in zhinkgit/embeddedskills) into .claude/skills/openocd in your project. Claude Code loads it when a task matches its description.

How do I install Openocd in Codex?

Run `npx skills add zhinkgit/embeddedskills --skill openocd -a codex`. Or copy the skill folder (openocd in zhinkgit/embeddedskills) into .agents/skills/openocd in your project. Codex loads it when a task matches its description.

Can I use Openocd in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add zhinkgit/embeddedskills --skill openocd -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/openocd, .gemini/skills/openocd, .github/skills/openocd and .opencode/skills/openocd in your project.

What does Openocd need to run?

Going by SKILL.md and its folder, Openocd needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Openocd access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Openocd safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Openocd use?

Openocd is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Openocd use?

About 2.7k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 692 tokens, read only when the agent opens those files.

What are the alternatives to Openocd?

Skills that share tags, products or a category with Openocd: Flash Openocd (LeoKemp223/embed-ai-tool, 984 stars), Debug Gdb Openocd (LeoKemp223/embed-ai-tool, 984 stars), Flashing Content (thedaviddias/Front-End-Checklist, 74k stars) and Gdb CLI (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Openocd?

zhinkgit (a GitHub user) maintains it in zhinkgit/embeddedskills, which has 733 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on September 3, 2026.

Source: zhinkgit/embeddedskills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.