Agent skill

Probe Rs

probe-rs 下载与调试工具，用于探针发现、固件烧录、复位、内存读写、GDB Server 调试和 RTT 日志读取。

MITAuto-check passed

Install Probe Rs

skills CLI

$ npx skills add zhinkgit/embeddedskills --skill probe-rs -a claude-code

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

GitHub CLI

$ gh skill install zhinkgit/embeddedskills probe-rs --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/probe-rs .claude/skills/probe-rs && 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/

Paste into Claude Code

Install the "probe-rs" agent skill from https://github.com/zhinkgit/embeddedskills/tree/main/probe-rs into .claude/skills/probe-rs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "probe-rs", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/zhinkgit/embeddedskills/tree/main/probe-rs

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add zhinkgit/embeddedskills --skill probe-rs -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install zhinkgit/embeddedskills probe-rs --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/zhinkgit/embeddedskills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/probe-rs .agents/skills/probe-rs && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "probe-rs" agent skill from https://github.com/zhinkgit/embeddedskills/tree/main/probe-rs into .agents/skills/probe-rs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "probe-rs", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add zhinkgit/embeddedskills --skill probe-rs -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install zhinkgit/embeddedskills probe-rs --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/zhinkgit/embeddedskills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/probe-rs .cursor/skills/probe-rs && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "probe-rs" agent skill from https://github.com/zhinkgit/embeddedskills/tree/main/probe-rs into .cursor/skills/probe-rs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "probe-rs", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/zhinkgit/embeddedskills.git --path probe-rs

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add zhinkgit/embeddedskills --skill probe-rs -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install zhinkgit/embeddedskills probe-rs --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/zhinkgit/embeddedskills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/probe-rs .gemini/skills/probe-rs && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "probe-rs" agent skill from https://github.com/zhinkgit/embeddedskills/tree/main/probe-rs into .gemini/skills/probe-rs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "probe-rs", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install zhinkgit/embeddedskills probe-rs

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add zhinkgit/embeddedskills --skill probe-rs -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/zhinkgit/embeddedskills.git skills-src && mkdir -p .github/skills && cp -r skills-src/probe-rs .github/skills/probe-rs && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "probe-rs" agent skill from https://github.com/zhinkgit/embeddedskills/tree/main/probe-rs into .github/skills/probe-rs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "probe-rs", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add zhinkgit/embeddedskills --skill probe-rs -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install zhinkgit/embeddedskills probe-rs --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/zhinkgit/embeddedskills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/probe-rs .opencode/skills/probe-rs && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "probe-rs" agent skill from https://github.com/zhinkgit/embeddedskills/tree/main/probe-rs into .opencode/skills/probe-rs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "probe-rs", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: probe-rs
GitHub stars: 733
Token cost: ~767 tokens
SKILL.md length: 148 words
Files: 8 (incl. scripts)
Skills in repo: 11
Repo updated: Sep 3, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

probe-rs 下载与调试工具，用于探针发现、固件烧录、复位、内存读写、GDB Server 调试和 RTT 日志读取。

SKILL.md covers 配置, 子命令, 典型调用 and 核心规则
Runs Python scripts from its folder

What it does

Probe Rs is an agent skill from zhinkgit/embeddedskills. probe-rs 下载与调试工具，用于探针发现、固件烧录、复位、内存读写、GDB Server 调试和 RTT 日志读取。当用户提到 probe-rs、cargo-embed、DAP、RTT、CMSIS-DAP、ST-Link、J-Link、烧录、芯片信息、连接 under reset、probe 选择器、probe-rs gdb、probe-rs attach 时自动触发，也兼容 /probe-rs 显式调用。即使用户只是说"用 probe-rs 烧进去"、"看看 RTT"或"拉个 backtrace"，只要上下文明确提到 probe-rs 的功能、CLI 命令或相关术语（如 cargo-embed、RTT、probe-rs flash）时就应触发此 skill。

Its SKILL.md is about 770 tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files, including scripts (for example `README.md`, `config.example.json` and `scripts/probe_rs_exec.py`).

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

“用 probe-rs 烧进去”
“看看 RTT”
“拉个 backtrace”
“/probe-rs”

Requirements

Python 3

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

Probe Rs loads about 767 tokens when it runs. Until then it costs about 87 tokens; SKILL.md has 148 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~87
When it runs · the whole SKILL.md, loaded when a task matches: ~767

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). 148 words, ~767 tokens.

Download SKILL.mdSave it as .claude/skills/probe-rs/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.

name: probe-rs
description: probe-rs 下载与调试工具，用于探针发现、固件烧录、复位、内存读写、GDB Server 调试和 RTT 日志读取。当用户提到 probe-rs、cargo-embed、DAP、RTT、CMSIS-DAP、ST-Link、J-Link、烧录、芯片信息、连接 under reset、probe 选择器、probe-rs gdb、probe-rs attach 时自动触发，也兼容 /probe-rs 显式调用。即使用户只是说"用 probe-rs 烧进去"、"看看 RTT"或"拉个 backtrace"，只要上下文明确提到 probe-rs 的功能、CLI 命令或相关术语（如 cargo-embed、RTT、probe-rs flash）时就应触发此 skill。
argument-hint: [list|info|flash|erase|reset|read-mem|write-mem|attach|run|gdb|rtt] ...

probe-rs 下载与调试

本 skill 提供 probe-rs CLI 的结构化包装，覆盖探针发现、目标信息、烧录、复位、内存读写、one-shot GDB 调试和 RTT 日志读取。

Windows 下优先使用 py -3 调用脚本；若 arm-none-eabi-gdb 已在 PATH 中，gdb 子命令可自动发现，不强依赖 skill config.json。

配置

环境级配置（skill/config.json）

首次使用前建议在 skill 目录下创建 config.json：

json

{
  "exe": "probe-rs",
  "gdb_exe": "C:\\Program Files\\Arm\\GNU Toolchain mingw-w64-x86_64-arm-none-eabi\\bin\\arm-none-eabi-gdb.exe",
  "gdb_port": 3333,
  "dap_port": 50000,
  "operation_mode": 1
}

exe：probe-rs 可执行文件路径或命令名
gdb_exe：arm-none-eabi-gdb 路径，gdb 子命令需要
gdb_port：默认 GDB 端口
dap_port：预留给交互式 DAP 会话
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）

json

{
  "probe-rs": {
    "chip": "STM32F407VGTx",
    "protocol": "swd",
    "probe": "",
    "speed": 4000,
    "connect_under_reset": false
  }
}

chip：芯片型号，probe-rs 主后端必填
protocol：swd 或 jtag
probe：探针选择器，格式 VID:PID[:Serial]
speed：调试速率 kHz
connect_under_reset：连接时是否保持 reset

参数优先级：CLI 参数 > 工程配置（.embeddedskills/config.json）> state.json > skill 配置（config.json）> 默认值

各层职责：skill config.json 提供工具路径与端口等环境级常量；.embeddedskills/config.json 提供芯片、协议等工程级参数；CLI 参数在单次调用中覆盖一切。

子命令

子命令	用途	风险
`list`	枚举可用探针	低
`info`	查看探针与目标信息	低
`flash`	烧录固件（elf/hex/bin/uf2）	高
`erase`	擦除芯片非易失存储	高
`reset`	复位目标芯片	高
`read-mem`	读取内存	低
`write-mem`	写内存	高
`attach` / `run`	包装 probe-rs attach/run	低
`gdb`	启动 GDB Server 并执行 one-shot 调试	低
`rtt`	读取 RTT 日志	低

典型调用

bash

# 列出探针
py -3 <skill-dir>/scripts/probe_rs_exec.py list --json

# 烧录 ELF
py -3 <skill-dir>/scripts/probe_rs_exec.py flash --chip STM32F407VGTx --file build/app.elf --json

# 烧录 BIN（必须提供地址）
py -3 <skill-dir>/scripts/probe_rs_exec.py flash --chip STM32F407VGTx --file build/app.bin --address 0x08000000 --json

# 读取内存
py -3 <skill-dir>/scripts/probe_rs_exec.py read-mem --chip STM32F407VGTx --address 0x20000000 --length 16 --width b32 --json

# one-shot backtrace
py -3 <skill-dir>/scripts/probe_rs_gdb.py backtrace --chip STM32F407VGTx --elf build/app.elf --json

# RTT
py -3 <skill-dir>/scripts/probe_rs_rtt.py --chip STM32F407VGTx --json

核心规则

不自动猜测 chip，缺失时直接报错
多探针场景建议显式提供 --probe；若未检测到任何探针，应提示用户检查 USB 连接并重试；若探针配置错误（如 VID:PID 不匹配），应报告具体错误信息并建议运行 list 子命令确认可用探针
.bin 烧录必须显式提供地址
workflow build-debug 只走 one-shot 诊断包装，不启动需要人工接管的长期 DAP 会话
Windows 下若要用 probe-rs 驱动 J-Link，通常需要切换到 WinUSB，这会影响 SEGGER 官方工具继续使用；若仍依赖 J-Link 官方工具链，优先继续用现有 jlink skill

Files

SKILL.md and 7 other files (scripts) in probe-rs of zhinkgit/embeddedskills.

SKILL.md
README.md
config.example.json
scripts/probe_rs_exec.py
scripts/probe_rs_gdb.py
scripts/probe_rs_gdb_common.py
scripts/probe_rs_rtt.py
scripts/probe_rs_runtime.py

Open the folder on GitHubat commit 536c1f9

Compare with similar skills

Probe Rs 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.

Probe Rs compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Probe Rs this skillzhinkgit/embeddedskills	733	—	~767	Automated safety check: Pass	MIT	1 mo ago
Gdb CLIsickn33/agentic-awesome-skills	47k	2 repos	~1.4k	Automated safety check: Pass	MIT	today
Runtime Behavior Probeopenai/openai-agents-python	30k	—	~3.8k	Automated safety check: Pass	MIT	today
Runtime Behavior Proberedis/node-redis	18k	—	~4.4k	Automated safety check: Pass	MIT	yesterday
Probe Win95felixrieseberg/windows95	24k	—	~1.9k	Automated safety check: Pass	Custom licence	27 days ago
Probe Platformsnubjs/nub	4.4k	—	~2.6k	Automated safety check: Pass	MIT	today

Similar skills

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
Runtime Behavior Probe
openai/openai-agents-python
Official
Plan controlled runtime probes when explicitly invoked; execute only after the required probe approval.
30k GitHub stars~3.8k tokensUpdated today
DevelopmentAuto-check passed
Runtime Behavior Probe
redis/node-redis
Official
Plan and execute runtime-behavior investigations with temporary TypeScript probe scripts, validation matrices, state controls, and findings-first reports.
18k GitHub stars~4.4k tokensUpdated yesterday
DatabasesAuto-check passed
Probe Win95
felixrieseberg/windows95
Boot Windows 95 in Electron under Claude's control, without a human clicking anything.
24k GitHub stars~1.9k tokensUpdated 27 days ago
Auto-check passed
Probe Platforms
nubjs/nub
Bring a test harness or probe up on a NEW operating system (Windows or Linux), or debug one that fails there.
4.4k GitHub stars~2.6k tokensUpdated today
Auto-check passed
Catalog Probe
nubjs/nub
Run the build-jail catalog probe — measure the minimum OS capability grant a package's lifecycle scripts need, sweep a worklist of packages, and collate the results into the catalog.
4.4k GitHub stars~2.4k tokensUpdated today
Auto-check passed

Questions about Probe Rs

What does Probe Rs do?

probe-rs 下载与调试工具，用于探针发现、固件烧录、复位、内存读写、GDB Server 调试和 RTT 日志读取。. Probe Rs is an agent skill from zhinkgit/embeddedskills.

How do I install Probe Rs in Claude Code?

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

How do I install Probe Rs in Codex?

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

Can I use Probe Rs 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 probe-rs -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/probe-rs, .gemini/skills/probe-rs, .github/skills/probe-rs and .opencode/skills/probe-rs in your project.

What does Probe Rs need to run?

Going by SKILL.md and its folder, Probe Rs needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Probe Rs 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 Probe Rs 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 Probe Rs use?

Probe Rs 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 Probe Rs use?

About 767 tokens (SKILL.md is roughly 3.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Probe Rs?

Skills that share tags, products or a category with Probe Rs: Gdb CLI (sickn33/agentic-awesome-skills, 47k stars), Runtime Behavior Probe (openai/openai-agents-python, 30k stars), Runtime Behavior Probe (redis/node-redis, 18k stars) and Probe Win95 (felixrieseberg/windows95, 24k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Probe Rs?

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.

Probe Rs

Install Probe Rs

Facts

At a glance

What it does

Example prompts

Requirements

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

probe-rs 下载与调试

配置

环境级配置（skill/config.json）

工程级配置（.embeddedskills/config.json）

子命令

典型调用

核心规则

Files

Compare with similar skills

Similar skills

Gdb CLI

Runtime Behavior Probe

Runtime Behavior Probe

Probe Win95

Probe Platforms

Catalog Probe

More from zhinkgit/embeddedskills

Can

Eide

Jlink

Keil

Openocd

Serial

Questions about Probe Rs