Agent skill

Workflow

embeddedskills 的薄编排层，用于在当前 workspace 中发现工程、选择 build/flash/debug/observe 后端、串联 .embeddedskills/state.json，并聚合底层 skill 的结果。

MITAuto-check passed

Install Workflow

skills CLI

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

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

GitHub CLI

$ gh skill install zhinkgit/embeddedskills workflow --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/workflow .claude/skills/workflow && 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 "workflow" agent skill from https://github.com/zhinkgit/embeddedskills/tree/main/workflow into .claude/skills/workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "workflow", 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/workflow

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 workflow -a codex

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

GitHub CLI

$ gh skill install zhinkgit/embeddedskills workflow --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/workflow .agents/skills/workflow && 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 "workflow" agent skill from https://github.com/zhinkgit/embeddedskills/tree/main/workflow into .agents/skills/workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "workflow", 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 workflow -a cursor

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

GitHub CLI

$ gh skill install zhinkgit/embeddedskills workflow --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/workflow .cursor/skills/workflow && 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 "workflow" agent skill from https://github.com/zhinkgit/embeddedskills/tree/main/workflow into .cursor/skills/workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "workflow", 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 workflow

--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 workflow -a gemini-cli

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

GitHub CLI

$ gh skill install zhinkgit/embeddedskills workflow --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/workflow .gemini/skills/workflow && 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 "workflow" agent skill from https://github.com/zhinkgit/embeddedskills/tree/main/workflow into .gemini/skills/workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "workflow", 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 workflow

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 workflow -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/workflow .github/skills/workflow && 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 "workflow" agent skill from https://github.com/zhinkgit/embeddedskills/tree/main/workflow into .github/skills/workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "workflow", 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 workflow -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 workflow --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/workflow .opencode/skills/workflow && 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 "workflow" agent skill from https://github.com/zhinkgit/embeddedskills/tree/main/workflow into .opencode/skills/workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "workflow", 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: workflow
GitHub stars: 733
Token cost: ~613 tokens
SKILL.md length: 112 words
Files: 6 (incl. scripts)
Skills in repo: 11
Repo updated: Sep 3, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

embeddedskills 的薄编排层，用于在当前 workspace 中发现工程、选择 build/flash/debug/observe 后端、串联 .embeddedskills/state.json，并聚合底层 skill 的结果。

Works in 3 steps: CLI 参数（优先级最高） → 配置文件（次优先） → 自动发现（兜底）
SKILL.md covers 命令, 配置说明 and 规则
Runs Python scripts from its folder; calls python

What it does

Workflow is an agent skill from zhinkgit/embeddedskills. embeddedskills 的薄编排层，用于在当前 workspace 中发现工程、选择 build/flash/debug/observe 后端、串联 .embeddedskills/state.json，并聚合底层 skill 的结果。当用户明确输入以下命令之一："一键构建烧录"、"自动诊断"、"串起 build - flash - debug - observe" 或显式调用 /workflow 时触发。

Its SKILL.md is about 610 tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts (for example `README.md`, `config.example.json` and `scripts/workflow_plan.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

“一键构建烧录”
“串起 build - flash - debug - observe”
“Use the workflow skill to embeddedskill 的薄编排层，用于在当前 workspace 中发现工程、选择 build/flash/debug/observe 后端、串联 .embeddedskills/state.json，并聚合底层 skill 的结果”
“/workflow”

Requirements

Python 3

Workflow steps

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

CLI 参数（优先级最高）
配置文件（次优先）
自动发现（兜底）

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 3 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

Workflow loads about 613 tokens when it runs. Until then it costs about 55 tokens; SKILL.md has 112 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~55
When it runs · the whole SKILL.md, loaded when a task matches: ~613

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). 112 words, ~613 tokens.

Download SKILL.mdSave it as .claude/skills/workflow/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.

name: workflow
description: embeddedskills 的薄编排层，用于在当前 workspace 中发现工程、选择 build/flash/debug/observe 后端、串联 .embeddedskills/state.json，并聚合底层 skill 的结果。当用户明确输入以下命令之一："一键构建烧录"、"自动诊断"、"串起 build -> flash -> debug -> observe" 或显式调用 /workflow 时触发。
argument-hint: [plan|build|build-flash|build-debug|observe|diagnose] ...

Workflow 编排层

本 skill 不重复实现底层逻辑，只做发现、选择、串联和聚合。

支持 Keil / GCC / EIDE 三种构建后端，以及 jlink / openocd / probe-rs 三种 flash/debug/observe 后端。

observe 阶段当前会给出 jlink:rtt、jlink:swo、openocd:semihosting、openocd:itm、probe-rs:rtt 这几类候选观测后端。

命令

bash

python <skill-dir>/scripts/workflow_plan.py --json
python <skill-dir>/scripts/workflow_run.py plan --json
python <skill-dir>/scripts/workflow_run.py build --json
python <skill-dir>/scripts/workflow_run.py build-flash --json
python <skill-dir>/scripts/workflow_run.py build-debug --json
python <skill-dir>/scripts/workflow_run.py observe --json
python <skill-dir>/scripts/workflow_run.py diagnose --json

配置说明

workflow 不再维护独立的工程配置结构，所有工程参数统一从 .embeddedskills/config.json 读取。

配置结构

.embeddedskills/config.json 中的 workflow 段仅包含首选后端配置：

json

{
  "workflow": {
    "preferred_build": "auto",
    "preferred_flash": "auto",
    "preferred_debug": "auto",
    "preferred_observe": "auto"
  }
}

workflow 通过读取 .embeddedskills/config.json 中其他 skill 的配置段来获取工程参数（如 keil.project、eide.project、eide.config、jlink.device、probe-rs.chip 等）。

参数解析顺序

按以下决策树依次判断，命中即停止：

CLI 参数（优先级最高）
- 条件：用户在命令行传入 --build-backend、--flash-backend 等参数
- 示例：workflow_run.py build-flash --build-backend=keil --flash-backend=jlink
- --build-backend 可选值：auto / keil / gcc / eide
- 行为：直接使用该参数指定的后端，跳过后续步骤
配置文件（次优先）
- 条件：CLI 未指定，且 .embeddedskills/config.json 的 workflow 段中对应 preferred_* 字段不为 "auto"
- 示例："preferred_build": "keil" → 使用 keil 作为构建后端
- 行为：读取配置值并使用，跳过自动发现
自动发现（兜底）
- 条件：CLI 未指定，且配置中 preferred_* 为 "auto" 或字段缺失
- 示例："preferred_flash": "auto" → 扫描 workspace 自动推断可用 flash 后端
- 行为：枚举候选后端列表；若唯一则直接使用，若多个则返回列表请用户确认

成功执行后，实际使用的后端会自动写回 .embeddedskills/config.json 的 workflow 段。

规则

发现多个工程或多个候选后端时，只返回候选列表，不自动猜测
构建、烧录、调试、观测之间优先通过 .embeddedskills/state.json 串联
observe 只生成推荐命令，不在 workflow 内直接长时间占用观测通道
失败时优先返回哪个阶段失败，以及底层脚本的结构化错误
workflow 与其他 Skill 的协同只通过 .embeddedskills/config.json、.embeddedskills/state.json 和子进程调用底层 Skill

Files

SKILL.md and 5 other files (scripts) in workflow of zhinkgit/embeddedskills.

SKILL.md
README.md
config.example.json
scripts/workflow_plan.py
scripts/workflow_run.py
scripts/workflow_runtime.py

Open the folder on GitHubat commit 536c1f9

Compare with similar skills

Workflow 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.

Workflow compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Workflow this skillzhinkgit/embeddedskills	733	—	~613	Automated safety check: Pass	MIT	1 mo ago
Flashing Contentthedaviddias/Front-End-Checklist	74k	—	~530	Automated safety check: Pass	MIT	yesterday
Flashnodetool-ai/nodetool	556	—	~2.2k	Automated safety check: Pass	AGPL-3.0	today
Optimizing Attention FlashOrchestra-Research/AI-Research-SKILLs	13k	5 repos	~2.5k	Automated safety check: Pass	MIT	3 mo ago
Hsb FlashNVIDIA/skills	3.5k	1 repos	~4.4k	Automated safety check: Notes	Apache-2.0	today
Jetson Flash ImageNVIDIA/skills	3.5k	—	~4.9k	Automated safety check: Notes	Apache-2.0	today

Similar skills

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 yesterday
Frontend & DesignAuto-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
Hsb Flash
NVIDIA/skills
Official
Flash the FPGA on an HSB board connected to an NVIDIA devkit.
3.5k GitHub starsUsed in 1 repo~4.4k tokens
Auto-check: notes
Jetson Flash Image
NVIDIA/skills
Official
A skill your agent uses to flash a promoted BSP image to a Jetson DUT in RCM mode via flash.sh or l4tinitrdflash.sh.
3.5k GitHub stars~4.9k tokensUpdated today
AI & LLM EngineeringAuto-check: notes
Gemini Omni Flash API
sickn33/agentic-awesome-skills
A skill your agent uses for generative video editing, text-to-video, image-referenced video generation, and first-frame-to-video transition animations using the official google-genai SDK.
47k GitHub starsUsed in 1 repo~4.2k tokens
Media & CreativeAuto-check passed

Questions about Workflow

What does Workflow do?

embeddedskills 的薄编排层，用于在当前 workspace 中发现工程、选择 build/flash/debug/observe 后端、串联 .embeddedskills/state.json，并聚合底层 skill 的结果。. Workflow is an agent skill from zhinkgit/embeddedskills.

How do I install Workflow in Claude Code?

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

How do I install Workflow in Codex?

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

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

What does Workflow need to run?

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

Does Workflow 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 Workflow 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 Workflow use?

Workflow 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 Workflow use?

About 613 tokens (SKILL.md is roughly 2.5k 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 Workflow?

Skills that share tags, products or a category with Workflow: Flashing Content (thedaviddias/Front-End-Checklist, 74k stars), Flash (nodetool-ai/nodetool, 556 stars), Optimizing Attention Flash (Orchestra-Research/AI-Research-SKILLs, 13k stars) and Hsb Flash (NVIDIA/skills, 3.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Workflow?

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.

Workflow

Install Workflow

Facts

At a glance

What it does

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Workflow 编排层

命令

配置说明

配置结构

参数解析顺序

规则

Files

Compare with similar skills

Similar skills

Flashing Content

Flash

Optimizing Attention Flash

Hsb Flash

Jetson Flash Image

Gemini Omni Flash API

More from zhinkgit/embeddedskills

Can

Eide

Jlink

Keil

Openocd

Serial

Questions about Workflow