Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add zhinkgit/embeddedskills --skill workflowgit clone --depth 1 https://github.com/zhinkgit/embeddedskillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/zhinkgit/embeddedskills/workflow)<a href="https://agentmods.dev/skills/zhinkgit/embeddedskills/workflow"><img src="https://agentmods.dev/badge/skills/zhinkgit/embeddedskills/workflow/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/zhinkgit/embeddedskills/workflow"><img src="https://agentmods.dev/badge/skills/zhinkgit/embeddedskills/workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00088 | $0.00993 |
| Opus 5.5 | $0.00035 | $0.00397 |
| Sonnet 5.5 | $0.00018 | $0.00199 |
| Haiku 4.5 | $0.00009 | $0.00099 |
Grade A, and why
workflow scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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
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:
{
"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
- 条件:用户在命令行传入
-
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
- 条件:CLI 未指定,且
-
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
- 条件:CLI 未指定,且配置中
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
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 80 lines · 88 tokens per session scan A 5187fa1d3580
workflow is a skill published in the GitHub repository zhinkgit/embeddedskills (747 stars, last pushed 1mo ago), licensed MIT. It adds 88 tokens to every session and 993 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
vscode-doctor
Diagnose slow or freezing VS Code-compatible editors with evidence-first, zero-hardcoded-assumption workflow. Use when the user reports editor lag, typing delay, UI freezes, extension host stalls, file watcher noise, high editor CPU/RSS, uses VS Code/Cursor as a file browser over a large folder, or wants a safe editor…
review-agent-harness
Review whether a repository's coding-agent harness can reliably carry work from intent through controlled execution, verification, delivery, and learning. Use when asked to assess agent readiness, repeated agent failures, Rules/Skills/Hooks/Memory effectiveness, missing validation or recovery loops, or whether a…
codebase-audit
A read-only method for auditing an entire codebase across contracts, data integrity, errors, security, architecture, technical debt, configuration, and caching. It produces prioritized findings and a repair roadmap.
codex-log-guard
Diagnose excessive Codex local SQLite diagnostic log writes with read-only evidence by default. Use when a user mentions logs2.sqlite, logs2.sqlite-wal, blockloginserts, SSD/TBW wear, or explicitly asks to protect, clean up, verify, or restore Codex diagnostic logging.
codex-agent
Use when you want a second-opinion review via Codex CLI, cross-verification after another agent implements changes, debugging help, or alternative implementation proposals. Requires Codex CLI to be installed and authenticated.
contribution-architect
Use when a contributor wants to move beyond simple bug fixes into architectural improvements, technical debt discovery, design proposals, or module ownership opportunities.