Embedded Systems Architect

Embedded systems and Edge AI architecture assistant for development-board projects. Use when the user works with dev boards, SoC, MCU or microcontroller (datasheet, TRM, HDK, schematics), firmware or RTOS development, cross-compilation, SDK / BSP / sample code, board families such as Jetson, Raspberry Pi, ESP32, STM32, deploying AI models to NPU / TinyML runtimes (ONNX, TFLite, vendor toolchains, operator compatibility, quantization), estimating performance / memory / power, or flashing, recovery and board bring-up. 嵌入式系統與 Edge AI 開發助手:開發板與 SoC 評估、韌體 / RTOS / 微控制器開發、交叉編譯、SDK/BSP/sample code 分

6 starsAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add Zachariah9420/embedded-systems-architect --skill embedded-systems-architect

Manual install

git clone --depth 1 https://github.com/Zachariah9420/embedded-systems-architect.git /tmp/embedded-systems-architect
mkdir -p ~/.claude/skills
cp -r /tmp/embedded-systems-architect/. ~/.claude/skills/embedded-systems-architect

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# 嵌入式系統 AI 架構師

探索式、證據導向的嵌入式開發助手。核心循環:**建立認知 → 選模組 → 產生方案或最小實驗 → 收集結果 → 更新認知**。你的價值不在檢索文件,而在跨層推理(產品情境 ↔ 模型 ↔ runtime ↔ 工具鏈 ↔ 系統軟體 ↔ 硬體 ↔ 部署)與誠實管理不確定性。

路徑約定:本檔與 references 內出現的 `references/`、`scripts/`、`assets/` 路徑一律相對於本 skill 安裝目錄(即本檔所在目錄),執行腳本時改用絕對路徑;`EMBEDDED_CONTEXT.md` 位於使用者專案根目錄(預設 = 目前工作目錄)。單檔安裝(只有本檔、無 references/ 與 scripts/)時:照本檔的原則、路由分類與硬閘門行動,缺少的細則以工程常識補位並明說「細則來自完整版」;適時告知使用者完整安裝方式(`git clone https://github.com/Zachariah9420/embedded-systems-architect`)。

## 最高原則

1. **專案材料優先於模型記憶**:板卡 revision、SDK 版本、私有模型、實測 log 才是依據;你的既有知識只提供搜尋方向與工程常識。
2. **缺的資訊不補造**:查無就標「資料不足」,並說明如何取得。
3. **理論規格不等於實際效能**:TOPS、MHz、RAM 容量單獨不得推出「跑得動」;結論必須通過 runtime、算子支援、記憶體頻寬、資料搬移的逐層檢查(檢查表見 references/performance-estimation.md)。
4. **口述與轉述的規格一律待驗證**:使用者或第三方口頭提供的數字(「datasheet 寫 8MB」「聽說有 high_performance 版」)標「待驗證」,與手上材料核對後才可用於計算或操作;要反駁使用者的說法之前同樣先查本地材料——你的記憶與材料矛盾時,以材料為準。

## 起手式(每次觸發,順序固定)

1. 檢查使用者專案根目錄的 `EMBEDDED_CONTEXT.md`:
   - 存在 → 讀入,從已有狀態繼續;已記錄的事實不重問。
   - 不存在 → 依 `assets/project-output-templates/embedded-context-template.md` 建立,只填推得出的欄位,其餘留「未知」。
   - 例外:純諮詢、無任何專案材料時不建檔,直接回答;出現第一個專案事實(板卡、SDK、模型、實測結果)時再建立。
2. 辨識使用者當下目標(可能從任何位置開始:剛拿到板子、轉換失敗、效能不足、燒錄失敗、準備量產),查路由表選模組;不走固定流程,不把釐清情境變成僵化問卷。使用者只丟一批材料、尚未說明目標時,**不先追問**:直接盤點分類全部材料、建立認知摘要,回報這批材料能支撐哪些工作與還缺什麼,讓使用者挑下一步。
3. 提問紀律:只問會改變技術決策的問題,一次 ≤3 個,並說明各問題影響哪個決策。

## 模組路由表(按需讀 reference,不預先全讀)

| 使用者情境 | 模組 | 先讀 |
|---|---|---|
| 丟來一批下載好的材料(文件 / SDK / repo / 模型),還沒說要做什麼 | 平台發現 + 文件與程式碼導航 | references/hardware-discovery.md + references/sdk-sample-analysis.md |

Read the full skill on GitHub

Details

Skill name: embedded-systems-architect
Repository: Zachariah9420/embedded-systems-architect
License: MIT
Repo updated: 12 August 2026

FAQ

What does the Embedded Systems Architect skill do?

How do I install the Embedded Systems Architect skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add Zachariah9420/embedded-systems-architect --skill embedded-systems-architect. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Embedded Systems Architect popular?

It lives in Zachariah9420/embedded-systems-architect, which has 6 GitHub stars and 0 forks.

Related skills

End Game Thinking

shosmer/end-game-thinking-skill

Strategic foresight methodology for reasoning backward from possible futures to identify defensible positions in the present. Combines backward induction, inversion, premortem analysis, regret minimization, and scenario stress-testing into a structured exercise that produces a written artifact. MANDATORY TRIGGERS: end game thinking, endgame, what positions should I hold, how do I prepare for AI, future-proofing, strategic positioning, what happens when AI, stress test my strategy, what are my blindspots, competitive positioning for AI, scenario planning, backward induction, inversion exercise,

AI, LLMs & Agents

Create Operator

riceshowerX/arknights-operator-skill

Distill an Arknights operator into an AI Skill. Generate Knowledge + Persona with 5-layer structure, evolution support. | 将明日方舟角色蒸馏成AI Skill，生成知识库+5层人格，支持持续进化。

AI, LLMs & Agents

Gpt Pro

199-biotechnologies/claude-skill-gpt-pro

Package files + structured prompts for manual copy-paste into GPT-5.4 Pro for deep reasoning review. Use when user says 'send to GPT Pro', 'GPT Pro review', 'ChatGPT Pro review', 'prepare for GPT', 'package for GPT Pro', 'get GPT to review', 'GPT Pro analysis', 'upload to ChatGPT', 'gpt-pro', '/gpt-pro', 'pack for GPT', 'bundle for ChatGPT', 'have ChatGPT check this', 'send this to GPT', 'GPT deep review'. Creates structured prompt + file bundle as tar.gz in ~/Documents/GPT Pro Analysis/ and copies prompt to clipboard for manual paste into ChatGPT Pro.

AI, LLMs & Agents

Claude Code Starter

cassmtnr/claude-code-starter

Analyze a project's tech stack and generate comprehensive Claude Code configuration files (.claude/ directory with CLAUDE.md, skills, agents, rules, and commands). Use when setting up Claude Code for a new or existing repository.

AI, LLMs & Agents

Hubspot AI Context

chadstamm/claude-skill-hubspot-ai-context

Fill HubSpot's AI Context page (Business tab + Customers tab — ICPs and Personas) by crawling a client website, researching competitors and brand reputation (positive + negative), and generating click-to-copy paste-sheet HTML. Use when setting up a new client in HubSpot's AI/Breeze Intelligence layer or when refreshing existing context. Triggers — "fill out AI context", "set up HubSpot ICPs", "create paste sheet for [client]", "generate Breeze Intelligence context", "research competitors for [client]".

AI, LLMs & Agents

Chinese De AI Writing

tangwenwen-md/chinese-de-ai-writing

中文去 AI 味：审稿、改稿、写作、流水线审核四种模式，专管简体中文。规则按证据分级：只有人机语料实测成立的特征才当硬规则，社区共识特征要"命中且空泛"才改，已被实测推翻的流行规则（调句长、删设问、删比喻、加口语词、加错别字、同义词替换）明确不用。最高约束是信息守恒：不编造经历、病例、数字、引文，不改论断强度。医学内容尤其如此。附 scripts/zh_ai_scan.py：量化扫描破折号、翻案腔、提示性冒号、段首零回指等 10 项实测特征，给出每千字密度和人机基线对照。文体分档：小红书/社媒、口播稿与短剧台词旁白、科普、正式文书（标书、汇报、公文）、中文学术。触发词：「去AI味」「去 AI 味」「AI味太重」「AI腔」「一眼AI」「像AI写的」「不像人话」「说人话」「改得像人写的」「这段有没有AI味」「帮我审一下AI味」「口播稿太书面」「台词不像人说的」「小红书文案太AI」「标书AI味」「中文humanize」。也用于 Claude 自己产出中文正文（小红书文案、科普稿、台词、汇报）之后的自检。不管：英文文本；以"降低知网/朱雀 AIGC 检测率"为唯一目标的改写（本 skill 改的是写法，不承诺过检测，也不用错别字、回译等对抗手段）；视觉层面的 AI 味；剧情结构与留存。

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.