MIT 授權的專案實作 Harness 工程課程（14 講、8 專案、15 種語言），提供可直接套用的範本、harness-creator 技能與 DeepSeek harness 設計解析——屬生態系學習資源，非安裝於 dsh 的外掛。
DSH 整合
生態系相關
作者聲明
安全稽核
未稽核
最後核實
2026-08-21
授權條款
MIT
01它能幫你完成什麼？
Learn how to build the environment that makes AI coding agents complete real engineering tasks reliably
14 lectures and 8 hands-on projects (around one evolving Electron knowledge-base app) covering the five harness subsystems: instructions, state, verification, scope, and session lifecycle
Engineers already using coding agents who want better stability and quality, and tech leads who need to understand how environment design affects agent performance
Improve an existing coding agent immediately with copy-ready harness templates
Starter templates (AGENTS.md, init.sh, feature_list.json, session progress log) dropped into your own repository so every agent session starts from the same state
Developers running coding agents — DeepSeek Harness (dsh), Claude Code, Codex or similar — on real projects who want more stable multi-session runs
Scaffold and audit a production-grade harness in your own repository
The harness-creator skill scaffolds AGENTS.md, feature lists, init.sh and verification workflows in minutes; audit-harness.sh checks a repo against all five harness subsystems and exits 0 when all CRITICAL items pass
Teams adopting harness engineering who want a quick scaffold and a repeatable audit for their agent workspace
02如何將外掛接入 DeepSeek Harness？
先決條件
- Familiarity with the terminal, git, and local development environments (course prerequisite)
- Node.js / npm to run the VitePress documentation site locally
- At least one coding agent (Claude Code, Codex, or another IDE/CLI agent supporting file editing, command execution, and multi-step tasks) to complete the projects
安裝步驟
- 01
Clone the repository, or read the course on the documentation website (walkinglabs.github.io/learn-harness-engineering)
- 02
Run `npm install` to install the VitePress tooling
$ npm install
- 03
Run `npm run docs:dev` and open the local URL that VitePress outputs in your browser
$ npm run docs:dev
驗證整合成功
作者未說明
03DSH 整合程度與能力邊界
Ecosystem learning resource: a course teaching harness engineering methodology (including a breakdown of DeepSeek's harness design) — read it online or locally, then apply its templates and methods to your own coding-agent workflows; it is not installed inside dsh.
Project-based harness engineering course
14 lectures + 8 hands-on projects + learning path in the repo's docs→a systematic method for the five harness subsystems (instructions, state, verification, scope, lifecycle) applied to real repositories
Copy-ready Resource Library
templates such as AGENTS.md, feature_list.json and init.sh→drop-in harness files you can use in your own repositories today
you copy template files into your own repositoryharness-creator skill + audit-harness.sh
your own project repository→a scaffolded production-grade harness (AGENTS.md, feature lists, init.sh, verification workflows); an audit that exits 0 when all CRITICAL items pass
harness-creator scaffolds harness files into your projectthe one-liner `curl ... | bash` downloads and executes a remote shell script; you can clone the repo and run `bash tools/audit-harness.sh` locally instead15-language content and PDF coursebooks
course sources translated into 15 languages→localized course pages; PDF coursebooks generated via `npm run pdf:build`
`npm run pdf:build` writes output files to artifacts/pdfs/
04適合誰？何時不該用？
適合
- Engineers already using coding agents who want better stability and quality, and tech leads who need to understand how environment design affects agent performance
- Developers running coding agents — DeepSeek Harness (dsh), Claude Code, Codex or similar — on real projects who want more stable multi-session runs
- Teams adopting harness engineering who want a quick scaffold and a repeatable audit for their agent workspace
不適合
- The hands-on projects require at least one coding agent (Claude Code, Codex, or another IDE/CLI agent with file editing, command execution and multi-step tasks). Without one you can read the course but cannot complete the projects as intended.
- The README's quick way to run audit-harness.sh pipes a remote script into bash (curl ... | bash), which executes network-fetched code on your machine. If you prefer not to, clone the repo and run `bash tools/audit-harness.sh /path/to/your/repo` locally instead.
05相容性、維護與安全提醒
- The hands-on projects require at least one coding agent (Claude Code, Codex, or another IDE/CLI agent with file editing, command execution and multi-step tasks). Without one you can read the course but cannot complete the projects as intended.
- The README's quick way to run audit-harness.sh pipes a remote script into bash (curl ... | bash), which executes network-fetched code on your machine. If you prefer not to, clone the repo and run `bash tools/audit-harness.sh /path/to/your/repo` locally instead.
- The course is actively evolving content — new lectures and projects were added in July and August 2026 — and has no tagged release, so course structure and materials may change between checkouts.
MIT · actively maintained (last push 2026-08-19)
06常見問題
這是安裝在 DeepSeek Harness 裡的外掛嗎？
不是。它是生態系學習資源——一個課程 repository。你可以在線閱讀，或在本機執行 `npm install` 後用 `npm run docs:dev` 預覽，再把課程方法與範本（AGENTS.md、init.sh、feature_list.json）套用到自己的 repository。課程不綁定特定代理，並收錄 DeepSeek 建構 harness 方式的解析（「一切皆外掛」、能力接縫、事件管線）。
開始實作專案前需要準備什麼？
需要熟悉終端機、git 與本機開發環境，並至少具備一個編碼代理——Claude Code、Codex，或任何支援檔案編輯、指令執行與多步驟任務的 IDE/CLI 代理。沒有這類工具仍可閱讀課程內容，但無法按預期完成實作專案。
課程的 harness 範本如何搭配我自己的編碼代理？
從資源庫取得入門範本放入專案根目錄即可：AGENTS.md 作為代理的操作手冊，加上 init.sh、feature_list.json 與工作階段進度記錄。README 說明進度檔案與代理無關：Codex、OpenHands、Antigravity 等編碼代理只要在根指令中要求啟動時讀取、交接前更新，即可使用同一份檔案。
harness-creator 技能和 audit-harness.sh 是什麼？
harness-creator 是可重複使用的代理技能，能在幾分鐘內為你的專案建立生產級 harness（AGENTS.md、功能清單、init.sh、驗證流程）。audit-harness.sh 是零相依的 shell 稽核腳本，依五大子系統（L03–L12）檢查現有 repository，所有 CRITICAL 項目通過時以結束代碼 0 退出，無需 Node.js。
課程有繁體中文或日文版本嗎？
有。課程提供 15 種語言，包含繁體中文、簡體中文與日文，翻譯完整覆蓋；也可以用 `npm run pdf:build` 在本機產生 PDF 教材。
07相關的 DSH 工作流程
archify
作者 tt-a1i
為編碼智慧體生成美觀可驗證的架構圖、時序圖與資料流圖，輸出自包含 HTML，支援動效與清晰匯出。
openviking
作者 volcengine
為 AI 智慧體打造的自進化上下文資料庫，統一智慧體記憶、知識 RAG 與技能。
nocobase
作者 nocobase
開源的 AI + 無程式碼應用搭建平臺：AI 在久經生產驗證的底層基礎設施與所見即所得的無程式碼介面之上工作，幫你快速構建 CRM、ERP 等業務系統，兼顧速度與可靠性。
skill
作者 anbeime
收錄最全、更新最快的技能Skills商店：精選原創技能包（涵蓋文件處理、內容創作、程式設計開發、機器學習、自動化工作流），全部打包好可直接安裝使用！同時自動抓取GitHub上萬個Skills專案，按分類、更新時間、Star數量整理。The most comprehensive and frequently updated AI Agent skill library, featuring curated skill packs across document processing, content creation, programming, machine learning, automated workflows, and many more domains.
08資料與來源
Learn Harness Engineering is a course dedicated to the engineering of AI coding agents.
[How DeepSeek builds its harness](docs/en/harness-designs/deepseek/index.md) — "everything is a plugin," capability seam…
此頁面根據專案公開文件、儲存庫中繼資料與 DSH Plugins 的結構化解析所產生；最後核實於 2026-08-21。發現錯誤？提交更正。
最佳 DeepSeek Harness 外掛
從全目錄挑出的 12 個值得優先安裝的外掛，涵蓋各個分類。