Beginner starter pack for DeepSeek Harness: welcome flow, 0→1 learning path, scenario-based plugin recommendations and a self-check checklist, paired with the dsh-handbook-zh Chinese tutorial repo.
Install
# from GitHub (first run asks for allowBuilds approval — follow the hint, retry)
dsh plugin --profile web add github:863683348/dsh-starter-zh
Any plugin you install runs third-party code with your own permissions — it can read your files, use your credentials, and reach the network, and tool approvals don’t sandbox it. GitHub-sourced plugins also run build scripts at install time. Only install sources you trust, and pin a commit (github:owner/repo#sha).
README
dsh-starter-zh is a beginner starter pack for DeepSeek Harness: install it and your agent instantly gains a welcome flow, a 0→1 learning path, scenario-based plugin recommendations, and a self-check checklist — paired with the dsh-handbook-zh Chinese tutorial repo.
"一切皆插件" — but where do you start? This plugin answers that question in Chinese, in-session.
What you get
| Feature | Tool / Section | What it does |
|---|---|---|
| Welcome | starter_zh action=welcome |
Greeting + what you can do next |
| Learning path | starter_zh action=path |
0→1 in 5 stages: run → profile → install → write → publish |
| Recommended plugins | starter_zh action=plugins |
Scenario groups (start here / focus & memory / security / productivity) |
| Self-check | starter_zh action=checklist |
10-item onboarding checklist |
| Guidance prompt | systemPrompt section |
Tells the model to use starter_zh when the user is a beginner |
Install
dsh plugin --profile <name> add dsh-starter-zh
Then ask your agent: "我是 DSH 新手,带我入门" — it will call starter_zh automatically.
Config
| Key | Default | Meaning |
|---|---|---|
sectionOrder |
10 | Prompt section order |
promptEnabled |
true | Inject the guidance prompt section |
handbookUrl |
dsh-handbook-zh repo | Companion tutorial URL in the welcome text |
Why this plugin
The DSH ecosystem exploded to thousands of plugins in 72 hours, but there is no systematic Chinese onboarding path. This starter pack fills that gap — it is the "from 0 to 1" entry point, backed by a full Chinese handbook repo.
Docs
- USAGE.md — model-side usage, tool parameters, config
- RELEASE.md — release checklist
Development
node --check lib/index.js && node --check lib/starter.js
node test/starter.test.mjs
node scripts/verify.mjs
Pure logic lives in lib/starter.js (zero deps, unit-tested); the Cordis plugin in lib/index.js registers the starter_zh tool and the prompt section.
License
MIT
Links
More in this category
tt-a1i/archify#integrations/deepseek-harness★ 13539
Generate validated, self-contained interactive architecture, workflow, sequence, data-flow, and lifecycle diagrams from repositories or system descriptions.
GanyuanRan/Aegis★ 1034
Software-engineering method pack for coding agents, with skills for baseline-first planning, systematic debugging, prompt hygiene, verification before completion, and repair/retirement tracking.
superdesigndev/superdesign-skill★ 424
Design skill for UI and marketing graphics on the Superdesign canvas: reads the repo for context, extracts its design system, then generates and iterates branchable design drafts, flow pages, and reusable components through the Superdesign CLI.
Ikalus1988/MisakaNet★ 394
Failure-recovery memory: search and record failure-recovery lessons from real engineering sessions, with BM25 + semantic RAG retrieval and a lessons knowledge base.
linhay/harmony-next.skills★ 324
HarmonyOS NEXT skill bundle for DeepSeek Harness with offline API references and DevEco, HDC, and emulator automation guidance.
Vladimir-Human/humanizer-ru#dsh★ 101
Cleans AI traces from Russian text: finds chatbot copy-paste artefacts (ChatGPT, Gemini, Grok, Perplexity, DeepSeek) and rewrites the text into natural prose on request; 39 regex markers with an evidence registry, offline, text-only bundle.