Asher-2000/dsh-expert-mode

DSH (DeepSeek Harness) 专家模式 agent preset — 首席协调官 + 11 位领域专家子代理 Expert-mode preset for DeepSeek Harness

Bundle verified MIT Unknown v0.3.0
Bundle verified

Listed

5

Tools

Bundle verified

★ 5 View on GitHub
Versionv0.3.0
LanguageUnknown
LicenseMIT
View on GitHub

Preview

Preview 1 of 2: Asher-2000/dsh-expert-mode
Preview 2 of 2: Asher-2000/dsh-expert-mode

What it does

Expert-mode agent preset for DeepSeek Harness (v0.3.0, bilingual EN/ZH): a chief coordinator plus 11 domain-expert subagents with automatic task delegation. New: Three-Anchor constraint (recall/convergence/anti-drift per turn) and Near-distance Guidance (identity/task/output template per expert). Experts: data analyst, copywriter, legal review, product manager, frontend, UI/UX, architect, social media ops, growth hacker, quant finance, finance.

Best for

  • DSH users who want a bilingual coordinator preset that automatically delegates work to 11 named domain experts.
  • Cross-domain tasks spanning areas such as data analysis, product, frontend, UI/UX, architecture, legal, growth, or finance.
  • Complex workflows that benefit from multiple specialist subagents and per-turn recall, convergence, and anti-drift constraints.

Not ideal for

  • Users who prefer direct manual control of a single agent without automatic delegation.
  • Simple tasks where a coordinator-and-expert preset adds little value, even though the coordinator can handle them directly.
  • Specialist workflows outside the 11 domains named in the authoritative preset description.

README

🧠 DSH Expert Mode

1 Coordinator + 16 Experts — Full-Stack Multi-Agent Team
首席协调官 + 16 位领域专家 — 全栈多智能体团队

dsh-plugin Featured in Awesome DSH Plugin Release License: MIT Stars

中文 · English

✨ What it does

Install this preset and DSH automatically becomes a “Chief Coordinator” mode:

Scenario Behavior
Receives task Identifies domain → delegates to the best expert
Complex tasks Dispatches multiple experts in parallel
Simple tasks Coordinator handles directly — no forced delegation
Task complete Experts stay online for follow-up modifications

No custom prompts to write. No multi-config to maintain. Just install and use.

🖼️ Demo

DSH Expert Mode main interface
Select the “Expert Mode” preset in DSH workspace to use

Expert Mode running
5 expert subagents working in parallel, with real-time token usage and timing

🧩 16 Experts

🎯 Full-Stack Core (6)
Expert Tool Domain
🖥️ Frontend Dev expert_frontend_dev Web frontend, React/Vue, CSS/UI
🖥️ Backend Dev expert_backend_dev API, server logic, authentication
🗄️ Database expert_database Schema design, SQL, optimization
🏗️ Architect expert_architect System design, tech selection
🛠️ DevOps expert_devops CI/CD, Docker, K8s, deployment
🧪 QA Engineer expert_qa_engineer Testing strategy, automation
🔒 Security & Data (3)
Expert Tool Domain
🔒 Security expert_security Code audit, vulnerabilities, hardening
📊 Data Analyst expert_data_analyst Statistics, visualization, insights
🎨 UI/UX Design expert_uiux_design Interface design, design systems
💼 Business (7)
Expert Tool Domain
📋 Product Manager expert_product_manager PRD, requirements, competitor research
✍️ Copywriter expert_copywriter Marketing copy, content creation
⚖️ Legal Review expert_legal_review Contract review, legal risk
📱 Social Media expert_social_media Multi-platform distribution
🚀 Growth Hacker expert_growth Growth strategy, A/B testing
💹 Quant Finance expert_quant_finance Quantitative models, risk
💰 Finance expert_finance Financial analysis, budget

🛡️ Features

Feature Description
🎯 Smart Delegation Auto-identifies task domain and routes to the best expert
🚀 Fast Track Simple tasks handled directly — no forced delegation
🔄 Five-Anchor Constraint Prevents topic drift with per-turn self-check
🤝 Cross Review High-risk tasks get multi-expert independent review
💾 Experience Pool Lessons learned are saved and injected next time
💬 Subagent Communication Experts can communicate via send_message (continuable mode)
⚡ Fault Recovery Auto-retry on timeout, strategy switch on failure
📉 Progressive Disclosure Methodology injected on-demand, 28% token savings
🌐 Bilingual Complete EN/ZH documentation

📦 Installation

# In DSH workspace
dsh plugin add @deepseek-ai/dsh-expert-mode

Then select “专家模式” in the workspace preset selector.

🚀 Quick Start

  1. Install the plugin
  2. Select “专家模式” preset
  3. Ask any question — the coordinator auto-delegates to the right expert
Example
User: 帮我设计一个用户认证系统

Coordinator:
  → 识别领域: 后端开发 + 安全
  → 委派 Backend Dev: API 设计、JWT 实现
  → 委派 Security: 安全审计、漏洞防护
  → 汇总输出完整方案

🏗️ Architecture

┌─────────────────────────────────────────────────────────────────┐
│                    Expert Mode Architecture                      │
├─────────────────────────────────────────────────────────────────┤
│                                                                  │
│  ┌──────────────────────────────────────────────────────────┐   │
│  │              Chief Coordinator (协调官)                    │   │
│  │  • Task analysis    • Domain identification               │   │
│  │  • Expert routing   • Result aggregation                  │   │
│  └──────────────────────────────────────────────────────────┘   │
│                           │                                      │
│           ┌───────────────┼───────────────┐                     │
│           ▼               ▼               ▼                     │
│  ┌─────────────┐  ┌─────────────┐  ┌─────────────┐            │
│  │  Frontend   │  │  Backend    │  │  DevOps     │            │
│  │  Database   │  │  Security   │  │  QA         │            │
│  │  Architect  │  │  ...        │  │  ...        │            │
│  └─────────────┘  └─────────────┘  └─────────────┘            │
│                                                                  │
└─────────────────────────────────────────────────────────────────┘

📚 Documentation

Document Description
User Guide Installation and usage
Expert Methods Detailed methodology for each expert
Architecture System design details
Changelog Version history

🤝 Contributing

  1. Fork the repository
  2. Create a feature branch
  3. Commit your changes
  4. Push to the branch
  5. Open a Pull Request

📄 License

MIT License - see LICENSE for details.

🙏 Acknowledgments

Frequently Asked QuestionsFAQ

Use the verified command dsh plugin --profile default add github:Asher-2000/dsh-expert-mode in a DSH-enabled shell. The command resolves the public package metadata and keeps the plugin attached to the catalog identity shown on this page.

tt-a1i/archify#integrations/deepseek-harness★ 14,012

Generate validated, self-contained interactive architecture, workflow, sequence, data-flow, and lifecycle diagrams from repositories or system descriptions.

MIT
liustack/modlens★ 2,925

Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).

MIT
GanyuanRan/Aegis★ 1,048

Software-engineering method pack for coding agents, with skills for baseline-first planning, systematic debugging, prompt hygiene, verification before completion, and repair/retirement tracking.

MIT
ysr666/dsh-vision-router★ 680

Free vision for text-only agents: built-in keyless vision chain plus pixel tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots); paste an image to use it.

MIT