# ๐ง DSH Expert Mode
1 Coordinator + 17 Experts โ Full-Stack Multi-Agent Team
้ฆๅธญๅ่ฐๅฎ + 17 ไฝ้ขๅไธๅฎถ โ ๅ
จๆ ๅคๆบ่ฝไฝๅข้
ไธญๆ ยท English
---
## โจ What it does
Install this preset and DSH automatically becomes a "Chief Coordinator" mode:
| Scenario | Behavior |
|----------|----------|
| Receives task | Identifies domain โ delegates to the best expert |
| Complex tasks | Dispatches multiple experts in parallel |
| Simple tasks | Coordinator handles directly โ 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.**
---
## ๐ผ๏ธ Demo
Select the "Expert Mode" preset in DSH workspace to use
5 expert subagents working in parallel, with real-time token usage and timing
---
## ๐งฉ 17 Experts
### ๐ฏ Full-Stack Core (6)
| Expert | Tool | Domain |
|--------|------|--------|
| ๐ฅ๏ธ Frontend Dev | `expert_frontend_dev` | Web frontend, React/Vue, CSS/UI |
| ๐ฅ๏ธ Backend Dev | `expert_backend_dev` | API, server logic, authentication |
| ๐๏ธ Database | `expert_database` | Schema design, SQL, optimization |
| ๐๏ธ Architect | `expert_architect` | System design, tech selection |
| ๐ ๏ธ DevOps | `expert_devops` | CI/CD, Docker, K8s, deployment |
| ๐งช QA Engineer | `expert_qa_engineer` | Testing strategy, automation |
### ๐ Security & Data (3)
| Expert | Tool | Domain |
|--------|------|--------|
| ๐ Security | `expert_security` | Code audit, vulnerabilities, hardening |
| ๐ Data Analyst | `expert_data_analyst` | Statistics, visualization, insights |
| ๐จ UI/UX Design | `expert_uiux_design` | Interface design, design systems |
### ๐ผ Business (7)
| Expert | Tool | Domain |
|--------|------|--------|
| ๐ Product Manager | `expert_product_manager` | PRD, requirements, competitor research |
| โ๏ธ Copywriter | `expert_copywriter` | Marketing copy, content creation |
| ๐ฌ Media Creator | `expert_media_creator` | Storyboard, AI image, AI video, final cut |
| โ๏ธ Legal Review | `expert_legal_review` | Contract review, legal risk |
| ๐ฑ Social Media | `expert_social_media` | Multi-platform distribution |
| ๐ Growth Hacker | `expert_growth` | Growth strategy, A/B testing |
| ๐น Quant Finance | `expert_quant_finance` | Quantitative models, risk |
| ๐ฐ Finance | `expert_finance` | Financial analysis, budget |
---
## ๐ก๏ธ Features
| Feature | Description |
|---------|-------------|
| ๐ฏ **Smart Delegation** | Auto-identifies task domain and routes to the best expert |
| ๐ **Fast Track** | Simple tasks handled directly โ no forced delegation |
| ๐ **Five-Anchor Constraint** | Prevents topic drift with per-turn self-check |
| ๐ค **Cross Review** | High-risk tasks get multi-expert independent review |
| ๐พ **Experience Pool** | Lessons learned are saved and injected next time |
| ๐ฌ **Inter-Expert Bus** | File-based message bus (bus.py): experts send/read directly, zero coordinator relay, P2P capable |
| ๐ **Taskboard** | File-system task scheduler (taskboard.py): pending/ready/running/done/failed state machine, dependency DAG, retry, crash recovery โ real scheduling, not just chat coordination |
| ๐ฆ **Quality Gates** | 5-stage pipeline for high-risk tasks: requirement clarity โ implementation โ verification โ review โ integration. Independent-expert review with 2-round rework limit |
| โก **Fault Recovery** | Auto-retry on timeout, strategy switch on failure |
| ๐ **Progressive Disclosure** | Methodology injected on-demand, 28% token savings |
| ๐ **Bilingual** | Complete EN/ZH documentation |
---
## ๐ฆ Installation
### Option A: npm one-click (recommended) ๐
The package is published on npm as [`dsh-expert-mode`](https://www.npmjs.com/package/dsh-expert-mode). You can install it with the DSH plugin manager or npm directly:
```bash
# In DSH workspace โ via plugin manager
dsh plugin add dsh-expert-mode
# ...or install the npm package directly
npm install dsh-expert-mode
```
> โน๏ธ **How agent-presets work**: this is an **agent-preset plugin**, not a Cordis service plugin. Installing the npm package pulls all files into your `node_modules` โ but the preset only **activates** once its files are mounted into DSH's preset discovery directory. The preset ships a copy step (below) that makes this one command.
### Option B: One-command preset mount (recommended for activation)
After installing the npm package, mount the preset into DSH's preset discovery directory:
```bash
# 1. Find where npm put the package
# (usually ./node_modules/dsh-expert-mode in your DSH workspace, or globally)
# 2. Mount the preset into DSH's agent-presets directory
mkdir -p ~/.dsh/.agent-presets/expert-mode
cp -r node_modules/dsh-expert-mode/agent.cordis.yml \
node_modules/dsh-expert-mode/preset.yml \
node_modules/dsh-expert-mode/cordis.patch.yml \
~/.dsh/.agent-presets/expert-mode/
# If you want the full methodology docs (methods/, experts/, comm/ bus, taskboard):
# cp -r node_modules/dsh-expert-mode/.expert-mode ~/.dsh/.agent-presets/expert-mode/
# 3. Restart DSH web, then select "ไธๅฎถๆจกๅผ" in the workspace preset selector
dsh web
```
> **Note**: `~/.dsh/.agent-presets/` is DSH's preset discovery directory. Each subdirectory = one preset. The preset name comes from `preset.yml`'s `name` field.
### Option C: Manual install from GitHub
Clone the repository, then copy the preset into DSH's agent-presets directory:
```bash
# 1. Clone anywhere
git clone https://github.com/Asher-2000/dsh-expert-mode.git
cd dsh-expert-mode
# 2. Copy the preset into DSH's agent-presets directory
mkdir -p ~/.dsh/.agent-presets/expert-mode
cp -r agent.cordis.yml preset.yml cordis.patch.yml ~/.dsh/.agent-presets/expert-mode/
# If you want the full methodology docs (methods/, experts/, comm/ bus), copy the whole tree:
# cp -r .expert-mode ~/.dsh/.agent-presets/expert-mode/
# 3. Restart DSH web, then select "ไธๅฎถๆจกๅผ" in the workspace preset selector
dsh web
```
> **Note**: `~/.dsh/.agent-presets/` is DSH's preset discovery directory. Each subdirectory = one preset. The preset name comes from `preset.yml`'s `name` field.
Then select **"ไธๅฎถๆจกๅผ"** in the workspace preset selector.
### Optional: Cross-session memory (recommended)
The expert-mode preset itself does **not** register the cross-session memory service โ it is a HOST-PLANE plugin, and registering it inside a preset conflicts with the host composition (causing preset mount failure). To enable cross-session memory, install [dsh-memory-connect](https://github.com/Asher-2000/dsh-memory-connect) separately into the **host composition**:
```bash
# 1. Clone the memory plugin
git clone https://github.com/Asher-2000/dsh-memory-connect.git
cd dsh-memory-connect
npm install github:Asher-2000/dsh-memory-connect#v0.4.0 # or place it into the dsh dependency tree manually
# 2. Register it in the host composition (e.g. append to ~/.dsh/profiles/web/cordis.patch.yml):
# - id: cross-session-memory
# name: '@deepseek-ai/dsh-memory-connect'
# config:
# path: ~/.dsh/memory.db
# openAt: startup
# 3. Restart DSH web
dsh web
```
> โ ๏ธ **Important**: **Do NOT** add `@deepseek-ai/dsh-memory-connect` into this preset's `agent.cordis.yml`. It is a HOST-PLANE plugin (injects `sessions` + `systemPrompt`); registering it inside the preset throws `service has been registered at `, which makes the expert-mode preset fail to mount and the UI fall back to the default preset. This preset ships with an explanatory comment about it.
---
## ๐ Quick Start
1. Install the plugin
2. Select "ไธๅฎถๆจกๅผ" preset
3. Ask any question โ the coordinator auto-delegates to the right expert
### Example
```
User: ๅธฎๆ่ฎพ่ฎกไธไธช็จๆท่ฎค่ฏ็ณป็ป
Coordinator:
โ ่ฏๅซ้ขๅ: ๅ็ซฏๅผๅ + ๅฎๅ
จ
โ ๅงๆดพ Backend Dev: API ่ฎพ่ฎกใJWT ๅฎ็ฐ
โ ๅงๆดพ Security: ๅฎๅ
จๅฎก่ฎกใๆผๆด้ฒๆค
โ ๆฑๆป่พๅบๅฎๆดๆนๆก
```
---
## ๐๏ธ Architecture
```
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ Expert Mode Architecture โ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโค
โ โ
โ โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ โ
โ โ Chief Coordinator (ๅ่ฐๅฎ) โ โ
โ โ โข Task analysis โข Domain identification โ โ
โ โ โข Expert routing โข Result aggregation โ โ
โ โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ โ
โ โ โ
โ โโโโโโโโโโโโโโโโโผโโโโโโโโโโโโโโโโ โ
โ โผ โผ โผ โ
โ โโโโโโโโโโโโโโโ โโโโโโโโโโโโโโโ โโโโโโโโโโโโโโโ โ
โ โ Frontend โ โ Backend โ โ DevOps โ โ
โ โ Database โ โ Security โ โ QA โ โ
โ โ Architect โ โ ... โ โ ... โ โ
โ โโโโโโโโโโโโโโโ โโโโโโโโโโโโโโโ โโโโโโโโโโโโโโโ โ
โ โ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
```
---
### ๐ฌ Inter-Expert Communication Bus (v0.8.0)
```
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ File Message Bus (comm/bus.py) โ
โ .expert-mode/comm/mailboxes//*.msg โ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโค
โ โ
โ data-analyst โโsendโโโถ frontend-dev (direct, async) โ
โ copywriter โโsendโโโถ social-media (direct, async) โ
โ coordinator โโbroadcastโโโถ all experts (global sync) โ
โ expert A โโP2P subagentโโโถ expert B (synchronous) โ
โ โ
โ โข Zero relay: content flows between experts, NOT through โ
โ coordinator context โ
โ โข Durable: every message persisted as .msg file โ
โ โข Auditable: full log at comm/logs/bus.log โ
โ โข Commands: send / read / ack / broadcast / stats โ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
```
**Communication Modes**:
| Mode | How | Use case |
|------|-----|----------|
| **A. Relay** | Expert A sends result โ Expert B reads | Sequential collaboration |
| **B. Parallel** | Experts send results to coordinator โ read --all | Independent collection |
| **C. Broadcast** | One message โ all mailboxes | Global state changes |
| **D. Review** | Experts send "agree/partial/disagree + reason" | Cross review |
| **E. P2P** | Expert spawns subagent for direct Q&A | Synchronous clarification |
---
## ๐ Documentation
| Document | Description |
|----------|-------------|
| [Communication Protocol](.expert-mode/comm/PROTOCOL.md) | Inter-expert message bus protocol v1 |
| [Expert Methods](.expert-mode/methods/) | 16 expert methodology docs |
| [Experience Pool](.expert-mode/experts/) | Lessons learned per expert |
| [README.zh.md](README.zh.md) | ไธญๆๆๆกฃ |
---
## ๐ค Contributing
1. Fork the repository
2. Create a feature branch
3. Commit your changes
4. Push to the branch
5. Open a Pull Request
---
## ๐ License
MIT License - see [LICENSE](LICENSE) for details.
---
## ๐ Acknowledgments
- [DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness) - The core framework
- [Cordis](https://github.com/cordiverse/cordis) - Plugin system
- [Awesome DSH Plugin](https://github.com/awesome-dsh-plugin/awesome-dsh-plugin) - Community listing