DSH Expert Mode

🧠 DSH Expert Mode

One agent preset that turns DSH into a "1 Coordinator + 11 Experts" multi-agent team

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

δΈ­ζ–‡ Β· English

--- ## ✨ What it does Install this preset and DSH automatically becomes a "Chief Coordinator" mode: | Scenario | Behavior | |----------|----------| | Receives task | Identifies domain β†’ delegates to the best expert | | Complex tasks | Dispatches multiple experts in parallel | | Simple tasks | Coordinator handles directly β€” 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.** --- ## πŸ–ΌοΈ 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

--- ## 🧩 11 Experts | Expert | Tool | Domain | |--------|------|--------| | πŸ“Š Data Analyst | `expert_data_analyst` | Data cleaning, statistics, visualization | | ✍️ Copywriter | `expert_copywriter` | Marketing copy, content creation, rewriting | | βš–οΈ Legal Review | `expert_legal_review` | Contract review, legal risk assessment | | πŸ“‹ Product Manager | `expert_product_manager` | Requirements analysis, PRD writing, competitor research | | πŸ–₯️ Frontend Dev | `expert_frontend_dev` | Web frontend implementation, component development | | 🎨 UI/UX Design | `expert_uiux_design` | Interface design, interaction patterns, design systems | | πŸ—οΈ Architect | `expert_architect` | System design, tech selection, architecture review | | πŸ“± Social Media | `expert_social_media` | Multi-platform content distribution, account management | | πŸš€ Growth Hacker | `expert_growth` | Growth strategy, conversion funnels, A/B testing | | πŸ’Ή Quant Finance | `expert_quant_finance` | Quantitative models, financial analysis, risk control | | πŸ’° Finance | `expert_finance` | Financial analysis, report interpretation, budget planning | --- ## πŸ”§ Core Mechanisms ### πŸš€ Quick Path The Coordinator **answers directly** without delegating for: - Single file read/write/edit - Simple Q&A (no domain expertise needed) - Casual chat / greetings - User says "do it yourself" or "no delegation needed" - Task completable with a single command ### ⚑ Fault Recovery - Expert call timeout/failure β†’ **auto-retry once** - 2 consecutive failures β†’ inform user, suggest alternative - Expert output clearly off-topic β†’ **recall and re-guide** ### πŸ“‹ Progressive Disclosure The Coordinator holds a complete expert methodology index and **injects on-demand** β€” not dumping all expert personas into context at startup. | Metric | Before | After | Improvement | |--------|--------|-------|-------------| | Expert persona tokens | 3850 chars | 533 chars | **-86%** | | Total prompt tokens | ~2205 | ~1582 | **-28%** | ### 🎯 Anchored Non-degradation Solves the "trajectory flip" problem caused by system prompt mutations: | Anchor | Purpose | |--------|---------| | **Style Lock** | Maintain default reasoning style regardless of context changes | | **Evidence Priority** | Every conclusion backed by data/logic | | **Step-by-step** | Complex tasks decomposed into single steps | | **Consistency Check** | Verify reasoning style matches previous turn | | **Anti-drift** | Proactively save state before context window fills | ### πŸ—οΈ Five Anchor Constraints The Coordinator self-checks five anchor points every turn: | Anchor | Purpose | |--------|---------| | **Review** | One-sentence recap of current subtask | | **Convergence** | Confirm this step advanced the goal | | **Anti-drift** | 2 turns with no progress β†’ force strategy switch | | **Collaboration Check** | Before delegation, verify routing is correct | | **Resource Awareness** | Monitor token usage; auto-simplify if >70% | ### 🎯 Near-distance Guidance During delegation, the Coordinator fills in the structured guidance template: ``` β”Œβ”€ Near-distance Guidance ─┐ Identity: You are [expert role] Task: {specific task description} Input: {input data} Output format: [extracted from methodology index] Completion criteria: {clear delivery standard} β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ ``` Subagents start with clear "who I am, what to do, how to deliver." ### πŸ”— Expert Communication Protocol When cross-expert collaboration is needed: ``` [FROM:expert_data_analyst β†’ TO:expert_frontend_dev] Task: Design frontend data display based on analysis Data: {Expert A's conclusion summary} ``` ### πŸ” Cross Review High-risk tasks (architecture selection, contract review, financial analysis) trigger multi-expert independent review. The Coordinator synthesizes conclusions. ### πŸ’Ύ Experience Pool After completing important tasks, experts extract lessons to `.expert-mode/experts/{name}/lessons.md`, automatically injected for similar future tasks. ### 🧠 Expert Persistence Experts stay online after task completion. The Coordinator can wake them up for follow-up modifications with full context preserved. --- ## πŸ“¦ Installation ### Method 1: dsh plugin add (recommended) ```bash dsh plugin --profile web add github:Asher-2000/dsh-expert-mode ``` ### Method 2: git clone ```bash mkdir -p ~/.dsh/.agent-presets git clone https://github.com/Asher-2000/dsh-expert-mode.git ~/.dsh/.agent-presets/expert-mode ``` **Want English?** The repo includes an `expert-mode-en/` preset: ```bash cp -r ~/.dsh/.agent-presets/expert-mode/expert-mode-en ~/.dsh/.agent-presets/expert-mode-en ``` ### Method 3: Manual download Download from [Releases](https://github.com/Asher-2000/dsh-expert-mode/releases) and place `preset.yml` + `agent.cordis.yml` into `~/.dsh/.agent-presets/expert-mode/`. --- ## πŸš€ Usage After installation, select the Expert Mode preset when creating a new session in DSH Web GUI. --- ## ❓ FAQ **Q: Does Expert Mode consume extra model quota?** A: Delegating to expert subagents triggers subagent model calls (DSH subagent mechanism), same as the official subagent feature. Simple tasks are handled directly by the Coordinator with no extra calls. **Q: Can I add my own experts?** A: Yes. Copy any expert entry in `agent.cordis.yml`, modify the tool name and persona. **Q: How does it relate to the official standard preset?** A: Built on top of the official standard preset combination, preserving the full toolset and only adding the expert delegation layer. --- ## πŸ“ File Structure ``` . β”œβ”€β”€ preset.yml # Preset metadata (name + description) β”œβ”€β”€ agent.cordis.yml # Coordinator persona + methodology index + expert tools β”œβ”€β”€ expert-mode-en/ # English preset β”‚ β”œβ”€β”€ preset.yml β”‚ └── agent.cordis.yml β”œβ”€β”€ .expert-mode/ # Expert experience pool β”‚ └── experts/ # Each expert's lessons.md β”œβ”€β”€ assets/ # Screenshots β”œβ”€β”€ README.md # English β”œβ”€β”€ README.zh.md # δΈ­ζ–‡ └── LICENSE ``` --- ## πŸ“ Changelog | Version | Changes | |---------|---------| | **v0.6.0** | Quick Path + Fault Recovery + bilingual parity | | **v0.5.0** | Progressive disclosure + anchored non-degradation (tokens -28%) | | **v0.4.0** | Five anchors + near-distance guidance + cross review + experience pool | | **v0.3.0** | Expert persistence + communication protocol | | **v0.2.0** | Basic multi-expert delegation | --- ## πŸ† Community - πŸ“’ Featured in **Awesome DSH Plugin**: https://github.com/awesome-dsh-plugin/awesome-dsh-plugin - 🏷️ GitHub `dsh-plugin` topic: https://github.com/topics/dsh-plugin --- ## 🏷️ Tags `dsh` `deepseek-harness` `agent-preset` `expert-mode` `multi-agent` `subagent` `ai-agent` `dsh-plugin` --- ## πŸ“„ License MIT License β€” see [LICENSE](LICENSE).