一键导入
staff-architect
Architecture guidance for AI Doctor Assistant
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Architecture guidance for AI Doctor Assistant
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Generate a structured pre-consultation patient briefing. Use when the physician asks for a briefing, a pre-consultation summary, or sends /briefing.
Search the live web or read a specific web page for recency-sensitive clinical information — drug recalls, newly published guidance, FDA/EMA safety communications — that the local clinical guidelines corpus does not cover. Use when the physician asks to "search the web", "look up the latest", or asks about something the guidelines search returned no results for.
Claude Agent SDK patterns and best practices
Code review and refactoring guidelines
FastAPI backend patterns for AI Doctor Assistant
React frontend development patterns for AI Doctor Assistant
| name | staff-architect |
| description | Architecture guidance for AI Doctor Assistant |
┌─────────────────────────────────────────────────┐
│ Two-Step Briefing Flow │
├─────────────────────────────────────────────────┤
│ │
│ STEP 1: Deterministic Rules (Python) │
│ - FlagAnalyzer.apply_rules(patient) │
│ - Returns: List[Flag] (100% deterministic) │
│ - Source: "rule" │
│ │
│ STEP 2: AI Synthesis (Claude Agent SDK) │
│ - BriefingAgent.generate(patient, rule_flags) │
│ - Returns: PatientBriefing (Pydantic validated)│
│ - AI insights: source="ai" │
│ │
└─────────────────────────────────────────────────┘
| Benefit | Explanation |
|---|---|
| Auditability | Can prove which flags came from rules vs AI |
| Testability | Unit test rules separately, mock agent for integration |
| Reliability | Rules are 100% deterministic (critical for healthcare) |
| Traceability | Clear separation: source: "rule" vs source: "ai" |
Frontend → API → Service → Agent → Tools
↓
Rule Engine
/api/v1/...Keep services loosely coupled
Prefer explicit over implicit
Don't over-engineer
Healthcare Context