brycewang-stanford
brycewang-stanford/Auto-Empirical-Research-Skills
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。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills --skill clinical-dialogue-agents-guide命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Route empirical-research requests through the Auto-Empirical Research Skills catalog when this whole repository is installed as one skill in Codex, CodeBuddy, Claude Code, or another IDE. Use to choose and load the right vendored AERS skill for causal inference, econometrics, replication, data acquisition, manuscript writing, peer review and referee responses, citation checking, de-AIGC editing, or full empirical-paper workflows without reading the entire repository at once.
中英双语学术降 AIGC / bilingual academic de-AIGC skill. Removes AI-generated writing signatures from empirical papers in economics, management, and the social sciences — in both English and Chinese. Covers Turnitin AI, GPTZero, Originality.ai on the English side and 知网 AMLC, 万方, 维普 on the Chinese side. Uses a six-step loop (intake → audit → claim-evidence check → differentiated rewrite → five-dimension self-score → cold-reader recheck) with two pattern libraries (22 English + 17 Chinese patterns), section-by-section strategies for empirical papers, and hard protections that keep every number, coefficient, and citation intact.
Use when a research task needs reproducible Kaggle discovery, metadata inspection, bounded public-data downloads, competition or kernel discovery, model discovery, or an explicitly approved Kaggle write/delete operation through the official CLI.
基于 SOC 职业分类
正在显示 SKILL.md
| name | clinical-dialogue-agents-guide |
| description | Papers on AI agents for clinical dialogue and medical QA |
| metadata | {"openclaw":{"emoji":"🗣️","category":"domains","subcategory":"biomedical","keywords":["clinical dialogue","medical QA","patient interaction","clinical agents","healthcare AI","diagnosis"],"source":"https://github.com/xqz614/Awesome-Agentic-Clinical-Dialogue"}} |
A curated collection of papers on AI agents for clinical dialogue — systems that conduct patient interviews, perform differential diagnosis, explain medical information, and support clinical decision-making through conversation. Covers medical QA benchmarks, patient simulation, clinical reasoning chains, and safety considerations unique to healthcare AI.
Agentic Clinical Dialogue
├── Patient-Facing Agents
│ ├── Symptom checkers
│ ├── Triage systems
│ ├── Health information
│ └── Follow-up management
├── Clinician-Facing Agents
│ ├── Diagnostic support
│ ├── Treatment recommendation
│ ├── Clinical documentation
│ └── Literature integration
├── Clinical Reasoning
│ ├── Differential diagnosis
│ ├── History taking
│ ├── Physical exam interpretation
│ └── Test ordering
├── Patient Simulation
│ ├── Standardized patients (SP)
│ ├── Medical education
│ └── Agent evaluation
└── Safety & Ethics
├── Hallucination in medicine
├── Bias in clinical AI
├── Liability frameworks
└── Informed consent
| System | Focus | Approach |
|---|---|---|
| AMIE | Diagnostic dialogue | LLM with clinical reasoning |
| Med-PaLM | Medical QA | Finetuned on medical data |
| ChatDoctor | Patient consultation | LLaMA + medical knowledge |
| AgentClinic | Clinical evaluation | Simulated clinical encounters |
| ClinicalAgent | Decision support | Multi-step clinical reasoning |
benchmarks = {
"MedQA (USMLE)": {
"task": "US Medical Licensing Exam questions",
"size": "11,450 questions",
"metric": "Accuracy",
},
"PubMedQA": {
"task": "Biomedical yes/no/maybe QA",
"size": "1,000 expert-labeled",
"metric": "Accuracy",
},
"AgentClinic": {
"task": "Simulated clinical encounters",
"size": "Various patient scenarios",
"metric": "Diagnostic accuracy + safety",
},
"MedMCQA": {
"task": "Indian medical entrance MCQs",
"size": "194k questions",
"metric": "Accuracy",
},
"HealthSearchQA": {
"task": "Consumer health search questions",
"size": "3,375 questions",
"metric": "Expert evaluation",
},
}
for name, info in benchmarks.items():
print(f"\n{name}:")
print(f" Task: {info['task']}")
print(f" Size: {info['size']}")
### Critical Safety Issues
1. **Hallucination** — Fabricated medical facts are dangerous
2. **Scope limitations** — AI must know when to defer to human
3. **Emergency recognition** — Must identify urgent situations
4. **Bias** — Demographic biases in training data
5. **Liability** — Legal framework for AI medical advice
6. **Privacy** — Patient data protection (HIPAA compliance)
### Safety Patterns
- Always recommend consulting healthcare providers
- Flag emergency symptoms immediately
- Disclose AI nature to patients
- Log all interactions for audit
- Implement uncertainty quantification
### Foundations
1. AMIE: "Towards Conversational Diagnostic AI" (Google, 2024)
2. Med-PaLM 2: "Expert-level medical QA" (Google, 2023)
3. "Evaluating LLMs in Clinical Dialogue" (Survey, 2024)
### Clinical Reasoning
4. "Chain-of-Diagnosis" (Clinical CoT, 2024)
5. "AgentClinic: Evaluating Clinical Agents" (2024)
6. "Simulated Patient Encounters with LLMs" (2024)
### Safety
7. "Hallucination in Medical AI" (Survey, 2024)
8. "Red Teaming Medical LLMs" (2024)