Back to Details

doctorg

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Doctor G -- Evidence-Based Health Research

Doctor G -- 循证健康研究

Answer health and wellness questions using only trusted, evidence-based sources with explicit evidence strength ratings.
仅使用可信的循证来源并附带明确的证据强度评级来解答健康与养生相关问题。

Usage

使用方法

bash
undefined
bash
undefined

Quick answer (WebSearch only, ~30s)

快速回答（仅WebSearch，约30秒）

/doctorg Is creatine safe for daily use?
/doctorg 肌酸日常服用安全吗？

Deep research (WebSearch + Tavily, ~90s)

深度研究（WebSearch + Tavily，约90秒）

/doctorg --deep Huberman vs Attia on fasted training
/doctorg --deep Huberman与Attia关于空腹训练的观点对比

Full investigation (WebSearch + Tavily + Firecrawl, ~3min)

全面调查（WebSearch + Tavily + Firecrawl，约3分钟）

/doctorg --full What does current evidence say about GLP-1 agonists for non-diabetic weight loss?
/doctorg --full 当前关于GLP-1激动剂用于非糖尿病患者减重的证据有哪些？

Without personal health context

不使用个人健康场景

/doctorg --no-personal Best stretching protocol for lower back pain
undefined
/doctorg --no-personal 针对下背痛的最佳拉伸方案
undefined

Depth Levels

研究深度等级

LevelFlagToolsTimeUse When
Quick(default)WebSearch~30sSimple factual questions
Deep
--deep
WebSearch + Tavily~90sCompeting claims, nuanced topics
Full
--full
WebSearch + Tavily + Firecrawl~3minControversial topics, need primary sources
等级参数标识使用工具耗时适用场景
快速（默认）WebSearch~30秒简单事实类问题
深度
--deep
WebSearch + Tavily~90秒存在争议的观点、复杂主题
全面
--full
WebSearch + Tavily + Firecrawl~3分钟极具争议的主题、需要原始来源的问题

How It Works

工作原理

1. Parse Query & Detect Topic Category

1. 解析查询并检测主题分类

Classify the question into one of:
  • Nutrition/Supplements (examine.com gets priority)
  • Exercise/Training (PubMed + ACSM get priority)
  • Sleep (focus sleep-specific databases)
  • Disease/Condition (condition-specific orgs + clinical guidelines)
  • Medication/Treatment (FDA, EMA, Cochrane get priority)
  • Mental Health (APA, mental health orgs)
  • General Wellness (broad search across all tiers)
将问题归类为以下类别之一：
  • 营养/补充剂（优先使用examine.com）
  • 运动/训练（优先使用PubMed + ACSM）
  • 睡眠（聚焦睡眠专用数据库）
  • 疾病/症状（特定疾病组织 + 临床指南）
  • 药物/治疗（优先使用FDA、EMA、Cochrane）
  • 心理健康（APA、心理健康组织）
  • 通用养生（跨所有层级的广泛搜索）

2. Search Evidence Sources (Tiered)

2. 分层搜索证据来源

Search sources in priority order. See 
references/sources.md
for complete domain list.
Tier 1 -- Primary Research (highest weight):
  • PubMed/PMC, Cochrane Library, WHO, ClinicalTrials.gov
Tier 2 -- Clinical/Institutional (high weight):
  • Mayo Clinic, Hopkins Medicine, Cleveland Clinic, Harvard Health
  • Condition-specific: AHA, ACS, ADA, Alzheimer's Association
Tier 3 -- Expert Analysis (medium weight):
  • Examine.com, STAT News, Health News Review
  • Consensus.app, Epistemonikos
Tier 4 -- Quality Journalism (context/framing):
  • The Atlantic, NYT, NPR, Guardian, FiveThirtyEight
按优先级顺序搜索来源。完整域名列表请参阅
references/sources.md
。
第一层 -- 原始研究（权重最高）：
  • PubMed/PMC、Cochrane Library、WHO、ClinicalTrials.gov
第二层 -- 临床/机构来源（权重高）：
  • Mayo Clinic、Hopkins Medicine、Cleveland Clinic、Harvard Health
  • 特定疾病机构：AHA、ACS、ADA、阿尔茨海默病协会
第三层 -- 专家分析（权重中等）：
  • Examine.com、STAT News、Health News Review
  • Consensus.app、Epistemonikos
第四层 -- 优质新闻报道（提供背景/框架）：
  • The Atlantic、NYT、NPR、Guardian、FiveThirtyEight

Search Strategy by Depth

按深度划分的搜索策略

Quick (default):
WebSearch(query, allowed_domains=[Tier 1 + Tier 2 domains])
WebSearch(query + "systematic review OR meta-analysis", allowed_domains=[Tier 1])
Deep (--deep): All Quick searches PLUS:
tavily-search(query, include_domains=[Tier 1-3])
WebSearch(query + "expert opinion OR position statement", allowed_domains=[Tier 2-3])
WebSearch(query + "risks OR side effects OR contraindications")
Full (--full): All Deep searches PLUS:
firecrawl-research for top 2-3 most relevant results from Tier 1
WebSearch for competing/contrarian viewpoints
WebSearch(query + "retracted OR debunked OR misleading")
快速（默认）：
WebSearch(query, allowed_domains=[第一层 + 第二层域名])
WebSearch(query + "systematic review OR meta-analysis", allowed_domains=[第一层])
深度（--deep）： 包含所有快速搜索，再加上：
tavily-search(query, include_domains=[第一层-第三层])
WebSearch(query + "expert opinion OR position statement", allowed_domains=[第二层-第三层])
WebSearch(query + "risks OR side effects OR contraindications")
全面（--full）： 包含所有深度搜索，再加上：
对第一层中最相关的2-3个结果进行firecrawl-research
搜索对立/相反观点
WebSearch(query + "retracted OR debunked OR misleading")

3. Pull Personal Health Context (unless --no-personal)

3. 获取个人健康场景（除非使用--no-personal）

Query Apple Health database for relevant metrics:
bash
python ~/ai_projects/claude-skills/health-data/scripts/health_query.py --format json vitals
python ~/ai_projects/claude-skills/health-data/scripts/health_query.py --format json daily
python ~/ai_projects/claude-skills/health-data/scripts/health_query.py --format json sleep --days 7
python ~/ai_projects/claude-skills/health-data/scripts/health_query.py --format json workouts --days 30
Select ONLY metrics relevant to the query:
  • Exercise question -> recent workouts, activity, resting HR, VO2 max
  • Sleep question -> sleep data, HRV
  • Nutrition question -> weight trends, activity level
  • Heart question -> HR, HRV, resting HR, blood pressure
查询Apple Health数据库获取相关指标：
bash
python ~/ai_projects/claude-skills/health-data/scripts/health_query.py --format json vitals
python ~/ai_projects/claude-skills/health-data/scripts/health_query.py --format json daily
python ~/ai_projects/claude-skills/health-data/scripts/health_query.py --format json sleep --days 7
python ~/ai_projects/claude-skills/health-data/scripts/health_query.py --format json workouts --days 30
仅选择与查询相关的指标：
  • 运动相关问题 -> 近期运动记录、活动量、静息心率、最大摄氧量（VO2 max）
  • 睡眠相关问题 -> 睡眠数据、心率变异性（HRV）
  • 营养相关问题 -> 体重变化趋势、活动水平
  • 心脏相关问题 -> 心率、心率变异性、静息心率、血压

4. Synthesize with Evidence Grading

4. 结合证据评级进行综合分析

Rate each claim using simplified GRADE scale:
RatingMeaningBased On
StrongConsistent evidence from systematic reviews/meta-analyses or multiple large RCTsLevel I-II evidence
ModerateSupported by well-designed studies but some inconsistency or limitationsLevel II-III evidence
WeakLimited evidence, small studies, or conflicting resultsLevel III-IV evidence
MinimalExpert opinion, case reports, or preliminary/animal studies onlyLevel V evidence
ContestedActive scientific debate with credible evidence on both sidesMixed levels
使用简化版GRADE量表对每个主张进行评级：
评级含义依据
Strong（强）来自系统综述/荟萃分析或多项大型随机对照试验（RCT）的一致证据I-II级证据
Moderate（中）有设计良好的研究支持，但存在一些不一致性或局限性II-III级证据
Weak（弱）证据有限、研究规模小或结果存在冲突III-IV级证据
Minimal（极少）仅基于专家意见、病例报告或初步/动物研究V级证据
Contested（有争议）存在活跃的科学争论，双方均有可信证据混合等级证据

5. Format Output

5. 输出格式

markdown
undefined
markdown
undefined

[Topic Title]

[主题标题]

Short answer: [1-2 sentence direct answer]
简短回答：[1-2句话的直接答复]

[Expert/Position A] (if comparing viewpoints)

[专家/观点A]（若对比观点）

  • Key claim 1
  • Key claim 2
  • Has evolved stance: [if applicable]
  • 核心主张1
  • 核心主张2
  • 立场演变：（如适用）

[Expert/Position B]

[专家/观点B]

  • Key claim 1
  • Key claim 2
  • 核心主张1
  • 核心主张2

Where They Actually Agree (if comparing)

双方共识点（若对比）

  • Agreement point 1
  • Agreement point 2
  • 共识点1
  • 共识点2

What Research Shows

研究结论

ClaimEvidence Strength
Claim 1Strong
Claim 2Weak (reason)
Claim 3Contested
主张证据强度
主张1Strong（强）
主张2Weak（弱）（原因）
主张3Contested（有争议）

For You Specifically (if --personal context available)

针对您的个性化建议（若有--personal场景数据）

[Personalized interpretation based on user's health data]
[Specific actionable recommendation]
[基于用户健康数据的个性化解读]
[具体可执行建议]

Sources

参考来源

  • Source 1 title -- Tier, year
  • Source 2 title -- Tier, year
  • 来源1标题 -- 层级，年份
  • 来源2标题 -- 层级，年份

Limitations

局限性

  • [Any caveats about the evidence or this analysis]

**Output rules**:
- NEVER give medical diagnoses or replace professional advice
- ALWAYS include disclaimer: "This is research synthesis, not medical advice"
- When evidence is **Weak** or **Minimal**, explicitly say so
- When claims are **Contested**, present both sides fairly
- Prefer recent sources (last 5 years) over older ones
- Flag if key studies have been retracted or challenged
- Include the "For You Specifically" section only when health data adds meaningful context
  • [关于证据或本次分析的注意事项]

**输出规则**：
- 绝不提供医疗诊断或替代专业医疗建议
- 必须包含免责声明："本内容为研究综合分析，非医疗建议"
- 当证据为**Weak（弱）**或**Minimal（极少）**时，需明确说明
- 当主张存在**Contested（有争议）**时，需公平呈现双方观点
- 优先使用近5年的来源而非旧来源
- 若关键研究已被撤回或受到质疑，需标注
- 仅当健康数据能提供有意义的场景时，才包含"针对您的个性化建议"部分

6. Disclaimer (always append)

6. 免责声明（始终附加）

---
*Research synthesis, not medical advice. Consult a healthcare provider for personal decisions.*
---
*本内容为研究综合分析，非医疗建议。请咨询医疗保健专业人员以获取个人决策建议。*

Examples

示例

Quick

快速查询

/doctorg Is 10000 steps a day backed by science?
/doctorg 每天走10000步有科学依据吗？

Deep (comparing experts)

深度对比（专家观点）

/doctorg --deep Huberman vs Attia on fasted training
/doctorg --deep Huberman与Attia关于空腹训练的观点对比

Full (controversial topic)

全面调查（争议性主题）

/doctorg --full Safety profile of long-term melatonin supplementation
/doctorg --full 长期服用褪黑素的安全性概况

Integration with Other Skills

与其他技能的集成

  • health-data: Pulls Apple Health metrics for personalization
  • tavily-search: Deep research at Tier 1-3 sources
  • firecrawl-research: Full-text extraction from primary sources
  • fact-checker: Can be chained for verification of specific claims
  • health-data：获取Apple Health指标以实现个性化
  • tavily-search：针对1-3层级来源进行深度研究
  • firecrawl-research：从原始来源提取全文
  • fact-checker：可链式调用以验证特定主张