pubmed-gene-drug-research
Gene, compound, and variant research using search_gene, search_compound, and search_clinvar. Triggers: 基因, gene, 藥物, drug, compound, PubChem, ClinVar, 變異, variant, 臨床意義
Best use case
pubmed-gene-drug-research is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Gene, compound, and variant research using search_gene, search_compound, and search_clinvar. Triggers: 基因, gene, 藥物, drug, compound, PubChem, ClinVar, 變異, variant, 臨床意義
Teams using pubmed-gene-drug-research should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/pubmed-gene-drug-research/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How pubmed-gene-drug-research Compares
| Feature / Agent | pubmed-gene-drug-research | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Gene, compound, and variant research using search_gene, search_compound, and search_clinvar. Triggers: 基因, gene, 藥物, drug, compound, PubChem, ClinVar, 變異, variant, 臨床意義
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# 基因與藥物研究
## 描述
這個 workflow 用在基因、化合物、藥物與臨床變異查詢。公開 MCP 工具已經收斂成一組新的 NCBI extended 介面:基因用 `search_gene` / `get_gene_details` / `get_gene_literature`,化合物用 `search_compound` / `get_compound_details` / `get_compound_literature`,變異則用 `search_clinvar`。
## 觸發條件
- 「這個基因的功能是什麼?」
- 「這個藥物的結構或機轉?」
- 「這個變異的臨床意義?」
- 提到 BRCA1、TP53、CYP2C9、warfarin、PubChem、ClinVar
---
## 工具對照
| 主題 | 工具 |
|------|------|
| Gene 搜尋 | `search_gene`, `get_gene_details`, `get_gene_literature` |
| Compound 搜尋 | `search_compound`, `get_compound_details`, `get_compound_literature` |
| Variant / ClinVar | `search_clinvar` |
| 後續文獻追蹤 | `fetch_article_details`, `unified_search` |
---
## Gene 工作流
### 1. 搜尋基因
```python
search_gene(query="BRCA1", organism="human")
```
### 2. 取得基因詳情
```python
get_gene_details(gene_id="672")
```
### 3. 取得基因相關文獻
```python
get_gene_literature(gene_id="672", limit=20)
```
### 4. 展開 PubMed 細節
```python
fetch_article_details(pmids="12345678,87654321")
```
> `get_gene_literature` 走的是 NCBI curated gene-to-publication links,通常比單純 keyword 搜尋更準。
---
## Compound / Drug 工作流
### 1. 搜尋化合物
```python
search_compound(query="remimazolam")
```
### 2. 取得化合物詳情
```python
get_compound_details(cid="11526795")
```
### 3. 取得化合物相關文獻
```python
get_compound_literature(cid="11526795", limit=20)
```
### 4. 做更廣泛的機轉或比較搜尋
```python
unified_search(
query="remimazolam mechanism action",
limit=20,
ranking="quality"
)
```
---
## ClinVar / Variant 工作流
### 搜尋變異
```python
search_clinvar(query="BRCA1 pathogenic")
search_clinvar(query="NM_007294.4:c.5266dupC")
search_clinvar(query="CYP2C9 drug response")
```
### 使用方式重點
- 查 gene-level 臨床意義:`search_clinvar(query="BRCA1 pathogenic")`
- 查精確變異:用 HGVS,例如 `NM_007294.4:c.5266dupC`
- 查藥物基因體學:用基因 + phenotype,例如 `CYP2C9 drug response`
> 目前公開介面沒有獨立的 ClinVar detail 工具。要更精準,就把 `search_clinvar` 的查詢寫得更具體。
---
## 常見整合流程
### 情境 1:基因到文獻
```python
search_gene(query="TP53", organism="human")
get_gene_details(gene_id="7157")
get_gene_literature(gene_id="7157", limit=20)
```
### 情境 2:藥物到文獻
```python
search_compound(query="propofol")
get_compound_details(cid="4943")
get_compound_literature(cid="4943", limit=20)
```
### 情境 3:變異到機轉與文獻
```python
search_clinvar(query="BRCA1 pathogenic")
search_gene(query="BRCA1", organism="human")
unified_search(
query="BRCA1 pathogenic variant DNA repair",
limit=20,
ranking="quality"
)
```
### 情境 4:藥物基因組學
```python
search_compound(query="warfarin")
search_gene(query="CYP2C9 warfarin metabolism", organism="human")
search_clinvar(query="CYP2C9 drug response")
unified_search(
query="warfarin CYP2C9 pharmacogenomics",
limit=30,
ranking="quality"
)
```
---
## 實務建議
### Gene
- 優先用官方 symbol,例如 `TP53`,不要先用模糊別名
- 常常要補 `organism="human"`,避免混到小鼠或其他物種
### Compound
- 優先用 generic name,不要先用商品名
- 一旦拿到 CID,後續都用 CID 最穩定
### ClinVar
- 最精確的是 HGVS 命名
- 次佳是 `gene + pathogenic` 或 `gene + condition`
---
## 最後原則
新的公開工具名應統一為:
- `search_gene`
- `get_gene_details`
- `get_gene_literature`
- `search_compound`
- `get_compound_details`
- `get_compound_literature`
- `search_clinvar`Related Skills
pubmed-search-mcp-harness
Cline harness for PubMed Search MCP. Triggers: pubmed search, literature search, unified_search, pipeline, fulltext, release checklist, Cline.
test-generator
Generate comprehensive test suites including static analysis, unit tests, integration tests, E2E tests, and coverage reports. Triggers: TG, test, 測試, 寫測試, coverage, 覆蓋率, pytest, unittest, 驗證.
pubmed-systematic-search
Comprehensive search using generate_search_queries and unified_search. Triggers: 系統性搜尋, 完整搜尋, 文獻回顧, systematic search, comprehensive, MeSH expansion, 同義詞
pubmed-quick-search
Quick literature search using unified_search. Triggers: 搜尋, 找論文, search papers, find articles, PubMed, 文獻搜尋, 快速搜尋
pubmed-pico-search
Agent-guided PICO clinical question search using parse_pico handoff and unified_search. Triggers: PICO, 臨床問題, A比B好嗎, treatment comparison, clinical question, 療效比較
pubmed-paper-exploration
Deep exploration from a key paper using related, citing, reference, and citation tree tools. Triggers: 這篇論文的相關研究, 誰引用這篇, 類似文章, related articles, citation tree, paper exploration
pubmed-multi-source-search
Cross-database search using unified_search across academic sources. Triggers: 跨資料庫, multi-source, Semantic Scholar, OpenAlex, CORE, Europe PMC, 綜合搜尋
pubmed-mcp-tools-reference
Complete reference for all 46 PubMed Search MCP tools. Triggers: 工具列表, all tools, 完整功能, tool reference, 有哪些工具
pubmed-fulltext-access
Full text access using get_fulltext, figure extraction, and institutional link tools. Triggers: 全文, fulltext, PDF, open access, 免費下載, PMC, 開放取用
academic-figure-drawing-harness
Codex drawing harness integration. Triggers: 繪圖, draw, figure, chart, plot, mermaid, SVG, Gemini, graph, 生成圖表.
zotero-keeper-harness
Cline harness for Zotero Keeper and the bundled VS Code extension. Triggers: zotero keeper, zotero mcp, full check, release checklist, workflow, vsix, Cline.
llm-wiki-builder
Build or refresh Foam-compatible LLM wikis from Zotero, PubMed, documents, and local Markdown notes using a multi-tool workflow.