菜单
Query MedlinePlus for consumer-oriented drug and health-topic information. Accepts drug names, RxCUI codes, NDC codes, or ICD-10-CM diagnosis codes. Uses two free, keyless NLM APIs: the Web Service (keyword search) and MedlinePlus Connect (code-based lookup).
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
Query the DrugComb drug combination database for cancer cell-line synergy and sensitivity data. Use whenever the user asks about drug combinations, synergy scores (ZIP/Bliss/Loewe/HSA), combination sensitivity (CSS), or wants to look up how two drugs interact in a specific cancer cell line.
Query canonical DrugCombDB combination records. Use when the user asks about drug pairs, synergy values, or cell-line-specific combination evidence.
Query or inspect the FDA Orange Book - FDA-Approved Drug Products Listing resource for drug-centric tasks with emphasis on drug knowledgebase Use whenever Codex needs the calling pattern, downloadable entrypoint, or example query flow from this skill example script.
Query the RepurposeDrugs single-agent drug repurposing database. Use whenever the user asks about drug-disease repurposing associations, clinical trial phases for repurposed drugs, or wants to look up any entity (drug name, disease name, NCT ID) in RepurposeDrugs.
Query the Gene-Drug Knowledge Database (GDKD) for variant-specific gene–drug associations in oncology. Use when the user asks about cancer genomic biomarkers, drug sensitivity/resistance by gene or variant, targetable mutations, or clinical evidence for cancer therapeutics.
Query canonical TarKG drug-target triplets. Use when the user asks about drug-target interactions, relation labels, disease/pathway context, or quick lookups for drugs/targets in TarKG.
| name | medlineplus-drug-info |
| description | Query MedlinePlus for consumer-oriented drug and health-topic information. Accepts drug names, RxCUI codes, NDC codes, or ICD-10-CM diagnosis codes. Uses two free, keyless NLM APIs: the Web Service (keyword search) and MedlinePlus Connect (code-based lookup). |
Search MedlinePlus drug / health-topic pages. Auto-detects input type:
| Input Pattern | Detected As | Example | Endpoint Used |
|---|---|---|---|
0069-3060-30 | NDC code | NDC → drug page | Connect (NDC) |
637188 (5-7 digits) | RxCUI | RxNorm concept | Connect (RxCUI) |
E11.9, J45.20 | ICD-10-CM | Diagnosis code → topic | Connect (ICD-10) |
| anything else | free text | metformin, aspirin | Connect (name) + wsearch |
Both APIs are free, require no API key, and are rate-limited to 85 req/min.
| Function | Input | Returns |
|---|---|---|
search(query, max_results=10) | single entity string | dict with connect_results, wsearch_results |
search_batch(queries, max_results=10) | list of entity strings | dict[str, dict] |
summarize(result) | one search() result dict | compact text for LLM |
to_json(result) | one search() result dict | list[dict] flat records |
{
"query": "metformin",
"input_type": "text", # ndc | rxcui | icd10 | text
"connect_results": [ # from MedlinePlus Connect
{"title": "...", "url": "...", "summary": "...", "source": "..."},
],
"wsearch_results": [ # from keyword web service
{"title": "...", "url": "...", "snippet": "...", "rank": "..."},
],
"errors": [],
}
See if __name__ == "__main__" block in 57_MEDLINEPLUS_DRUG_INFO.py for
runnable examples covering: drug name, RxCUI, NDC, ICD-10, batch search,
summarize, and JSON output.
| Field | Source | Description |
|---|---|---|
title | Connect / wsearch | MedlinePlus page title |
url | Connect / wsearch | Direct link to MedlinePlus page |
summary | Connect | HTML-stripped page summary (≤400 chars) |
snippet | wsearch | Keyword-in-context excerpt (≤300 chars) |
source | Connect | Content attribution (e.g., AHFS, ASHP) |
rank | wsearch | Relevance rank returned by NLM |
https://wsearch.nlm.nih.gov/ws/query (XML, keyword search)https://connect.medlineplus.gov/service (JSON, code-based)