Medlineplus

Skill BioTender-max/awesome-bio-agent-skills/skills/drugclaw/medlineplus

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).From its SKILL.md

Install

npx -y skills add BioTender-max/awesome-bio-agent-skills --skill medlineplus

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.

SKILL.md

2.7 KB, 714 tokens by cl100k_base, as published. Nobody here has run it

MedlinePlus Drug Info Skill

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.

API

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

Result dict structure

{
    "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": [],
}

Usage

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.

Key Fields

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

Data Source

Provider: U.S. National Library of Medicine (NLM)
Web Service: https://wsearch.nlm.nih.gov/ws/query (XML, keyword search)
Connect API: https://connect.medlineplus.gov/service (JSON, code-based)
Rate limit: 85 requests / minute / IP
Update frequency: daily (Tue–Sat)
License: Public domain (U.S. Government work); attribution to MedlinePlus.gov requested

What ships with it: 5 files

23.7 KB alongside SKILL.md, 4 of them executable

example.pyruns10.9 KB
__init__.pyruns150 B
medlineplus_skill.pyruns10.9 KB
README.md1016 B
retrieve.pyruns807 B