medlineplus

Name: medlineplus
Author: QSong-github

132stars4forks

How to install medlineplus?

qsong-github/drugclaw/medlineplus

$npx -y skills add QSong-github/DrugClaw --skill medlineplus

Installs into the current project.

Summary

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).

Files · 1

View on GitHub

SKILL.md

1	# MedlinePlus Drug Info Skill
2
3	Search MedlinePlus drug / health-topic pages. Auto-detects input type:
4
5	\| Input Pattern \| Detected As \| Example \| Endpoint Used \|
6	\|---\|---\|---\|---\|
7	\| `0069-3060-30` \| NDC code \| NDC → drug page \| Connect (NDC) \|
8	\| `637188` (5-7 digits) \| RxCUI \| RxNorm concept \| Connect (RxCUI) \|
9	\| `E11.9`, `J45.20` \| ICD-10-CM \| Diagnosis code → topic \| Connect (ICD-10) \|
10	\| anything else \| free text \| `metformin`, `aspirin` \| Connect (name) + wsearch \|
11
12	Both APIs are free, require no API key, and are rate-limited to 85 req/min.
13
14	## API
15
16	\| Function \| Input \| Returns \|
17	\|---\|---\|---\|
18	\| `search(query, max_results=10)` \| single entity string \| `dict` with `connect_results`, `wsearch_results` \|
19	\| `search_batch(queries, max_results=10)` \| list of entity strings \| `dict[str, dict]` \|
20	\| `summarize(result)` \| one `search()` result dict \| compact text for LLM \|
21	\| `to_json(result)` \| one `search()` result dict \| `list[dict]` flat records \|
22
23	### Result dict structure
24
25	```python
26	{
27	"query": "metformin",
28	"input_type": "text", # ndc \| rxcui \| icd10 \| text
29	"connect_results": [ # from MedlinePlus Connect
30	{"title": "...", "url": "...", "summary": "...", "source": "..."},
31	],
32	"wsearch_results": [ # from keyword web service
33	{"title": "...", "url": "...", "snippet": "...", "rank": "..."},
34	],
35	"errors": [],
36	}
37	```
38
39	## Usage
40
41	See `if __name__ == "__main__"` block in `57_MEDLINEPLUS_DRUG_INFO.py` for
42	runnable examples covering: drug name, RxCUI, NDC, ICD-10, batch search,
43	summarize, and JSON output.
44
45	## Key Fields
46
47	\| Field \| Source \| Description \|
48	\|---\|---\|---\|
49	\| `title` \| Connect / wsearch \| MedlinePlus page title \|
50	\| `url` \| Connect / wsearch \| Direct link to MedlinePlus page \|
51	\| `summary` \| Connect \| HTML-stripped page summary (≤400 chars) \|
52	\| `snippet` \| wsearch \| Keyword-in-context excerpt (≤300 chars) \|
53	\| `source` \| Connect \| Content attribution (e.g., AHFS, ASHP) \|
54	\| `rank` \| wsearch \| Relevance rank returned by NLM \|
55
56	## Data Source
57
58	- Provider: U.S. National Library of Medicine (NLM)
59	- Web Service: `https://wsearch.nlm.nih.gov/ws/query` (XML, keyword search)
60	- Connect API: `https://connect.medlineplus.gov/service` (JSON, code-based)
61	- Rate limit: 85 requests / minute / IP
62	- Update frequency: daily (Tue–Sat)
63	- License: Public domain (U.S. Government work); attribution to MedlinePlus.gov requested

People who liked this also viewed

6 picks

Type

medlineplus

132stars4forks

View on GitHub

How to install medlineplus?

qsong-github/drugclaw/medlineplus

$npx -y skills add QSong-github/DrugClaw --skill medlineplus

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# MedlinePlus Drug Info Skill
2
3	Search MedlinePlus drug / health-topic pages. Auto-detects input type:
4
5	\| Input Pattern \| Detected As \| Example \| Endpoint Used \|
6	\|---\|---\|---\|---\|
7	\| `0069-3060-30` \| NDC code \| NDC → drug page \| Connect (NDC) \|
8	\| `637188` (5-7 digits) \| RxCUI \| RxNorm concept \| Connect (RxCUI) \|
9	\| `E11.9`, `J45.20` \| ICD-10-CM \| Diagnosis code → topic \| Connect (ICD-10) \|
10	\| anything else \| free text \| `metformin`, `aspirin` \| Connect (name) + wsearch \|
11
12	Both APIs are free, require no API key, and are rate-limited to 85 req/min.
13
14	## API
15
16	\| Function \| Input \| Returns \|
17	\|---\|---\|---\|
18	\| `search(query, max_results=10)` \| single entity string \| `dict` with `connect_results`, `wsearch_results` \|
19	\| `search_batch(queries, max_results=10)` \| list of entity strings \| `dict[str, dict]` \|
20	\| `summarize(result)` \| one `search()` result dict \| compact text for LLM \|
21	\| `to_json(result)` \| one `search()` result dict \| `list[dict]` flat records \|
22
23	### Result dict structure
24
25	```python
26	{
27	"query": "metformin",
28	"input_type": "text", # ndc \| rxcui \| icd10 \| text
29	"connect_results": [ # from MedlinePlus Connect
30	{"title": "...", "url": "...", "summary": "...", "source": "..."},
31	],
32	"wsearch_results": [ # from keyword web service
33	{"title": "...", "url": "...", "snippet": "...", "rank": "..."},
34	],
35	"errors": [],
36	}
37	```
38
39	## Usage
40
41	See `if __name__ == "__main__"` block in `57_MEDLINEPLUS_DRUG_INFO.py` for
42	runnable examples covering: drug name, RxCUI, NDC, ICD-10, batch search,
43	summarize, and JSON output.
44
45	## Key Fields
46
47	\| Field \| Source \| Description \|
48	\|---\|---\|---\|
49	\| `title` \| Connect / wsearch \| MedlinePlus page title \|
50	\| `url` \| Connect / wsearch \| Direct link to MedlinePlus page \|
51	\| `summary` \| Connect \| HTML-stripped page summary (≤400 chars) \|
52	\| `snippet` \| wsearch \| Keyword-in-context excerpt (≤300 chars) \|
53	\| `source` \| Connect \| Content attribution (e.g., AHFS, ASHP) \|
54	\| `rank` \| wsearch \| Relevance rank returned by NLM \|
55
56	## Data Source
57
58	- Provider: U.S. National Library of Medicine (NLM)
59	- Web Service: `https://wsearch.nlm.nih.gov/ws/query` (XML, keyword search)
60	- Connect API: `https://connect.medlineplus.gov/service` (JSON, code-based)
61	- Rate limit: 85 requests / minute / IP
62	- Update frequency: daily (Tue–Sat)
63	- License: Public domain (U.S. Government work); attribution to MedlinePlus.gov requested

People who liked this also viewed

6 picks

Type