openfda

Name: openfda
Author: QSong-github

132stars4forks

How to install openfda?

qsong-github/drugclaw/openfda

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

Installs into the current project.

Summary

Query FDA drug labeling data via openFDA. Use whenever the user asks about drug prescribing information — indications, warnings, dosage, adverse reactions, contraindications, or administration routes. Supports single or batch lookup by brand/generic name or by indication/conditio

Files · 1

View on GitHub

SKILL.md

1	# openFDA Human Drug Skill
2
3	Query structured SPL (Structured Product Labeling) data from the FDA. No API key needed (≤1 000 req/day).
4
5	## Input → Detection
6
7	\| Input Example \| Routed To \|
8	\|---\|---\|
9	\| `"ASPIRIN"` or `["METFORMIN","LISINOPRIL"]` \| `search_drug` — brand/generic name lookup \|
10	\| `"hypertension"` or `["diabetes","migraine"]` \| `search_by_indication` — indication text search \|
11	\| (no input) \| `count_by_route` — top administration routes \|
12
13	All search functions accept a single string or a list of strings.
14
15	## API
16
17	\| Function \| Input \| Returns \|
18	\|---\|---\|---\|
19	\| `search_drug(query, limit)` \| str \\| list[str], int \| `{term: [label_dicts]}` \|
20	\| `search_by_indication(query, limit)` \| str \\| list[str], int \| `{condition: [label_dicts]}` \|
21	\| `count_by_route(top_n)` \| int \| `[{term, count}]` \|
22	\| `summarize(results)` \| dict from above \| compact multi-line text \|
23
24	Each `label_dict` contains: `brand_name`, `generic_name`, `manufacturer`, `route`, `substance_name`, `product_type`, `indications`, `contraindications`, `warnings`, `dosage`, `adverse_reactions`.
25
26	## Usage
27
28	See `if __name__ == "__main__"` block in `05_openFDA_Human_Drug.py` for runnable examples covering: single drug, batch drugs, single indication, batch indications, route counts, and raw JSON output.
29
30	## Notes
31
32	- Long text fields (`indications`, `warnings`, etc.) are truncated to keep payloads concise.
33	- On HTTP/query errors the result dict contains an `error` key for that term.
34	- Endpoint: `https://api.fda.gov/drug/label.json`

People who liked this also viewed

6 picks

Type

openfda

132stars4forks

View on GitHub

How to install openfda?

qsong-github/drugclaw/openfda

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

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# openFDA Human Drug Skill
2
3	Query structured SPL (Structured Product Labeling) data from the FDA. No API key needed (≤1 000 req/day).
4
5	## Input → Detection
6
7	\| Input Example \| Routed To \|
8	\|---\|---\|
9	\| `"ASPIRIN"` or `["METFORMIN","LISINOPRIL"]` \| `search_drug` — brand/generic name lookup \|
10	\| `"hypertension"` or `["diabetes","migraine"]` \| `search_by_indication` — indication text search \|
11	\| (no input) \| `count_by_route` — top administration routes \|
12
13	All search functions accept a single string or a list of strings.
14
15	## API
16
17	\| Function \| Input \| Returns \|
18	\|---\|---\|---\|
19	\| `search_drug(query, limit)` \| str \\| list[str], int \| `{term: [label_dicts]}` \|
20	\| `search_by_indication(query, limit)` \| str \\| list[str], int \| `{condition: [label_dicts]}` \|
21	\| `count_by_route(top_n)` \| int \| `[{term, count}]` \|
22	\| `summarize(results)` \| dict from above \| compact multi-line text \|
23
24	Each `label_dict` contains: `brand_name`, `generic_name`, `manufacturer`, `route`, `substance_name`, `product_type`, `indications`, `contraindications`, `warnings`, `dosage`, `adverse_reactions`.
25
26	## Usage
27
28	See `if __name__ == "__main__"` block in `05_openFDA_Human_Drug.py` for runnable examples covering: single drug, batch drugs, single indication, batch indications, route counts, and raw JSON output.
29
30	## Notes
31
32	- Long text fields (`indications`, `warnings`, etc.) are truncated to keep payloads concise.
33	- On HTTP/query errors the result dict contains an `error` key for that term.
34	- Endpoint: `https://api.fda.gov/drug/label.json`

People who liked this also viewed

6 picks

Type