fda

Name: fda
Author: ai4protein

244stars35forks

How to install fda?

ai4protein/venusfactory2/fda

$npx -y skills add ai4protein/VenusFactory2 --skill fda

Installs into the current project.

Summary

Query openFDA API for drugs, devices, adverse events, recalls, regulatory submissions (510k, PMA), substance identification (UNII), for FDA regulatory data analysis and safety research.

Files · 1

View on GitHub

SKILL.md

1	# FDA Database Access
2
3	## Overview
4
5	Access comprehensive FDA regulatory data through openFDA, the FDA's initiative to provide open APIs for public datasets. Query information about drugs, medical devices, foods, animal/veterinary products, and substances using Python with standardized interfaces.
6
7	Key capabilities:
8	- Query adverse events for drugs, devices, foods, and veterinary products
9	- Access product labeling, approvals, and regulatory submissions
10	- Monitor recalls and enforcement actions
11	- Look up National Drug Codes (NDC) and substance identifiers (UNII)
12	- Analyze device classifications and clearances (510k, PMA)
13	- Track drug shortages and supply issues
14	- Research chemical structures and substance relationships
15
16	## When to Use This Skill
17
18	This skill should be used when working with:
19	- Drug research: Safety profiles, adverse events, labeling, approvals, shortages
20	- Medical device surveillance: Adverse events, recalls, 510(k) clearances, PMA approvals
21	- Food safety: Recalls, allergen tracking, adverse events, dietary supplements
22	- Veterinary medicine: Animal drug adverse events by species and breed
23	- Chemical/substance data: UNII lookup, CAS number mapping, molecular structures
24	- Regulatory analysis: Approval pathways, enforcement actions, compliance tracking
25	- Pharmacovigilance: Post-market surveillance, safety signal detection
26	- Scientific research: Drug interactions, comparative safety, epidemiological studies
27
28	## Quick Start
29
30	### 1. Project Scripts and Import
31
32	Scripts live in `src/tools/search/deepsearch/fda/`. Each module is runnable with `python -m src.tools.search.deepsearch.fda.<module>`.
33
34	\| Script \| Purpose \| Main \|
35	\|--------\|---------\|------\|
36	\| `fda_query.py` \| Full `FDAQuery` class: all categories (drug, device, food, animal, substance), rate limit, cache \| Yes \|
37	\| `fda_examples.py` \| Comprehensive examples: drug safety, device surveillance, food recalls, substance, comparative, veterinary \| Yes \|
38	\| `fda_drug.py` \| Drug-only demo: events, label, recalls \| Yes \|
39	\| `fda_device.py` \| Device-only demo: events, 510k, classification \| Yes \|
40	\| `fda_substance.py` \| Substance demo: by name, by UNII \| Yes \|
41
42	Import the client:
43
44	```python
45	from src.tools.search.deepsearch.fda import FDAQuery
46
47	# Initialize (API key optional but recommended)
48	fda = FDAQuery(api_key="YOUR_API_KEY")
49
50	# Query drug adverse events
51	events = fda.query_drug_events("aspirin", limit=100)
52
53	# Get drug labeling
54	label = fda.query_drug_label("Lipitor", brand=True)
55
56	# Search device recalls
57	recalls = fda.query("device", "enforcement",
58	search="classification:Class+I",
59	limit=50)
60	```
61
62	### 2. API Key Setup
63
64	While the API works without a key, registering provides higher rate limits:
65	- Without key: 240 requests/min, 1,000/day
66	- With key: 240 requests/min, 120,000/day
67
68	Register at: https://open.fda.gov/apis/authentication/
69
70	Set as environment variable:
71	```bash
72	export FDA_API_KEY="your_key_here"
73	```
74
75	### 3. Running Scripts (each has `if __name__ == "__main__"`)
76
77	```bash
78	# Full query module (minimal drug/label examples)
79	python -m src.tools.search.deepsearch.fda.fda_query
80
81	# Comprehensive examples (drug, device, food, substance, comparative, veterinary)
82	python -m src.tools.search.deepsearch.fda.fda_examples
83
84	# Domain-specific demos
85	python -m src.tools.search.deepsearch.fda.fda_drug
86	python -m src.tools.search.deepsearch.fda.fda_device
87	python -m src.tools.search.deepsearch.fda.fda_substance
88	```
89
90	## FDA Database Categories
91
92	### Drugs
93
94	Access 6 drug-related endpoints covering the full drug lifecycle from approval to post-market surveillance.
95
96	Endpoints:
97	1. Adverse Events - Reports of side effects, errors, and therapeutic failures
98	2. Product Labeling - Prescribing information, warnings, indications
99	3. NDC Directory - National Drug Code product information
100	4. Enforcement Reports - Drug recalls and safety actions
101	5. Drugs@FDA - Historical approval data since 1939
102	6. Drug Shortages - Current and resolved supply issues
103
104	Common use cases:
105	```python
106	from src.tools.search.deepsearch.fda import FDAQuery
107	fda = FDAQuery(api_key="YOUR_API_KEY")
108
109	# Safety signal detection
110	fda.count_by_field("drug", "event",
111	search="patient.drug.medicinalproduct:metformin",
112	field="patient.reaction.reactionmeddrapt")
113
114	# Get prescribing information
115	label = fda.query_drug_label("Keytruda", brand=True)
116
117	# Check for recalls
118	recalls = fda.query_drug_recalls(drug_name="metformin")
119
120	# Monitor shortages
121	shortages = fda.query("drug", "drugshortages",
122	search="status:Currently+in+Shortage")
123	```
124
125	Reference: See `references/drugs.md` for de

People who liked this also viewed

6 picks

Type

find-skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skSkillsJul 20262.6M27k
grill-meA relentless interview to sharpen a plan or design.SkillsJul 2026633k182k
vercel-react-best-practicesVercel's official collection of agent skillsSkillsJul 2026573k29k
improve-codebase-architectureScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.SkillsJul 2026522k182k
setup-matt-pocock-skillsConfigure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.SkillsJul 2026454k182k
triageMove issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.SkillsJul 2026424k182k

fda

244stars35forks

View on GitHub

How to install fda?

ai4protein/venusfactory2/fda

$npx -y skills add ai4protein/VenusFactory2 --skill fda

Installs into the current project.

Summary

Query openFDA API for drugs, devices, adverse events, recalls, regulatory submissions (510k, PMA), substance identification (UNII), for FDA regulatory data analysis and safety research.

Files · 1

View on GitHub

SKILL.md

1	# FDA Database Access
2
3	## Overview
4
5	Access comprehensive FDA regulatory data through openFDA, the FDA's initiative to provide open APIs for public datasets. Query information about drugs, medical devices, foods, animal/veterinary products, and substances using Python with standardized interfaces.
6
7	Key capabilities:
8	- Query adverse events for drugs, devices, foods, and veterinary products
9	- Access product labeling, approvals, and regulatory submissions
10	- Monitor recalls and enforcement actions
11	- Look up National Drug Codes (NDC) and substance identifiers (UNII)
12	- Analyze device classifications and clearances (510k, PMA)
13	- Track drug shortages and supply issues
14	- Research chemical structures and substance relationships
15
16	## When to Use This Skill
17
18	This skill should be used when working with:
19	- Drug research: Safety profiles, adverse events, labeling, approvals, shortages
20	- Medical device surveillance: Adverse events, recalls, 510(k) clearances, PMA approvals
21	- Food safety: Recalls, allergen tracking, adverse events, dietary supplements
22	- Veterinary medicine: Animal drug adverse events by species and breed
23	- Chemical/substance data: UNII lookup, CAS number mapping, molecular structures
24	- Regulatory analysis: Approval pathways, enforcement actions, compliance tracking
25	- Pharmacovigilance: Post-market surveillance, safety signal detection
26	- Scientific research: Drug interactions, comparative safety, epidemiological studies
27
28	## Quick Start
29
30	### 1. Project Scripts and Import
31
32	Scripts live in `src/tools/search/deepsearch/fda/`. Each module is runnable with `python -m src.tools.search.deepsearch.fda.<module>`.
33
34	\| Script \| Purpose \| Main \|
35	\|--------\|---------\|------\|
36	\| `fda_query.py` \| Full `FDAQuery` class: all categories (drug, device, food, animal, substance), rate limit, cache \| Yes \|
37	\| `fda_examples.py` \| Comprehensive examples: drug safety, device surveillance, food recalls, substance, comparative, veterinary \| Yes \|
38	\| `fda_drug.py` \| Drug-only demo: events, label, recalls \| Yes \|
39	\| `fda_device.py` \| Device-only demo: events, 510k, classification \| Yes \|
40	\| `fda_substance.py` \| Substance demo: by name, by UNII \| Yes \|
41
42	Import the client:
43
44	```python
45	from src.tools.search.deepsearch.fda import FDAQuery
46
47	# Initialize (API key optional but recommended)
48	fda = FDAQuery(api_key="YOUR_API_KEY")
49
50	# Query drug adverse events
51	events = fda.query_drug_events("aspirin", limit=100)
52
53	# Get drug labeling
54	label = fda.query_drug_label("Lipitor", brand=True)
55
56	# Search device recalls
57	recalls = fda.query("device", "enforcement",
58	search="classification:Class+I",
59	limit=50)
60	```
61
62	### 2. API Key Setup
63
64	While the API works without a key, registering provides higher rate limits:
65	- Without key: 240 requests/min, 1,000/day
66	- With key: 240 requests/min, 120,000/day
67
68	Register at: https://open.fda.gov/apis/authentication/
69
70	Set as environment variable:
71	```bash
72	export FDA_API_KEY="your_key_here"
73	```
74
75	### 3. Running Scripts (each has `if __name__ == "__main__"`)
76
77	```bash
78	# Full query module (minimal drug/label examples)
79	python -m src.tools.search.deepsearch.fda.fda_query
80
81	# Comprehensive examples (drug, device, food, substance, comparative, veterinary)
82	python -m src.tools.search.deepsearch.fda.fda_examples
83
84	# Domain-specific demos
85	python -m src.tools.search.deepsearch.fda.fda_drug
86	python -m src.tools.search.deepsearch.fda.fda_device
87	python -m src.tools.search.deepsearch.fda.fda_substance
88	```
89
90	## FDA Database Categories
91
92	### Drugs
93
94	Access 6 drug-related endpoints covering the full drug lifecycle from approval to post-market surveillance.
95
96	Endpoints:
97	1. Adverse Events - Reports of side effects, errors, and therapeutic failures
98	2. Product Labeling - Prescribing information, warnings, indications
99	3. NDC Directory - National Drug Code product information
100	4. Enforcement Reports - Drug recalls and safety actions
101	5. Drugs@FDA - Historical approval data since 1939
102	6. Drug Shortages - Current and resolved supply issues
103
104	Common use cases:
105	```python
106	from src.tools.search.deepsearch.fda import FDAQuery
107	fda = FDAQuery(api_key="YOUR_API_KEY")
108
109	# Safety signal detection
110	fda.count_by_field("drug", "event",
111	search="patient.drug.medicinalproduct:metformin",
112	field="patient.reaction.reactionmeddrapt")
113
114	# Get prescribing information
115	label = fda.query_drug_label("Keytruda", brand=True)
116
117	# Check for recalls
118	recalls = fda.query_drug_recalls(drug_name="metformin")
119
120	# Monitor shortages
121	shortages = fda.query("drug", "drugshortages",
122	search="status:Currently+in+Shortage")
123	```
124
125	Reference: See `references/drugs.md` for de

People who liked this also viewed

6 picks

Type