Query FDA drug labels (DailyMed) via REST API. Search structured product labels (SPLs) by name, NDC, set ID, or RxCUI; get indications, dosage, warnings, adverse reactions, packaging. No auth. For adverse events use fda-database; for DDIs use ddinter-database.
SkillScore91Maintained
Automatic
◆Clinical / Healthcare pack
Last verified 8/24/2026
What it changes
Passed 17 of 19 test cases with the skill, and 12 of 19 without it.
Without skill64%
With skill91%
Checks it passed that the model alone missed
The response identifies LOINC code 42229-5.
The query targets the drugnames.json endpoint.
The script creates a chart saved as statin_counts.png.
and 6 more in the full report
6 fixed14 passed either way2 still failing0 broke
Pass-rate lift
+27 pp
Tokens
+287%
Agent turns
0%
Response time
-40%
Model gemini-3.6-flashMeasured 8/24/2026v120 of 22 cases passed with skill · 19 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 5
Prompt
When analyzing the clinical pharmacology sections of official FDA labels, which LOINC code corresponds to the 'Mechanism of Action' section in DailyMed SPL documents?
What was checked, without and with the skill
Checked
Without skill
With skill
The response identifies LOINC code 42229-5.
Missed
Passed
case-18 · gemini-3.6-flash · 8/24/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md621 linessingle file
DailyMed Drug Label Database
Overview
DailyMed is the National Library of Medicine's official repository of FDA-approved drug labeling information, containing 140,000+ structured product labels (SPLs) for prescription drugs, OTC medications, biologics, and vaccines. The REST API (v2) provides structured JSON/XML access to the full label content including indications, dosage, warnings, contraindications, adverse reactions, and packaging data — with no authentication required.
When to Use
Retrieving official FDA-approved prescribing information for a drug by name, NDC code, or set ID
Extracting structured label sections (indications, warnings, dosage, adverse reactions) for pharmacological research
Looking up all marketed formulations of an active ingredient with packaging and NDC codes
Cross-referencing drug labels using RxCUI identifiers from RxNorm integration
Building drug information pipelines that require authoritative FDA label content (not user-reported data)
Comparing label content across brand name and generic formulations of the same drug
For adverse event reports from FAERS, use fda-database instead; DailyMed contains label text, not post-market safety signals
For drug-drug interaction severity data, use ddinter-database; DailyMed label text is unstructured for interactions
Prerequisites
Python packages: requests, pandas, matplotlib
Data requirements: drug names, NDC codes, set IDs, or RxCUI identifiers
Environment: internet connection; no API key required
Rate limits: no officially published limit; ~100 requests/minute is safe for polite access; add time.sleep(0.3) in batch loops
pip install requests pandas matplotlib
Quick Start
import requests
BASE = "https://dailymed.nlm.nih.gov/dailymed/services/v2"
# Search drug labels by name
r = requests.get(f"{BASE}/spls.json", params={"drug_name": "metformin", "pagesize": 5})
r.raise_for_status()
data = r.json()
print(f"Total labels found: {data['metadata']['total_elements']}")