Query DDInter drug-drug interactions via REST API (1.7M+ interactions, 2,400+ drugs). Search by drug name/ID for severity (major/moderate/minor), mechanisms, and clinical recommendations. No auth. For FDA labeling use dailymed-database; for pharmacogenomics use clinpgx-database.
SkillScore95Maintained
Automatic
◆Clinical / Healthcare pack
Last verified 8/23/2026
What it changes
Passed 21 of 22 test cases with the skill, and 9 of 22 without it.
Without skill41%
With skill95%
Checks it passed that the model alone missed
Sets parameter drug1.
Sets parameter drug2.
Queries the /between/ API endpoint.
and 18 more in the full report
12 fixed9 passed either way1 still failing0 broke
Pass-rate lift
+55 pp
Tokens
+366%
Agent turns
0%
Response time
-36%
Model gemini-3.6-flashMeasured 8/23/2026v121 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 12
Prompt
When requesting interaction data from the interaction REST endpoint, what query parameter increases the page limit beyond the default 10 items?
What was checked, without and with the skill
Checked
Without skill
With skill
Sets query parameter page_size to retrieve additional results.
Missed
Passed
case-09 · gemini-3.6-flash · 8/23/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md752 linessingle file
DDInter Drug-Drug Interaction Database
Overview
DDInter is an open, curated database of drug-drug interactions (DDIs) covering 2,400+ drugs and 1.7M+ pairwise interactions with structured severity levels (major, moderate, minor), mechanistic annotations, and clinical management recommendations. Access is provided via a JSON REST API at https://ddinter.scbdd.com/api/ — no authentication or registration required.
When to Use
Checking whether two co-administered drugs have a known interaction and its severity (major/moderate/minor)
Retrieving all known interactions for a given drug to support polypharmacy risk assessment
Identifying the mechanistic basis (pharmacokinetic vs. pharmacodynamic) of a drug-drug interaction
Screening a drug combination list for potential major interactions before clinical decision support
Building automated DDI checking pipelines for medication review or drug repurposing workflows
Analyzing the DDI network for a drug class (e.g., all major interactions for CYP3A4 substrates)
For FDA-approved drug labeling text (indications, dosage, contraindications) use dailymed-database
For pharmacogenomics interactions (CYP genotype-drug associations) use clinpgx-database; DDInter covers drug-drug not gene-drug pairs
For drug adverse event reports from FAERS use fda-database
Environment: internet connection; no API key required
Rate limits: no officially published rate limit; use time.sleep(0.3) between requests in batch loops for polite access
pip install requests pandas matplotlib networkx
Quick Start
import requests
BASE = "https://ddinter.scbdd.com/api"
# Search for a drug by name
r = requests.get(f"{BASE}/drug/", params={"drug_name": "warfarin", "format": "json"}, timeout=15)
r.raise_for_status()
data = r.json()