FAERS Query Skill
SkillDev toolsQuery the FDA Adverse Event Reporting System (FAERS) via openFDA API. Use whenever the user asks about adverse drug reactions, side effects, drug safety signals, or wants to look up reported adverse events for one or more drug names.
Instructions available. Your AI can read the instructions. Execution depends on the setup they require.
Account requirements not reviewed. Check the skill instructions before use; ahel provides instructions and does not run this skill.
Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
Then ask your AI: use the FAERS Query Skill skill
What this skill tells your AI
The instructions your AI receives, as published by qsong-github/drugclaw in skills/adr/faers/SKILL.md and read by ahel’s review.
Query adverse event reports from FDA's FAERS database. No API key required.
API
| Function | Input | Returns |
|---|---|---|
get_metadata() | — | {total, last_updated} |
count_reactions(drug, top_n) | single drug name | [{term, count}, ...] |
count_reactions_batch(drugs, top_n) | list of drug names | {drug: [{term, count}, ...]} |
search_adverse_events(drug, limit) | single drug name | raw openFDA response dict |
summarize_reactions(reactions, drug) | reaction list + label | compact one-line text |
Usage
See if __name__ == "__main__" block in faers_query.py for runnable examples covering: single drug query, batch query, metadata retrieval, raw report inspection, and LLM-friendly summary output.
Notes
- Drug names should be uppercase (auto-converted internally).
- Input accepts a single string or a list of strings for batch queries.
summarize_reactionsproduces compactDRUG: reaction(count), ...format suitable for LLM context.- Source: openFDA Drug Adverse Events endpoint (
https://api.fda.gov/drug/event.json).
Signals
- GitHub stars
- 116
- Forks
- 3
- Last commit
- Aug 2026
Advanced
- Item type
- skill
- Key
faers-query- Source
- github.com/qsong-github/drugclaw
github.com/qsong-github/drugclaw