openFDA Database

88TrustedShips scripts

Regulatory data retrieval from the openFDA API for research and safety analysis.

What it does

Installing this skill equips your assistant with a dedicated interface to the public openFDA database. Instead of guessing data availability or navigating complex web interfaces, the assistant can now execute structured queries to pull information across drug, device, food, tobacco, and cosmetic categories directly into your workspace.

By managing connections through the provided execution script, the assistant ensures requests stay within required API rate limits. It outputs findings to designated files, preventing your chat history from becoming cluttered with voluminous raw data and allowing you to analyze large datasets using other tools or scripts.

When it earns its place

Reach for it when…

This skill is ideal for professionals needing to pull specific regulatory records, such as adverse event reports, device 510(k) clearances, drug labeling text, or product recall notices for professional research or compliance verification.

Look elsewhere when…

Do not use this for tasks requiring real-time clinical diagnostics or patient-specific medical advice, as the database provides generalized regulatory records rather than individual patient health outcomes. It also lacks a graphical dashboard for visual data exploration, meaning users preferring charts over raw data files may find it less intuitive.

What to say to use it

You never invoke a skill directly — the assistant picks it up when your request matches what it covers. These are the kinds of things that do that.

  • find recent adverse events for this medication
  • pull a list of device recalls in the last year
  • retrieve the latest labeling requirements for cosmetics
  • count the frequency of reactions reported for a drug

Install it

Install for all your projects

Copy the skill directory into your personal skills folder. Claude picks it up on its own the next time your request matches what it does — there is nothing to enable.

bash
git clone --depth 1 --branch main https://github.com/google-deepmind/science-skills.git /tmp/science-skills
mkdir -p ~/.claude/skills
cp -r /tmp/science-skills/skills/openfda_database ~/.claude/skills/openfda-database

Install for one project only

Put it in the project's own skills folder instead, so it can be committed and shared with everyone working on that repository.

bash
cp -r /tmp/science-skills/skills/openfda_database .claude/skills/openfda-database

If a skill of the same name exists in both places, the personal one wins.

Installing on Claude.ai or through the API instead? The full guide covers every surface.