RepoAI
Browse MCPs

Clinical Trials Database

88TrustedShips scripts

Access structured registry data from ClinicalTrials.gov using API-linked search tools.

What it does

This skill installs a dedicated interface for interacting with the official ClinicalTrials.gov REST API. It transforms your assistant into a research tool capable of pulling specific study details, recruitment statuses, and eligibility requirements directly from the global record database.

By managing complex query construction and rate-limiting, the assistant retrieves precisely the data needed for medical literature reviews or patient-level research. It keeps context windows manageable by enforcing field-specific requests, ensuring that massive study records do not overwhelm your workflow.

When it earns its place

Reach for it when…

Use this to perform systematic searches across trial registries, identify active studies for specific conditions, or verify the inclusion criteria for particular drug interventions.

Look elsewhere when…

Do not use this for clinical diagnosis or as a substitute for professional medical advice. It is unsuitable for analyzing high-level statistical trends across massive, multi-decade historical datasets, where dedicated bioinformatics platforms or local database indexing would provide better performance.

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 active clinical trials for hypertension in the United States
  • List the eligibility requirements for this NCT ID
  • Are there any recruiting studies for this specific medication
  • Check how many trials are currently listed for this condition

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/clinical_trials_database ~/.claude/skills/clinical-trials-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/clinical_trials_database .claude/skills/clinical-trials-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.

Pair it with an MCP server

Clinical Trials Database changes how the work is done. These servers change what Claude can reach while doing it.

How skills and MCP servers differ →