searching-clinicaltrials

Searches ClinicalTrials.gov for studies by condition, intervention, and recruitment status using the modern v2 REST API with cursor (pageToken) pagination. Use when the user wants to find trials for a diagnosis or drug, screen patients against open studies, build a trial-matching feature, or pull a trial corpus for analysis. Trigger keywords: clinical trial, ClinicalTrials.gov, NCT number, trial search, recruiting studies, eligibility, query.cond, query.intr, pageToken, v2 API. Pairs adjacent to OpenMed: take Disease/Pharmaceutical entities from openmed.analyze_text and turn them into query.cond / query.intr filters; the returned eligibility text feeds parsing-trial-eligibility. ClinicalTrials.gov API v2 is fully public — no API key, no license.

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

82%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable API skill with executable examples, a clear response schema, and useful edge-case guidance. Slight verbosity from the redundant cURL block and only implicit batch validation keep it just short of top marks.

Suggestions

Drop or condense the cURL block since the Python example already shows the full request; keep one canonical form to tighten conciseness.

Add an explicit validation checkpoint in the Workflow (e.g., verify totalCount against pulled records and stop/restart on a rejected pageToken) to formalize the batch feedback loop.

Consider moving the full response-shape field table and edge-case enum list into a references file so SKILL.md stays a lean overview with one-level-deep pointers.

Dimension	Reasoning	Score
Conciseness	Mostly lean with executable code and no padding about concepts Claude already knows, but the cURL block duplicates the Python example and a few points ('no page numbers', 'no API key') are restated, leaving minor trim opportunities.	4 / 5
Actionability	Fully executable, copy-paste-ready Python (search_trials, iter_all), an equivalent cURL call, a field-trimming snippet, and a response-shape table cover the common cases concretely.	5 / 5
Workflow Clarity	A clear 4-step Workflow (build query → page through → persist → optionally re-NER) is sequenced with a 'cap total pulls' guardrail and raise_for_status feedback, though explicit validation checkpoints for the batch pull are only implicit.	4 / 5
Progressive Disclosure	Well-organized into clearly signaled sections (Quick start, Response shape, Pagination, Workflow, Edge cases, Standards & references) with external doc links one level deep; no bundle files are provided, so the single self-contained file is appropriately structured with minor gaps.	4 / 5
	Total	17 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that concretely states capabilities, explicit use-when triggers, and a comprehensive keyword list tied to a distinct API niche. Minor verbosity from the OpenMed pairing note does not detract from clarity.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Searches ClinicalTrials.gov for studies by condition, intervention, and recruitment status', 'screen patients against open studies', 'build a trial-matching feature', 'pull a trial corpus' — with comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Clearly answers 'what' ('Searches ClinicalTrials.gov for studies by condition, intervention, and recruitment status using the modern v2 REST API with cursor pagination') and 'when' ('Use when the user wants to find trials for a diagnosis or drug, screen patients against open studies, build a trial-matching feature, or pull a trial corpus') with concrete trigger phrases.	5 / 5
Trigger Term Quality	An explicit 'Trigger keywords' list covers natural user phrases ('clinical trial', 'ClinicalTrials.gov', 'NCT number', 'trial search', 'recruiting studies', 'eligibility') alongside technical synonyms, giving comprehensive coverage a user would actually say.	5 / 5
Distinctiveness Conflict Risk	Scoped tightly to ClinicalTrials.gov v2 API with NCT-specific triggers; the distinct niche and domain-specific keywords make conflict with other skills minimal.	5 / 5
	Total	20 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: maziyarpanahi/openmed
Path: skills/searching-clinicaltrials/SKILL.md
Commit: 80da98c

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.