clinical-trials-database

Query ClinicalTrials.gov via APIv2. Use when you want to search for trials by condition, drug, location, status, or phase; retrieve trial details by NCT ID; check eligibility/inclusion criteria; count trials across conditions or time periods; identify a sponsor's trial portfolio; find recruiting trials for patient matching.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

86%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, highly actionable skill body with excellent progressive disclosure and concrete examples. Minor conciseness loss from repeated `--fields` guidance and slight overlap between the inline Response Layout Summary and the schema reference.

Suggestions

Consolidate the `--fields` guidance into one place (Core Rules) and reference it rather than re-explaining in the Context Efficiency Warning and flag reference.

Trim or shorten the inline Response Layout Summary, pointing earlier to references/studies_schema.md to avoid duplicating field-path content.

Add a brief error-recovery note for API failures (non-200 responses / rate-limit retries) to strengthen workflow feedback loops.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and action-oriented, but the `--fields` guidance is repeated across Core Rules, the Context Efficiency Warning, and the flag reference, and the Response Layout Summary partially duplicates references/studies_schema.md; these could be trimmed.	4 / 5
Actionability	Copy-paste-ready `uv run` commands with full flag references and worked examples covering search, get-study, get-eligibility, count, location, sponsor, combined, raw-query, and pagination — fully executable across common cases.	5 / 5
Workflow Clarity	Core Rules give a sequenced checklist ('use --count-total first', 'always use --fields', 'paginate large result sets') and pagination is walked through, but there are no explicit error-recovery/feedback loops for API failures; the skill is read-only so the destructive-cap does not apply.	4 / 5
Progressive Disclosure	Clear overview body with well-signaled one-level-deep references — `references/clinical_trials_api.md` for Essie syntax/enums, `references/studies_schema.md` for field paths, and `scripts/clinical_trials_api.py` as the wrapper — confirmed against the actual bundle; content is appropriately split and a References section summarizes navigation.	5 / 5
	Total	18 / 20 Passed

Description

95%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, specific description with explicit what-and-when structure and rich natural trigger terms. The only blemish is second-person voice ('Use when you want to'), which slightly lowers specificity per the voice guideline.

Suggestions

Rewrite in third person to avoid the voice penalty, e.g. 'Use when searching for trials by condition, drug, location, status, or phase' → keep 'Query ClinicalTrials.gov...' as the lead imperative.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('search for trials by condition, drug, location, status, or phase', 'retrieve trial details by NCT ID', 'check eligibility/inclusion criteria', 'count trials', 'identify a sponsor's trial portfolio', 'find recruiting trials for patient matching') — comprehensive, but the second-person phrasing 'Use when you want to' triggers the voice penalty, reducing the score by 1.	4 / 5
Completeness	Explicitly answers both what ('Query ClinicalTrials.gov via APIv2' plus enumerated capabilities) and when ('Use when you want to...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural-term coverage including synonyms users actually say: 'clinical trials', 'trials', 'condition', 'drug', 'status', 'phase', 'NCT ID', 'eligibility', 'recruiting trials', 'patient matching', 'sponsor'.	5 / 5
Distinctiveness Conflict Risk	Clear niche (ClinicalTrials.gov APIv2) with domain-specific triggers (NCT ID, recruiting trials, patient matching, sponsor portfolio) unlikely to fire for unrelated skills.	5 / 5
	Total	19 / 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: google-deepmind/science-skills
Path: skills/clinical_trials_database/SKILL.md
Commit: 6883275

Reviewed: 4 days 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.