clinicaltrials-database

Query ClinicalTrials.gov via API v2. Search trials by condition, drug, location, status, or phase. Retrieve trial details by NCT ID, export data, for clinical research and patient matching.

Quality

68%

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

Fix and improve this skill with Tessl

tessl review fix ./backend/cli/skills/databases/clinicaltrials-database/SKILL.md

Quality

Content

71%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.

The content is highly actionable with executable, copy-paste-ready code throughout, and it correctly externalizes deep API detail into a real bundled reference. It is penalized for verbosity in the overview and for missing validation checkpoints on batch/pagination operations.

Suggestions

Trim the Overview and the repeated 'Common use cases' bullets — assume Claude already knows what a clinical trial registry is.

Add explicit validation checkpoints for batch operations: cap pagination/retry loops, surface a 'verify total retrieved vs totalCount' step, and bound the recursive rate-limit retry.

Move the long status-value list and the data-structure path reference into references/api_reference.md, leaving SKILL.md as a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with focused code examples, but the Overview re-explains what ClinicalTrials.gov is and several 'Common use cases' bullets pad out concepts Claude already knows, so it sits at the 'mostly efficient but could be tightened' anchor rather than a 4.	3 / 5
Actionability	Every capability is backed by copy-paste-ready executable Python against real endpoints and the bundled script's actual functions (search_studies, get_study_details, etc.), covering common cases with concrete field paths.	5 / 5
Workflow Clarity	Steps are listed and a rate-limit pattern is shown, but the batch/pagination and bulk-export operations lack validation checkpoints, and the retry example recurses without a retry cap — the guidelines cap batch-operation workflows at 3 when validation is missing.	3 / 5
Progressive Disclosure	Structure is good with a concise Quick Start, capability sections, and a real one-level-deep reference (references/api_reference.md) plus a bundled script that exist on disk, but some detail (status values, long data-structure path lists) could be pushed to the reference rather than inlined, keeping it just below a 5.	4 / 5
	Total	15 / 20 Passed

Description

66%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.

The description is specific and distinct, naming concrete API v2 actions and clinical-trial-specific terms, but it omits an explicit 'Use when...' trigger clause, which caps completeness at 3. Trigger-term coverage is solid but lacks synonyms.

Suggestions

Add an explicit trigger clause, e.g. 'Use when searching ClinicalTrials.gov for recruiting trials, matching patients to studies, or retrieving trial details by NCT ID.'

Include natural synonyms a patient or researcher might say, such as 'clinical studies', 'study registry', or 'clinicaltrial.gov'.

Confirm the 'when' guidance names concrete scenarios (patient matching, drug research) rather than only implying them via a trailing 'for ...' fragment.

Dimension	Reasoning	Score
Specificity	Lists several specific actions ('Search trials by condition, drug, location, status, or phase', 'Retrieve trial details by NCT ID, export data') with only minor coverage gaps, matching the 'lists several specific actions' anchor rather than the comprehensive 5.	4 / 5
Completeness	Has a clear 'what' (query/search/retrieve/export) but no explicit 'Use when...' trigger clause — the 'when' is only weakly implied by 'for clinical research and patient matching', which per the guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Good keyword coverage with natural user terms ('clinical trials', 'condition', 'drug', 'phase', 'NCT ID') but misses common synonyms or the .gov/source phrasing a user might say, falling just below the comprehensive 5.	4 / 5
Distinctiveness Conflict Risk	Names ClinicalTrials.gov specifically with NCT IDs and clinical-trial-specific parameters, giving it a clear niche with only minor overlap risk against other medical-database skills.	4 / 5
	Total	15 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (507 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/databases/clinicaltrials-database/SKILL.md
Commit: 3a6c3a9

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.