tooluniverse-clinical-trial-design

Strategic clinical trial design feasibility assessment. Analyzes 6 dimensions (endpoint, population, comparator, effect size, duration, regulatory pathway) using precedent trials and FDA guidance. Produces enrollment projections, endpoint recommendations, and approval-pathway analysis. Use for trial-protocol design, power/sample-size estimation, comparator selection, and FDA submission strategy. Driven by precedent-based reasoning rather than first-principles math.

Quality

82%

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

65%

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

The body is highly actionable with executable code and a well-specified report structure, but it is over-long for a SKILL.md, lacks explicit validation checkpoints in its workflow, and leans on reference files that are not present in the bundle.

Suggestions

Move the per-path tool listings, the 14-section report spec, and the programmatic-access API code into the referenced files (STUDY_DESIGN_PROCEDURES.md, REPORT_TEMPLATE.md, WORKFLOW_DETAILS.md) to slim the SKILL.md body to a true overview.

Add an explicit validation checkpoint to the workflow, e.g. verify retrieved trial/precedent data against a second source before scoring, and re-validate the feasibility score if any dimension is graded C/D.

Either ship the six referenced files as a bundle or remove the dangling references; currently every 'See X.md' link resolves to a missing file.

Dimension	Reasoning	Score
Conciseness	The ~275-line body is mostly substantive and assumes Claude's intelligence (no basic-concept explaining), but the long tool-by-path listings, the tangential programmatic-access code block, and a 'When to Use' section that repeats the description's triggers could be tightened or moved to references.	2 / 3
Actionability	Provides fully executable code — the Quick Start example uses real tool calls with parameters, and the ClinicalTrials.gov v2 API pagination block with pandas is copy-paste ready — plus specific named tools per path, not pseudocode.	3 / 3
Workflow Clarity	A sequence is present (reasoning-first questions → 6 parallel paths → report-first assembly), but there are no explicit validation checkpoints or fix-and-retry feedback loops, leaving checkpoints implicit.	2 / 3
Progressive Disclosure	References are clearly signaled inline and in a Reference Files table with one-level-deep intent, but the six referenced files (STUDY_DESIGN_PROCEDURES.md, REPORT_TEMPLATE.md, etc.) do not exist as bundles, and detailed content that should be split out (tool lists, 14-section spec, API code) remains inline.	2 / 3
	Total	9 / 12 Passed

Description

100%

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 follows the recommended pattern precisely: concrete multi-action capabilities followed by an explicit 'Use for' trigger clause. It is specific, complete, and well-differentiated with no over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Analyzes 6 dimensions (endpoint, population, comparator, effect size, duration, regulatory pathway)' and 'Produces enrollment projections, endpoint recommendations, and approval-pathway analysis' — matching the multi-action anchor rather than the single-domain level 2.	3 / 3
Completeness	Explicitly answers both what ('Analyzes 6 dimensions... Produces enrollment projections...') and when ('Use for trial-protocol design...'), with an explicit 'Use for' trigger clause, so it is not capped at level 2.	3 / 3
Trigger Term Quality	The 'Use for' clause surfaces natural domain terms a user would actually say — 'trial-protocol design', 'power/sample-size estimation', 'comparator selection', 'FDA submission strategy' — giving good coverage rather than the sparse single-keyword level 2.	3 / 3
Distinctiveness Conflict Risk	The clinical-trial-design feasibility niche with trial-specific triggers (enrollment projections, endpoint selection, FDA submission) is clearly distinct from sibling drug/disease-research skills and unlikely to fire for the wrong skill.	3 / 3
	Total	12 / 12 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: mims-harvard/ToolUniverse
Path: plugin/skills/tooluniverse-clinical-trial-design/SKILL.md
Commit: 089eb8e

Reviewed: about 6 hours 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.