tooluniverse-clinical-trial-design

Strategic clinical trial design feasibility assessment using ToolUniverse. Evaluates patient population sizing, biomarker prevalence, endpoint selection, comparator analysis, safety monitoring, and regulatory pathways. Creates comprehensive feasibility reports with evidence grading, enrollment projections, and trial design recommendations. Use when planning Phase 1/2 trials, assessing trial feasibility, or designing biomarker-driven studies.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

77%

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 examples and a clearly sequenced, validated workflow, but it is verbose and monolithic — heavy report templates and the full example belong in separate reference files rather than the SKILL.md overview.

Suggestions

Move the 14-section report template and the complete EGFR example workflow into reference files (e.g. references/report_template.md, references/example_workflow.md) and link to them from a lean SKILL.md overview to reduce token cost and improve progressive disclosure.

Trim inline boilerplate tables (eligibility criteria, assessment schedules, budget line items) to the minimal structural skeleton; let Claude fill domain-standard details rather than pre-listing them.

Condense the five use cases and best-practices/pitfalls sections into brief pointers or a single reference, keeping only the most instructive examples inline.

Dimension	Reasoning	Score
Conciseness	The ~1100-line body is packed with detailed fill-in-the-blank report templates (14 sections of boilerplate tables, full eligibility criteria, assessment schedules, budget line items) much of which a capable model could generate itself; valuable domain specifics are diluted by verbosity that could be tightened.	2 / 3
Actionability	Provides copy-paste-ready executable code with real ToolUniverse tool calls (Quick Start and the full EGFR example workflow), named tools per research path, and concrete report templates — fully actionable rather than abstract.	3 / 3
Workflow Clarity	Multi-step process is explicitly sequenced — report-first approach with numbered steps, 6 parallel research paths, cross-source validation checkpoints ('Validate Biomarker Prevalence Across Sources'), evidence grading, and Simon 2-stage go/no-go decision rules.	3 / 3
Progressive Disclosure	No bundle files exist; the entire skill is one monolithic document with the 14-section report template, full example workflow, and use cases all inline rather than split into reference files, despite being well-organized with clear section headers.	2 / 3
	Total	10 / 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 is specific, complete, and uses natural third-person voice with an explicit 'Use when' trigger clause. It clearly conveys both capabilities and activation conditions without padding.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Evaluates patient population sizing, biomarker prevalence, endpoint selection, comparator analysis, safety monitoring, and regulatory pathways' and 'Creates comprehensive feasibility reports with evidence grading, enrollment projections' — matching the multi-action anchor.	3 / 3
Completeness	Clearly answers both what (the six evaluation dimensions and report outputs) and when via an explicit 'Use when planning Phase 1/2 trials, assessing trial feasibility, or designing biomarker-driven studies' clause.	3 / 3
Trigger Term Quality	Natural terms a trial planner would actually say appear explicitly — 'planning Phase 1/2 trials', 'assessing trial feasibility', 'designing biomarker-driven studies' — with good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (clinical trial design feasibility via ToolUniverse) with distinct, domain-specific triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1196 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/med/tooluniverse-clinical-trial-design/SKILL.md
Commit: df37802

Reviewed: 2 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.