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 gr...

Quality

76%

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 ./scientific-skills/Protocol Design/tooluniverse-clinical-trial-design/SKILL.md

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.

The body is a strong, executable skill: copy-paste-ready code, a clearly sequenced 6-path workflow, concrete report templates, and well-structured one-level-deep references. Its main weakness is mild inline redundancy (scoring weighting restated, section list repeated) and the absence of explicit per-path validation feedback loops in a batch multi-path workflow.

Suggestions

Remove the inline duplication of the feasibility-score weighting — keep it once and point to references/scoring_and_endpoints.md for the rest — to tighten conciseness toward the lean anchor.

Add an explicit per-path validation checkpoint (e.g., 'After each path, verify at least one evidence-graded data source before compiling the report') to introduce a validate-then-compile feedback loop for the batch workflow.

Consolidate the 14-section list so it appears once (structure) rather than being restated in the Output Format Requirements section.

Dimension	Reasoning	Score
Conciseness	The body is dense and well-organized with executable snippets and tables, but the feasibility-score weighting is restated inline (Core Principles #3 and the Feasibility Scorecard Template) and the 14-section list is repeated conceptually in Output Format, which are minor instances of over-explanation that could be trimmed rather than the lean 'every token earns its place' of 5.	4 / 5
Actionability	It provides copy-paste-ready, fully executable Quick Start Python with concrete parameters, an exact Tool Quick Reference table of real tool names and signatures, and a concrete report template, matching the 'fully executable; copy-paste ready; specific examples cover the common cases' anchor.	5 / 5
Workflow Clarity	The 6 research paths are clearly sequenced with a diagram and the Report-First process is explicit, and verification exists via required 14-section completeness, mandatory evidence grading, score-transparency, and an Error Handling fallback section, but there is no explicit per-path validate-then-compile checkpoint or retry feedback loop, leaving minor validation gaps versus the 5 anchor.	4 / 5
Progressive Disclosure	SKILL.md is a clear overview with three well-signaled, one-level-deep references (each file links only back to SKILL.md with no nesting), content is appropriately split into research_paths_detail, scoring_and_endpoints, and examples_and_troubleshooting, and navigation is surfaced both inline ('→ Detailed ...') and via a References table, matching the top anchor.	5 / 5
	Total	18 / 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 six concrete capability dimensions in third person, but it omits any explicit 'Use when' trigger guidance and appears truncated ('with evidence gr...'), which cap its completeness. Adding a concrete trigger clause and finishing the sentence would lift it toward the top anchors.

Suggestions

Add an explicit 'Use when...' clause with natural trigger phrases (e.g., 'Use when planning Phase 1/2 trial feasibility, enrollment projections, endpoint selection, or biomarker-selected trial design') to satisfy the 'when' half of completeness.

Complete the truncated tail ('with evidence gr...') so the description is not cut off mid-word.

Include a couple of natural user-facing synonyms (e.g., 'trial planning', 'enrollment feasibility', 'basket trial') to broaden trigger-term coverage toward the comprehensive anchor.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'Evaluates patient population sizing, biomarker prevalence, endpoint selection, comparator analysis, safety monitoring, and regulatory pathways' and 'Creates comprehensive feasibility reports' — with only minor coverage gaps, matching the 'several specific actions' anchor rather than the comprehensive 5.	4 / 5
Completeness	It has a clear 'what' (the evaluated dimensions and report output) but no explicit 'when'/'Use when...' clause, so per the judging guideline a missing trigger clause caps completeness at 3; not a 4 because 'when' is entirely absent rather than merely weak.	3 / 5
Trigger Term Quality	Contains good domain keyword coverage (the six dimension names plus 'feasibility reports') that a specialist user would naturally say, but lacks natural conversational phrasings and file-format-style triggers, sitting noticeably above the 'some relevant keywords' anchor at 3 but below the comprehensive 5.	4 / 5
Distinctiveness Conflict Risk	The clinical-trial-design niche is mostly distinct with specific triggers (biomarker/endpoint/regulatory pathway sizing), with only minor overlap risk against the sibling trial-matching and adverse-event skills named in the body, fitting the 'mostly distinct' anchor.	4 / 5
	Total	15 / 20 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Protocol Design/tooluniverse-clinical-trial-design/SKILL.md
Commit: 63c61d3

Reviewed: 4 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.