tooluniverse-clinical-trial-matching

AI-driven patient-to-trial matching for precision medicine and oncology. Given a patient profile (disease, molecular alterations, stage, prior treatments), discovers and ranks clinical trials from ClinicalTrials.gov using multi-dimensional matching across molecular eligibility...

Quality

74%

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/Evidence Insight/tooluniverse-clinical-trial-matching/SKILL.md

Quality

Content

78%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 a well-structured overview with lean tables, a clearly sequenced multi-phase workflow with validation, and exemplary progressive disclosure into verified reference files; minor tightening and a few more inline examples would push it higher.

Dimension	Reasoning	Score
Conciseness	The body is dense and well-organized around tables (workflow phases, score components, gene IDs) with little concept over-explanation; a few sections like the 10-item KEY PRINCIPLES list could be trimmed slightly.	4 / 5
Actionability	Concrete, actionable guidance is present (exact point allocations, gene CIViC IDs, biomarker parsing table, tier thresholds), and executable tool-call code is appropriately delegated to reference files; minor gaps remain in inline examples.	4 / 5
Workflow Clarity	An 11-phase (0–10) sequence is clearly laid out with named steps and summaries, plus validation via Phase 0 parameter verification, an Input Validation section, and a required Completeness Checklist; checkpoints could be slightly more explicit within phases.	4 / 5
Progressive Disclosure	The SKILL.md is a clear overview that delegates detail to three real one-level-deep reference files (phases_detail.md, scoring_and_matching.md, parsing_and_validation.md), each signaled with markdown links and summarized in a References table.	5 / 5
	Total	17 / 20 Passed

Description

70%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 clearly scoped to a distinct niche, but it is missing an explicit 'Use when…' trigger clause and ends with a truncation ellipsis, which limits its completeness.

Suggestions

Append a 'Use when…' clause listing natural trigger phrases (e.g., 'Use when a patient asks about available clinical trials for a specific cancer or biomarker').

Remove the trailing '…' and complete the sentence so the description reads as finished rather than truncated.

Add common-synonym trigger terms users actually say, such as 'find cancer trials' or 'clinical trials for my mutation'.

Dimension	Reasoning	Score
Specificity	Names concrete inputs ('patient profile (disease, molecular alterations, stage, prior treatments)') and specific actions ('discovers and ranks clinical trials from ClinicalTrials.gov using multi-dimensional matching'), but the trailing '…' signals incompleteness, keeping it below a comprehensive 5.	4 / 5
Completeness	It clearly states what the skill does ('discovers and ranks clinical trials…') but has no 'Use when…' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	Good keyword coverage with natural terms like 'clinical trials', 'oncology', 'precision medicine', and 'ClinicalTrials.gov', but missing common user phrasings like 'find clinical trials for my cancer' or biomarker synonyms.	4 / 5
Distinctiveness Conflict Risk	The niche is clearly defined as AI-driven patient-to-trial matching on ClinicalTrials.gov for precision oncology, with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	16 / 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/Evidence Insight/tooluniverse-clinical-trial-matching/SKILL.md
Commit: 63c61d3

Reviewed: 5 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.