clinical-trial-finder

Find clinical trials for a gene, variant, or condition from ClinicalTrials.gov + EUCTR, with FHIR R4 output

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Evidence Insight/clinical-trial-finder/SKILL.md

Quality

Content

57%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 skill is well structured and self-contained with strong domain decisions and safety framing, but it is held back by verbosity in rationale, the absence of executable command examples, and the lack of an explicitly sequenced validation workflow. Tightening explanations and adding a concrete invocation plus a numbered validate-checkpoint workflow would lift the lower dimensions.

Suggestions

Add a concrete, copy-pasteable CLI example (e.g. a sample invocation with --gene / --rsid / --fhir flags and expected outputs) to improve actionability.

Replace the flat decision list with a short numbered workflow that includes explicit validation checkpoints (query -> validate FHIR -> retry on transient failure -> write outputs).

Trim non-essential rationale sentences (keep the decision and citation, drop the prose justification) to improve conciseness.

Dimension	Reasoning	Score
Conciseness	The body is decision-focused and mostly efficient, but rationale sentences like 'Clinical actionability does not scale with result volume...' add padding that could be tightened without losing the core decision.	3 / 5
Actionability	Concrete flags, endpoints, field names, and thresholds are provided, but there is no executable CLI example or script invocation to make the guidance copy-paste ready, leaving it incomplete on the execution side.	3 / 5
Workflow Clarity	Content is organized as a flat list of decisions rather than a sequenced workflow, and the batch/multi-page API operations lack an explicit validate->fix->retry checkpoint sequence beyond the retry-backoff mention.	3 / 5
Progressive Disclosure	With no bundle files and no external references, the self-contained body is well organized into clear sections (Domain Decisions, Safety Rules, Agent Boundary, Input Validation), satisfying the simple-skill exception for a top score.	5 / 5
	Total	14 / 20 Passed

Description

65%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 clearly states what the skill does and is highly distinct, but it is capped by the missing 'Use when...' trigger guidance and only moderate action specificity. Adding an explicit use-when clause and a couple more concrete actions would raise the top dimensions.

Suggestions

Add an explicit 'Use when...' clause naming when Claude should invoke this skill (e.g. 'Use when a user asks for clinical trials by gene, variant, or condition').

List a few more concrete actions beyond 'Find' (e.g. 'search, filter by status, and export trials as CSV/FHIR R4') to improve specificity.

Include common synonyms such as 'clinical studies' or 'recruiting trials' to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	It names the domain ('Find clinical trials') and the input modes ('gene, variant, or condition') but offers only one main action, matching the anchor for domain + 1-2 concrete actions without comprehensive coverage.	3 / 5
Completeness	The 'what' is clear (find trials from ClinicalTrials.gov + EUCTR with FHIR R4 output), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Natural terms like 'clinical trials', 'gene', 'variant', and 'condition' are present and would be said by users, but common synonyms ('clinical studies', 'recruiting trials') are missing, so it sits just below comprehensive coverage.	4 / 5
Distinctiveness Conflict Risk	The named registries (ClinicalTrials.gov + EUCTR) and FHIR R4 output carve a clear niche with distinct triggers and minimal overlap with other skills.	5 / 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/Evidence Insight/clinical-trial-finder/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.