CtrlK
BlogDocsLog inGet started
Tessl Logo

tooluniverse-clinical-data-integration

End-to-end drug safety review integrating FDA labels, FAERS adverse event reports, PRR/ROR disproportionality, pharmacogenomic biomarkers, clinical trial data, and published literature. Use for regulatory drug safety reviews, comprehensive pharmacovigilance reports, label-vs-real-world AE comparison, and clinical decision support for drug safety.

64

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/tooluniverse/skills/tooluniverse-clinical-data-integration/SKILL.md

The canonical home for this skill is tooluniverse-clinical-data-integration in mims-harvard/ToolUniverse

SKILL.md
Quality
Evals
Security

Quality

Content

63%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.

A thorough, well-structured drug-safety workflow with highly actionable tool specifics and a clear phase sequence. It is somewhat verbose and monolithic — trimming redundant prose and splitting the tool/interpretation reference into bundle files would improve token efficiency and navigation.

Suggestions

Remove the opening paragraph that duplicates the frontmatter description and tighten the 'Guiding principles' list to avoid restating points already made in later sections.

Extract the per-phase tool reference (input/output schemas) and the FAERS signal-interpretation table into a reference file under ./references/, keeping SKILL.md as a workflow overview that links one level deep.

Show at least one literal, copy-paste-ready tool invocation example (e.g., a FAERS disproportionality call with real arguments) to bridge the gap between described and executable guidance.

DimensionReasoningScore

Conciseness

Mostly dense and tool-focused, but the opening paragraph duplicates the description, the 'Guiding principles' section restates earlier points, and some conceptual prose (ICD-10 vs SNOMED flavor) could be trimmed without losing actionability.

3 / 5

Actionability

Concrete tool names with exact input/output parameters (e.g., 'setid NOT set_id', 'medicinalproduct NOT drug_name'), explicit signal thresholds (PRR >= 2.0, lower CI > 1, N >= 3), and query tips give mostly executable guidance, though tool calls are described rather than shown as literal invokable syntax.

4 / 5

Workflow Clarity

A clear 7-phase (0-6) sequence with per-phase numbered workflows and a 5-step signal-credibility validation checklist; minor gaps in explicit validate-then-proceed feedback loops, but operations are read-only so no destructive-cap applies.

4 / 5

Progressive Disclosure

Well-organized into clear sections, but the skill is a single monolithic ~14KB file with no bundle files; content such as the full per-tool reference and FAERS interpretation tables is inlined that could plausibly live in separate reference files.

3 / 5

Total

14

/

20

Passed

Description

88%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.

A strong, specific description that clearly states both capability and use-cases with concrete data sources and natural trigger phrases. Minor room to broaden trigger synonyms and sharpen separation from sibling pharmacovigilance skills.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities and data sources — 'integrating FDA labels, FAERS adverse event reports, PRR/ROR disproportionality, pharmacogenomic biomarkers, clinical trial data, and published literature' — giving comprehensive, specific coverage rather than vague language.

5 / 5

Completeness

Explicitly answers both what ('End-to-end drug safety review integrating...') and when ('Use for regulatory drug safety reviews, comprehensive pharmacovigilance reports, label-vs-real-world AE comparison, and clinical decision support') with concrete trigger phrases.

5 / 5

Trigger Term Quality

'Use for regulatory drug safety reviews, comprehensive pharmacovigilance reports, label-vs-real-world AE comparison, and clinical decision support' supplies natural trigger phrases, but a few common lay terms (e.g., 'side effects', 'adverse events') are absent in favor of specialized jargon.

4 / 5

Distinctiveness Conflict Risk

A clear regulatory-grade drug-safety niche with distinct multi-source integration triggers, but 'drug safety review' and 'pharmacovigilance' overlap with closely related sibling skills noted in the body.

4 / 5

Total

18

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
mims-harvard/ToolUniverse
Reviewed

Table of Contents

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.