CtrlK
BlogDocsLog inGet started
Tessl Logo

tooluniverse-pharmacogenomics

Pharmacogenomics (PGx) research — drug-gene interactions (CPIC, PharmGKB), CPIC dosing guidelines, variant-drug-response associations, ethnic-allele-frequency considerations, and metabolizer-status scoring. Use for PGx-informed dosing recommendations, CYP/HLA pharmacogenomic allele interpretation, and clinically-actionable PGx report generation.

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-sequenced operational reference with concrete tool signatures, gotchas, and fallback strategies. Its main weaknesses are minor cross-phase repetition and a monolithic single-file structure with no progressive disclosure into bundle files.

Suggestions

Move the per-tool reference (signatures, return shapes, parameter notes) into a references/ file and keep SKILL.md as a workflow overview pointing to it, improving progressive disclosure.

De-duplicate tools described in multiple phases (e.g., PharmGKB_get_dosing_guidelines, OpenTargets_drug_pharmacogenomics_data) by defining each once and cross-referencing.

Trim the "Key Parameter Notes" section to only items not already stated inline, or remove it in favor of inline gotchas, to reduce redundancy.

DimensionReasoningScore

Conciseness

Per-line content is dense and high-signal with no conceptual padding, but at ~270 lines it repeats a few tools across phases (e.g., PharmGKB_get_dosing_guidelines in Phase 2 and 5) and the "Key Parameter Notes" section restates gotchas already described inline.

2 / 3

Actionability

Gives exact tool names, required parameters, return shapes, copy-paste-ready call examples (e.g., CPIC_get_recommendations(drug="codeine", limit=50)) and concrete example workflow chains.

3 / 3

Workflow Clarity

A clear Phase 0→6 sequence with an overview diagram, explicit gotchas, and fallback/error-recovery branches; this is a read/query skill so the absence of destructive-operation validation loops does not apply.

3 / 3

Progressive Disclosure

No bundle files exist and all content is inline in a single ~270-line file; the large tool reference is well-sectioned but could be split into a separate reference file rather than living entirely in SKILL.md.

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.

A strong, third-person description that enumerates concrete capabilities and provides an explicit "Use for" trigger clause covering both what and when. It is specific, naturally triggered, and distinct from other skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions (drug-gene interactions, CPIC dosing guidelines, variant-drug-response associations, metabolizer-status scoring, allele interpretation, report generation) and names concrete domain entities (CPIC, PharmGKB, CYP/HLA).

3 / 3

Completeness

Explicitly answers both what (the enumerated research tasks) and when, via the "Use for PGx-informed dosing recommendations..." clause providing explicit trigger guidance.

3 / 3

Trigger Term Quality

Natural in-domain phrases a PGx user would actually say ("drug-gene interactions", "dosing recommendations", "dosing guidelines", "allele interpretation", "PGx report") are present, anchored by an explicit "Use for" trigger clause.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear pharmacogenomics niche with distinct triggers (CPIC, PharmGKB, CYP/HLA, metabolizer scoring) that are unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

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.