tooluniverse-infectious-disease

Rapid pathogen characterization and drug repurposing for outbreaks. Combines pathogen genomics (NCBI, BVBRC), host immune response (IEDB), drug-target databases (ChEMBL, DGIdb), and literature surveillance (PubMed/EuropePMC). Use for emerging-pathogen profiling, antiviral candidate identification, and outbreak intelligence reporting.

Quality

79%

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 ./plugin/skills/tooluniverse-infectious-disease/SKILL.md

Quality

Content

71%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 well-structured, largely actionable multi-phase workflow with concrete tooling guidance, clear sequencing, and useful error-recovery fallbacks. Its main weakness is progressive disclosure: the five referenced bundle files are absent, and the promised inline executable code is deferred to those missing references.

Suggestions

Ship the referenced bundle files (TOOLS_REFERENCE.md, phase_details.md, report_template.md, CHECKLIST.md, EXAMPLES.md) alongside SKILL.md, or inline the small ones and remove the broken links, so the one-level-deep references actually resolve.

Add at least one copy-paste-ready Python example in SKILL.md (e.g., scoring targets or ranking docking candidates) to honor the "COMPUTE, DON'T DESCRIBE" directive rather than deferring all code to phase_details.md.

Add an explicit inline validation gate between phases (e.g., "Complete the Phase N checklist before advancing to Phase N+1") so verification does not depend solely on the external CHECKLIST.md.

Dimension	Reasoning	Score
Conciseness	Mostly lean and operational (tool/parameter tables, fallback chains, scoring weights, thresholds) without explaining concepts Claude already knows; minor trimming possible in the "KEY PRINCIPLES" and "REASONING STRATEGY" sections, which carry some motivational padding.	4 / 5
Actionability	Highly concrete guidance via specific tool names, corrected parameters, and numeric thresholds (pLDDT > 70, 5+ targets, 20+ candidates, Essentiality 30%...), but inline executable Python is largely deferred to the referenced phase_details.md despite the "COMPUTE, DON'T DESCRIBE" directive.	4 / 5
Workflow Clarity	Clear Phase 0-6 sequence with an overview tree, per-phase outputs, completeness checklists, and fallback chains as error-recovery loops; the explicit pre-delivery verification detail lives in the referenced CHECKLIST.md rather than as inline validate-then-proceed gates.	4 / 5
Progressive Disclosure	A well-signaled one-level-deep References table (TOOLS_REFERENCE.md, phase_details.md, report_template.md, CHECKLIST.md, EXAMPLES.md) with clear contents descriptions, but none of the five referenced files exist in the bundle, so navigation would break, and a fair amount of operational detail is inlined in the body.	3 / 5
	Total	15 / 20 Passed

Description

87%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 description that clearly states both capability and explicit usage triggers within a well-defined, distinctive niche. Slight room to tighten action wording and broaden trigger synonyms, but it answers what-and-when comprehensively in third person.

Dimension	Reasoning	Score
Specificity	Lists several concrete action areas ("pathogen characterization", "drug repurposing", "emerging-pathogen profiling", "antiviral candidate identification", "outbreak intelligence reporting") plus specific data sources, but the actions are somewhat higher-level than the ultra-concrete anchor-5 examples.	4 / 5
Completeness	Explicitly answers both what ("Rapid pathogen characterization and drug repurposing... Combines pathogen genomics...") and when ("Use for emerging-pathogen profiling, antiviral candidate identification, and outbreak intelligence reporting.") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural domain terms users would say ("outbreaks", "drug repurposing", "emerging-pathogen", "antiviral") with good coverage, but misses common synonyms/variants a user might also say (e.g. "pandemic", "antibiotic resistance").	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (infectious-disease outbreak intelligence) with distinct triggers and named databases (NCBI, BVBRC, IEDB, ChEMBL, DGIdb, PubMed/EuropePMC), giving minimal overlap risk with other skills.	5 / 5
	Total	18 / 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
relative_links	Relative link issues: 5 missing	Warning

	Total	15 / 16 Passed

Repository: mims-harvard/ToolUniverse
Path: plugin/skills/tooluniverse-infectious-disease/SKILL.md
Commit: 1b02920

Reviewed: 1 day 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.