CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

85%

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

SKILL.md
Quality
Evals
Security

Quality

Content

77%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 body is an efficient, highly actionable, well-validated workflow document whose only material defect is bundle integrity: the carefully organized progressive-disclosure structure points at five detail files that do not exist alongside it. Secondary issues are mild redundancy across the overview/summary/checklist layers and thin specificity in Phases 4.5 and 6.

Suggestions

Ship the five referenced files (TOOLS_REFERENCE.md, phase_details.md, report_template.md, CHECKLIST.md, EXAMPLES.md) in the skill bundle, or inline their essential content and delete the dead links — as it stands, every reference in the References table is unresolvable.

Collapse the overlap between the Workflow Overview ASCII tree and the Phase Summaries (e.g., keep the tree as the map and strip duplicated phase descriptions down to operational deltas), and trim the KEY PRINCIPLES list of items like 'Speed is critical'.

Add concrete tool names and parameter guidance for the Phase 4.5 KEGG pathway analysis and Phase 6 report synthesis steps, matching the specificity level of Phases 1-4.

DimensionReasoningScore

Conciseness

The body is dense with tool-specific facts Claude cannot know (parameter correction table, fallback chains, pLDDT thresholds) and assumes domain competence throughout. It falls short of 5 because the workflow tree, phase summaries, and completeness checklist restate the same phase structure three times, and lines like 'Speed is critical - Optimize for rapid actionable intelligence' add little.

4 / 5

Actionability

Highly concrete for an instruction-only skill: wrong-vs-correct parameter table, example values ('GCF_000005845.2', "'mpox/clade-IIb'", min_proportion 0.95), scoring weights (30/25/25/20), and explicit thresholds (pLDDT > 70). Not 5 because Phase 4.5 (KEGG) and Phase 6 give only high-level direction without tool-call specifics, and code examples are delegated entirely to external files.

4 / 5

Workflow Clarity

Seven phases are clearly sequenced with a declared OUTPUT per phase, plus explicit validation checkpoints (Phase 0 parameter corrections, the pLDDT > 70 docking gate, per-phase completeness checklists) and fallback chains for error recovery — matching the anchor-5 pattern of sequence, validation, and feedback loops.

5 / 5

Progressive Disclosure

The References table is clearly signaled and one level deep, but none of the five referenced files (TOOLS_REFERENCE.md, phase_details.md, report_template.md, CHECKLIST.md, EXAMPLES.md) exist in the bundle — there are no references/, scripts/, or assets/ directories, and the files appear nowhere in the workspace. Judged against the actual bundle structure, the disclosure chain is broken: every link is dead, so detail-seeking navigation fails. Not 2 because SKILL.md itself is well-sectioned rather than a monolithic inline dump.

3 / 5

Total

16

/

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: concrete, source-anchored capability statements plus an explicit 'Use for...' trigger clause covering three concrete scenarios. The only gaps are uncovered capabilities (structure prediction/docking) and a few missing natural synonyms like 'epidemic' or 'pandemic'.

DimensionReasoningScore

Specificity

The description lists several concrete capability areas with named sources — 'pathogen genomics (NCBI, BVBRC)', 'host immune response (IEDB)', 'drug-target databases (ChEMBL, DGIdb)', 'literature surveillance (PubMed/EuropePMC)' — but omits other core capabilities of the skill such as structure prediction, docking, and pathway analysis. It is above the 3 anchor (which covers only 1-2 actions) but short of 5's comprehensive coverage.

4 / 5

Completeness

Explicitly answers both questions: the 'what' (combines genomics, immune response, drug-target databases, literature surveillance) and the 'when' via an explicit 'Use for emerging-pathogen profiling, antiviral candidate identification, and outbreak intelligence reporting' clause with concrete trigger phrases, mirroring the anchor-5 example pattern. Not 4 because the when-clause is explicit and specific rather than vague or weakly implied.

5 / 5

Trigger Term Quality

Natural user-facing terms are present — 'outbreak', 'drug repurposing', 'antiviral candidate', 'emerging-pathogen profiling' — matching the good-keyword-coverage anchor. Falls short of 5 because common synonyms users would say are missing (e.g., 'epidemic', 'pandemic', 'therapeutic options', 'repurpose [drug] against [pathogen]').

4 / 5

Distinctiveness Conflict Risk

A clear niche (outbreak pathogen intelligence) anchored by named bio-databases (IEDB, ChEMBL, DGIdb, BVBRC) that no generic skill would claim, giving it distinct triggers with minimal conflict risk.

5 / 5

Total

18

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

relative_links

Relative link issues: 5 missing

Warning

Total

15

/

16

Passed

Repository

mims-harvard/ToolUniverse

Path

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

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.