CtrlK
BlogDocsLog inGet started
Tessl Logo

tooluniverse-immunology

Immunology research workflows: antibody-antigen interactions, T/B cell repertoire, MHC/HLA binding prediction, autoimmune disease genetics, vaccine epitope mapping. Uses IEDB, IMGT, SAbDab, UniProt. Use for adaptive immunity questions, immune response analysis, antibody/TCR/BCR characterization, immunogenicity prediction, and immune-pathway-to-disease mapping.

70

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

The canonical home for this skill is tooluniverse-immunology in mims-harvard/ToolUniverse

SKILL.md
Quality
Evals
Security

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.

Highly actionable content with concrete tools, parameters, and gotchas, plus well-sequenced research workflows. It loses points for didactic re-explanation of known immunology concepts and for keeping a large tool reference inlined rather than in a dedicated reference file.

Suggestions

Trim the reasoning-framework paragraphs to decision-only guidance: drop textbook re-explanation of complement pathways and JAK-STAT cascades, keeping only the tool-selection rules and thresholds.

Move the Tool Reference tables and Parameter Gotchas into a references/tool_reference.md file, leaving SKILL.md as an overview with a clearly signaled one-level-deep pointer.

Add an explicit validate-and-retry checkpoint to the research workflows (e.g., 'if a database returns no hits, fall back to these alternative tools') to strengthen feedback loops.

DimensionReasoningScore

Conciseness

The body is information-dense, but several reasoning-framework paragraphs re-explain concepts Claude already knows (e.g., the three complement activation pathways, the innate-vs-adaptive distinction, JAK-STAT cascade tracing) that could be trimmed to decision-only guidance.

3 / 5

Actionability

Concrete tool names with exact parameters, a wrong/correct Parameter Gotchas table, specific pathway IDs (hsa04630, R-HSA-1280215), Kd thresholds, and copy-ready workflow sequences give fully executable guidance for common cases.

5 / 5

Workflow Clarity

Named workflows (Antibody target research, Autoimmune disease genetics, Immunotherapy safety comparison) give clear sequenced tool chains, with evidence grading and 'validate with orthogonal methods' serving as checkpoints, though explicit error-recovery feedback loops are mostly implicit.

4 / 5

Progressive Disclosure

Sections are clearly headed and well-organized, but no bundle files exist and the large Tool Reference tables and per-tool parameter details are inlined in SKILL.md rather than split into a separate reference file one level deep.

3 / 5

Total

15

/

20

Passed

Description

100%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, third-person description that pairs a concrete capability list with explicit, natural trigger guidance and a clearly bounded immunology niche. It is comprehensive without devolving into fluff.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('antibody-antigen interactions, T/B cell repertoire, MHC/HLA binding prediction, autoimmune disease genetics, vaccine epitope mapping') plus named databases, giving comprehensive coverage of the domain's capabilities.

5 / 5

Completeness

It explicitly answers both 'what' (the enumerated research workflows and databases) and 'when' ('Use for adaptive immunity questions...') with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

The 'Use for' clause supplies natural trigger phrases users would actually say ('adaptive immunity questions, immune response analysis, antibody/TCR/BCR characterization, immunogenicity prediction'), covering the main entry points to the skill.

5 / 5

Distinctiveness Conflict Risk

The immunology niche is sharply delimited by specialized databases (IEDB, IMGT, SAbDab) and immune-specific triggers, leaving minimal overlap with adjacent biomedical skills.

5 / 5

Total

20

/

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.