CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

Quality

80%

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 ./plugin/skills/tooluniverse-immunology/SKILL.md
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 highly actionable, tool-centric skill body: exact parameter formats, a Wrong/Correct gotchas table, concrete workflows, and database-specific IDs make it easy to execute correctly. Its weaknesses are the inlined bulk API reference (no progressive disclosure into separate files) and a Reasoning Frameworks section that re-explains basic immunology at token cost.

Suggestions

Move the Tool Reference tables and Parameter Gotchas into a references/tool-reference.md file, keeping only a short tool-orientation summary in SKILL.md with clearly signaled one-level-deep links.

Compress the Reasoning Frameworks section to decision rules and database-routing guidance only (e.g., keep 'Fab binding → IEDB/SAbDab/IMGT vs Fc function → FAERS/OpenTargets/TheraSAbDab') and drop textbook explanations of innate vs adaptive timing, CDR/Fc structure, and complement pathway biochemistry.

Add one or two fully worked example tool invocations with actual argument values (e.g., TheraSAbDab_search_therapeutics(query="pembrolizumab") followed by intact_get_interaction_network(identifier="Q9NZQ7")) to push actionability to copy-paste readiness.

DimensionReasoningScore

Conciseness

The tool tables, Parameter Gotchas, and pathway IDs are dense non-redundant value, but the 'Reasoning Frameworks' section spends paragraphs on textbook immunology Claude already knows ('Innate is fast (hours) and antigen-nonspecific; adaptive is slow (days)', the CDR/Fc and complement-pathway walkthroughs, the IL-12→JAK2/TYK2→STAT4 example). This is mostly efficient with clear trimming opportunities, matching the middle anchor.

3 / 5

Actionability

Concrete executable guidance throughout: exact parameter names and formats ('stId=' not 'pathway_id=', 'targetName="IL6"', organism '"9606" string taxon ID', UniProt accession 'Q9NZQ7'), a Wrong/Correct gotchas table, and ready-to-use pathway IDs (R-HSA-168256, hsa04630). Falls short of the top anchor only because no literal example invocations with argument values are shown.

4 / 5

Workflow Clarity

Four workflows give clear ordered tool sequences with named tools, and some validation checkpoints exist ('validate with orthogonal methods', 'FAERS PRR > 2 with IC025 > 0 is a signal, not causal proof', evidence grading A/B/C). Minor gaps — no explicit feedback/retry loops — keep it below the top anchor; no destructive or batch operations so the cap does not apply.

4 / 5

Progressive Disclosure

No bundle files exist, so the ~155-line body is monolithic: sections are well-organized, but roughly 85 lines of tool-reference tables and parameter gotchas are inlined in SKILL.md — content that belongs in a references/ file. This matches the anchor where structure exists but content that should be separate is inline.

3 / 5

Total

14

/

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 with an explicit 'Use for...' clause, concrete capability enumeration, named domain databases, and natural trigger phrases in third-person voice. The only weakness is that some listed capabilities read as topic nouns rather than concrete actions and a few natural keyword variants are absent.

DimensionReasoningScore

Specificity

Lists several concrete capabilities ('MHC/HLA binding prediction', 'vaccine epitope mapping', 'autoimmune disease genetics'), but several others are domain topics ('T/B cell repertoire', 'antibody-antigen interactions') rather than discrete actions, leaving minor gaps versus the comprehensive-anchor.

4 / 5

Completeness

Clearly answers both 'what' (workflow capabilities plus the databases used: 'Uses IEDB, IMGT, SAbDab, UniProt') and 'when' ('Use for adaptive immunity questions, immune response analysis, antibody/TCR/BCR characterization, immunogenicity prediction, and immune-pathway-to-disease mapping') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural user phrasings like 'adaptive immunity questions', 'immune response analysis', and 'immunogenicity prediction' with synonyms (antibody/TCR/BCR) give good keyword coverage, but common variants such as allergy or immuno-oncology terms are missing.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear immunology niche with named field-specific databases (IEDB, IMGT, SAbDab) and tightly scoped triggers ('adaptive immunity questions', 'immunogenicity prediction'), giving minimal overlap risk with other skills.

5 / 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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

mims-harvard/ToolUniverse

Path

plugin/skills/tooluniverse-immunology/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.