tooluniverse-vaccine-design

Computational vaccine candidate design: peptide/subunit vaccines via MHC-I/MHC-II epitope prediction (IEDB), population HLA coverage optimization, B-cell epitope identification, and cross-strain conservation analysis. Use for vaccine epitope prediction, HLA allele coverage, multi-epitope construct design, and immunogenicity assessment. Combines predicted MHC binding with experimentally validated IEDB epitopes for higher-confidence designs.

Quality

80%

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-vaccine-design/SKILL.md

Quality

Content

67%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, actionable workflow document with concrete code, threshold tables, and a clearly referenced helper script. Its main weakness is verbosity in the conceptual/priming sections and the absence of explicit validation-retry loops.

Suggestions

Tighten the 'Reasoning Strategy' section: trim immunology primers Claude already knows (e.g. 'B-cell epitopes trigger antibody production', CD8+/CD4+ definitions) and keep only the decision-relevant principles.

Add explicit feedback loops in the workflow — e.g. after Phase 3, 'if coverage <70%, return to Phase 1 to add epitopes for uncovered HLA supertypes' — rather than only noting actions in the interpretation table.

Give Phase 4 (Conservation) the same concrete, executable treatment as the other phases; currently it relies on PubMed literature search and VEP as indirect proxies rather than a direct cross-strain conservation step.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with dense tables, thresholds and code, but the multi-paragraph 'Reasoning Strategy' and inline immunology primers ('B-cell epitopes trigger antibody production', CD8+/CD4+ explanations) restate concepts Claude already knows and could be tightened.	3 / 5
Actionability	Provides concrete, mostly copy-paste-ready code with real tool names and arguments (IEDB_predict_mhci_binding, iedb_search_mhc, population_coverage.py) plus interpretation tables; Phase 4 conservation is comparatively hand-wavy (PubMed/VEP proxies rather than a direct conservation tool), a minor gap.	4 / 5
Workflow Clarity	Phases 0-5 are clearly sequenced with a diagram and per-phase interpretation tables whose 'Action' columns act as informal feedback checkpoints (e.g. '<50% coverage → fundamental redesign'), but there are no explicit validate-then-retry loops for the prediction pipeline.	4 / 5
Progressive Disclosure	Well-organized into clear sections (Reasoning Strategy, When to Use, Core Tools, Workflow per phase, Limitations) with the one bundle file scripts/population_coverage.py clearly referenced and signaled; no nested references, though a fair amount of detailed reference-style content (HLA supertype strategy, IC50 tables) is kept inline.	4 / 5
	Total	15 / 20 Passed

Description

92%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, specific description that clearly states both what the skill does and when to use it, with concrete domain trigger phrases and minimal overlap risk. The only minor gap is a few missing synonymous trigger phrasings.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'MHC-I/MHC-II epitope prediction', 'population HLA coverage optimization', 'B-cell epitope identification', 'cross-strain conservation analysis', 'multi-epitope construct design', 'immunogenicity assessment' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers 'what' ('Computational vaccine candidate design: ...') and 'when' with a concrete 'Use for ...' trigger clause listing the triggering tasks; both are present and concrete.	5 / 5
Trigger Term Quality	Strong natural domain keywords ('vaccine epitope prediction', 'HLA allele coverage', 'multi-epitope construct design', 'immunogenicity assessment') that a user in this field would actually say, though a few synonymous phrasings (e.g. 'T-cell epitopes', 'antibody epitopes') are absent.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — computational peptide/subunit vaccine design via epitope prediction — with distinct triggers; minimal conflict risk with sibling skills (the body further disambiguates against hla-immunogenomics and antibody-engineering).	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: mims-harvard/ToolUniverse
Path: plugin/skills/tooluniverse-vaccine-design/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.