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

86%

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

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable and well-structured with a real, correctly-referenced bundle script, but it is somewhat verbose and lacks explicit validation checkpoints in its multi-step workflow.

Suggestions

Tighten the Reasoning Strategy and concept-explaining tables (binding-affinity IC50, HLA supertype percentages) to operational thresholds only, removing immunology Claude already knows — this would lift conciseness.

Add explicit validation/verification checkpoints to the workflow, e.g. confirm prediction calls returned ranked peptides before assembly, and a check on population_coverage.py output before reporting coverage — this would lift workflow_clarity.

Consider moving the per-phase interpretation tables (binding thresholds, coverage targets, conservation tiers) into a reference file to keep SKILL.md a leaner overview while preserving the actionable tool calls inline.

Dimension	Reasoning	Score
Conciseness	The body is mostly operational and assumes Claude's competence, but the Reasoning Strategy paragraph and several concept-explaining asides (CD8/CD4 roles, IC50 binding tables, HLA supertype coverage percentages) restate immunology Claude already knows and could be tightened.	2 / 3
Actionability	Provides fully parameterized, copy-paste-ready tool calls (e.g. IEDB_predict_mhci_binding with allele/method/length, iedb_search_mhc with filters/select/limit, population_coverage.py with expected JSON output) plus interpretation tables.	3 / 3
Workflow Clarity	Phases 0-5 are clearly sequenced with a pipeline diagram, but validation/verification checkpoints and feedback loops are absent for the batch population-coverage and conservation steps, which caps workflow clarity per the rubric.	2 / 3
Progressive Disclosure	Well-organized sections with a clearly signaled, one-level-deep bundle reference (scripts/population_coverage.py, verified to exist) whose coverage math is appropriately split out rather than inlined; no nested reference chains.	3 / 3
	Total	10 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, complete, and well-triggered, naming concrete pipeline actions and an explicit 'Use for' clause with natural terms. It is clearly distinct from sibling skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — MHC-I/MHC-II epitope prediction, population HLA coverage optimization, B-cell epitope identification, conservation analysis, multi-epitope construct design, and immunogenicity assessment — matching the 'multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both what (the computational pipeline actions) and when (an explicit 'Use for ...' trigger clause), satisfying the 'both what AND when with explicit triggers' anchor.	3 / 3
Trigger Term Quality	The 'Use for vaccine epitope prediction, HLA allele coverage, multi-epitope construct design, and immunogenicity assessment' clause gives good coverage of natural phrases a user would say, with several relevant variations.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche (computational vaccine candidate design via epitope prediction) with distinct triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 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: 089eb8e

Reviewed: about 9 hours 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.