tooluniverse-hla-immunogenomics

HLA gene-family analysis and MHC-peptide binding for transplant compatibility, vaccine epitope coverage, and cancer immunotherapy. Uses IMGT (HLA polymorphism), IEDB (epitope-MHC binding), UniProt (annotation), DGIdb (druggability). Use for HLA typing/imputation review, vaccine HLA coverage, and immunotherapy prediction biomarkers (HLA-LOH, neoantigen presentation).

Quality

81%

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

62%

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

The body presents a clear, well-sequenced multi-phase workflow with concrete tool specs and useful fallbacks, but it is a verbose monolith with no progressive disclosure and lacks worked executable examples that would make the guidance copy-paste ready.

Suggestions

Tighten the Reasoning Strategy and guiding-principles prose to domain-specific guidance only, and consolidate the binding-affinity thresholds so they appear once rather than across multiple sections.

Add at least one worked example per phase — a concrete filled-in tool call (with real input values) or a short executable Python snippet — to move guidance from concrete to copy-paste ready.

Move the per-phase tool reference tables and detailed threshold tables into one-level-deep reference files (e.g. references/tools.md, references/binding-thresholds.md) and link them from SKILL.md to introduce progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient (tables, ASCII workflow, tool specs) but the prose-heavy Reasoning Strategy and guiding-principles list explain framing that could be tightened, and binding-affinity guidance appears in both the workflow steps and a separate threshold table. It is not lean enough to earn a 3.	2 / 3
Actionability	Tool names with explicit Input/Output fields and concrete binding thresholds are actionable, but there are no worked or copy-paste-ready example calls or executable code snippets, leaving guidance concrete but incomplete.	2 / 3
Workflow Clarity	A clearly sequenced seven-phase pipeline (Phase 0–6) with an ASCII overview diagram, per-phase objectives/tools/steps, and an Edge Cases & Fallbacks section providing explicit error-recovery guidance ("If allele not found...", "BVBRC empty results...").	3 / 3
Progressive Disclosure	Content is well-organized into sections but the skill is a monolithic 233-line SKILL.md with no bundle files or one-level-deep references; the detailed tool documentation and phase details are candidates for split-out reference files that are not present.	2 / 3
	Total	9 / 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 distinctive — it states concrete capabilities, names the underlying databases, and gives explicit "Use for" trigger guidance covering the skill's main use cases. It uses appropriate third-person voice and avoids vague fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("HLA gene-family analysis", "MHC-peptide binding") across three specific application domains (transplant compatibility, vaccine epitope coverage, cancer immunotherapy), matching the anchor for listing several specific concrete actions.	3 / 3
Completeness	Explicitly answers both what ("HLA gene-family analysis and MHC-peptide binding... Uses IMGT, IEDB, UniProt, DGIdb") and when ("Use for HLA typing/imputation review, vaccine HLA coverage, and immunotherapy prediction biomarkers"), with an explicit trigger clause.	3 / 3
Trigger Term Quality	Includes natural niche keywords a user would actually say — "HLA typing/imputation", "vaccine HLA coverage", "neoantigen presentation", "HLA-LOH" — giving good coverage of natural terms rather than abstract jargon.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear HLA/immunogenomics niche with distinct triggers and named databases, 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-hla-immunogenomics/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.