tooluniverse-metagenomics-analysis

Microbiome and metagenomics analysis using MGnify, GTDB taxonomy, ENA sequencing data, and EuropePMC literature. Covers taxonomic classification, genome quality assessment, biome-clinical phenotype linkage, and pathway interpretation. Use for amplicon/shotgun metagenomics study analysis.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

77%

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

The body is an information-dense, well-sequenced operational guide with strong concrete gotchas and an explicit phased workflow with fallbacks. Its main gaps are the absence of any fully executable code examples and a lack of file-level progressive disclosure for the reference material.

Suggestions

Add at least one complete, executable example — a Python block that calls ToolUniverse tools end-to-end with real parameters, or a full tool invocation — so the workflow moves from tool-name listings toward copy-paste-ready commands.

Move the detailed reference tables (KEGG pathway map, MIMAG quality tiers, MeSH-term mappings) into a references/ file such as references/pathways.md and link to it from SKILL.md, keeping the body as a lean overview with one-level-deep navigation.

Dimension	Reasoning	Score
Conciseness	Dense, domain-specific operational knowledge (GTDB naming 's__Bacteroides_A fragilis', ENA query syntax, MeSH conventions, kegg_search_pathway parameter gotchas) with no padding explaining concepts Claude already knows; every section earns its place. Not a 2 because there is no unnecessary explanation to tighten.	3 / 3
Actionability	Offers concrete specifics (tool names, parameters, KEGG IDs, MIMAG thresholds, MeSH terms), but the workflow block is a tool-name listing/pseudocode and there are no complete executable code blocks or copy-paste-ready commands. Not a 3 because it falls short of 'fully executable code/commands; copy-paste ready'; not a 1 because the inline guidance is specific and actionable.	2 / 3
Workflow Clarity	An explicit 8-phase sequence (Phase 0-7) with per-phase notes, fallback error-recovery ('If ENA fails, fall back to MGnify'), and grading checkpoints (MIMAG quality tiers, evidence grading) matches the 'clear sequence with explicit validation steps; feedback loops for error recovery; checklists' anchor. As a read-only analysis skill, the destructive/batch validation cap does not apply.	3 / 3
Progressive Disclosure	Sections are well-organized, but it is a single monolithic ~95-line file with no bundle/reference files and inline reference tables (KEGG pathways, quality tiers, MeSH mappings). It exceeds the 50-line safe-harbor for well-organized-sections-alone, and matches 'content that should be separate is inline'; not a 1 because internal navigation is clear and not deeply nested.	2 / 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 concise, specific, and third-person, with explicit capability enumeration and a clear 'Use for' trigger clause. It cleanly answers both what the skill does and when to invoke it with minimal jargon-only framing.

Dimension	Reasoning	Score
Specificity	Lists four concrete actions ('taxonomic classification, genome quality assessment, biome-clinical phenotype linkage, and pathway interpretation') alongside named tools, matching the 'lists multiple specific concrete actions' anchor; not a 2 because the action set is comprehensive rather than partial.	3 / 3
Completeness	Explicitly answers both what (the four capabilities) and when ('Use for amplicon/shotgun metagenomics study analysis'), satisfying the 'clearly answers both what AND when with explicit triggers' anchor.	3 / 3
Trigger Term Quality	Contains natural user terms — 'microbiome', 'metagenomics', 'amplicon/shotgun metagenomics study' — giving good coverage of what a researcher would actually say, despite some database-name jargon (MGnify, GTDB).	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (metagenomics/microbiome analysis with named databases) with distinct triggers, making it unlikely to fire for an unrelated skill.	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-metagenomics-analysis/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.