tooluniverse-microbiome-research

Microbiome research using MGnify, GTDB, ENA, OLS (ENVO biomes), and EuropePMC. Covers study discovery, taxonomic profiling, host-microbe interaction analysis, and biome-by-condition queries. Use for microbiome study selection, organism-environment associations, and clinical-microbiome literature review. Distinct from analytical workflow (use tooluniverse-metagenomics-analysis for that).

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 highly actionable with executable, real-accession examples and clear sequenced workflows backed by interpretation checkpoints. Its main weakness is conciseness and progressive disclosure: domain primers and the lengthy reasoning framework are inline in a single large file rather than split into reference material.

Suggestions

Move the Reasoning Framework / Interpretation Guidance / Evidence Grading sections into a separate reference file (e.g., REASONING.md) and link to it from SKILL.md to improve token economy and progressive disclosure.

Trim conceptual explanations of metrics Claude already knows (Shannon index, Bray-Curtis, UniFrac, PERMANOVA) and keep only tool-output-specific interpretation guidance.

Condense the Tips section, which repeats identifier prefixes already stated in the Key Identifiers section.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and action-oriented, but the Reasoning Framework and Interpretation Guidance sections teach domain concepts (Shannon index, Bray-Curtis/UniFrac, PERMANOVA thresholds, phylum-level ratios) that pad the token budget with microbiome primers.	2 / 3
Actionability	Provides fully executable Python snippets with real accessions (MGYS00006860, MGYA00612683), real biome lineages, concrete query syntax, and copy-paste-ready tool calls throughout Quick Start and all five workflows.	3 / 3
Workflow Clarity	Workflows are clearly sequenced (Quick Start 1-5, numbered dysbiosis strategy, data-type decision tree) with explicit "LOOK UP DON'T GUESS" checkpoints before interpretation; operations are read-only so no destructive validate-fix-retry loop is required.	3 / 3
Progressive Disclosure	Well-organized into clear navigable sections, but it is a large (~265-line) monolithic file with no bundle references; the Reasoning Framework and Interpretation Guidance content could be split into a separate reference file to improve token economy.	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, uses third-person voice, and explicitly covers both capabilities and use-when triggers with natural terms. It also clearly differentiates this skill from a sibling analytical-workflow skill, minimizing conflict risk.

Dimension	Reasoning	Score
Specificity	Names concrete actions across named data sources — "study discovery, taxonomic profiling, host-microbe interaction analysis, and biome-by-condition queries" — matching the multiple-specific-actions anchor.	3 / 3
Completeness	Explicitly answers both what ("Covers study discovery, taxonomic profiling...") and when via an explicit "Use for..." trigger clause, satisfying the both-what-and-when anchor.	3 / 3
Trigger Term Quality	Includes natural trigger phrases users would say ("microbiome study selection", "organism-environment associations", "clinical-microbiome literature review"), giving good coverage rather than just jargon.	3 / 3
Distinctiveness Conflict Risk	Explicitly distinguishes from a sibling skill ("Distinct from analytical workflow (use tooluniverse-metagenomics-analysis for that)") giving it a clear niche with non-conflicting triggers.	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-microbiome-research/SKILL.md
Commit: 089eb8e

Reviewed: about 8 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.