CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

70

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is tooluniverse-metagenomics-analysis in mims-harvard/ToolUniverse

SKILL.md
Quality
Evals
Security

Quality

Content

82%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 tightly written, operationally rich skill body that front-loads tool names, parameter gotchas, and quality/evidence thresholds without padding. The main gaps are the absence of an explicit inter-phase validation checkpoint and a complete end-to-end runnable example.

Suggestions

Add an explicit validation/verification step in the workflow (e.g., 'Before Phase 5, confirm each MAG meets at least Medium quality tier via CheckM metrics') to push workflow_clarity toward 5.

Include one short end-to-end example showing a full tool-call sequence for a representative query (e.g., an IBD amplicon study) to lift actionability from concrete signatures to fully executable guidance.

Consider splitting the dense Key Phase Notes table (KEGG pathways) or the quality-tier thresholds into a reference file if the skill grows, to keep the overview scannable.

DimensionReasoningScore

Conciseness

Lean and dense throughout — tables, terse phase notes, and operational gotchas (MeSH terms, KEGG pathway IDs, CheckM thresholds) with no padding or explanation of concepts Claude already knows; every section earns its tokens, matching the top anchor.

5 / 5

Actionability

Provides concrete, copy-paste-ready guidance at the tool-call level ('GTDB_search_taxon(operation="search_taxon", query=name)', 'kegg_search_pathway(keyword=...) NOT query', 'study_title="*IBD*"', exact MeSH terms and quality thresholds); not a 5 because there is no full end-to-end executable example, only inline tool signatures.

4 / 5

Workflow Clarity

A clear 8-phase sequence (Phase 0-7) each mapped to named tools, plus an Edge Cases & Fallbacks section giving error recovery ('If ENA fails, fall back to MGnify'); not a 5 because there are no explicit validation checkpoints between phases (e.g., confirm genome-quality tier before interpretation).

4 / 5

Progressive Disclosure

Well-organized into clearly headed sections (Core Databases, Workflow, Key Phase Notes, Edge Cases, Limitations) with no nested references and content kept at overview level; no bundle files exist so references cannot be evaluated, and the body slightly exceeds the <50-line simple-skill threshold, keeping it just below 5.

4 / 5

Total

17

/

20

Passed

Description

87%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, third-person description that names a distinctive domain, concrete capabilities, and the backing databases, with an explicit 'Use for amplicon/shotgun metagenomics study analysis' trigger. Minor room to add more user-natural synonyms and slightly more concrete action verbs.

DimensionReasoningScore

Specificity

Names the domain plus four concrete capabilities ('taxonomic classification, genome quality assessment, biome-clinical phenotype linkage, and pathway interpretation') and four specific databases, listing several specific actions with only minor abstraction gaps; not a 5 because the action phrases are analytic categories rather than the fully concrete verbs seen in the top anchor.

4 / 5

Completeness

Explicitly answers both what ('Covers taxonomic classification, genome quality assessment, biome-clinical phenotype linkage, and pathway interpretation') and when ('Use for amplicon/shotgun metagenomics study analysis') with concrete trigger phrases, matching the top anchor's structure; clearly above 4 whose 'when' is only weakly specified.

5 / 5

Trigger Term Quality

Includes natural domain terms a user would say ('microbiome', 'metagenomics', 'amplicon/shotgun metagenomics study analysis') with the amplicon/shotgun synonym pair; not a 5 because common variations like '16S', 'shotgun sequencing', or 'microbiome study' are absent.

4 / 5

Distinctiveness Conflict Risk

A clear niche (microbiome/metagenomics) anchored to distinctive tooling (MGnify, GTDB, ENA, EuropePMC) with specific triggers, giving minimal conflict risk with other skills; well above 4.

5 / 5

Total

18

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
mims-harvard/ToolUniverse
Reviewed

Table of Contents

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.