mims-harvard/tooluniverse-metagenomics-analysis
skills/tooluniverse-metagenomics-analysis/SKILL.md
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.
$ install --global
skillsauthnpx skillsauth add mims-harvard/tooluniverse tooluniverse-metagenomics-analysisInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 26, 2026, 7:13 AM13.6s1 file scanned
SKILL.md
- name:
- tooluniverse-metagenomics-analysis
- description:
- 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.
- disable-model-invocation:
- true
Metagenomics & Microbiome Analysis
Integrated pipeline for exploring microbiome studies, classifying taxa, assessing genome quality, linking microbial composition to clinical phenotypes, and interpreting findings through pathway analysis and literature context.
Guiding principles:
- Study context first -- understand biome, sequencing method, and metadata before diving into taxa
- Taxonomic consistency -- GTDB taxonomy as reference standard; reconcile NCBI where needed
- Genome quality matters -- CheckM completeness/contamination thresholds determine trustworthy MAGs
- Interpretation over enumeration -- explain what taxa mean for the biological question
- English-first queries -- use English terms in tool calls
LOOK UP, DON'T GUESS
When uncertain about any scientific fact, SEARCH databases first rather than reasoning from memory.
COMPUTE, DON'T DESCRIBE
When analysis requires computation (statistics, data processing, scoring, enrichment), write and run Python code via Bash. Don't describe what you would do — execute it and report actual results. Use ToolUniverse tools to retrieve data, then Python (pandas, scipy, statsmodels, matplotlib) to analyze it.
Core Databases
| Database | Best For | |----------|---------| | MGnify | Processed metagenomics studies, taxonomic/functional results | | GTDB | Standardized bacterial/archaeal taxonomy, species-level resolution | | GMrepo | Gut species-to-human-health phenotype associations | | ENA | Raw sequencing datasets and study metadata | | KEGG | Pathway mapping for microbial functional annotations | | PubMed/EuropePMC | Published microbiome-disease studies | | CTD | Chemical-microbiome-disease relationships |
Workflow
Phase 0: Parse query → organism, biome, phenotype, or accession
Phase 1: Study Discovery → MGnify_search_studies, ENAPortal_search_studies
Phase 2: Taxonomic Classification → GTDB_search_genomes, GTDB_get_species, GTDB_search_taxon
Phase 3: Genome Quality → MGnify_search_genomes, MGnify_get_genome (CheckM metrics)
Phase 4: Functional Annotation → MGnify GO terms + KEGG pathway mapping
Phase 5: Clinical Associations → GMrepo species-phenotype links
Phase 6: Literature → PubMed/EuropePMC + CTD gene-disease
Phase 7: Interpretation & Report Synthesis
Key Phase Notes
Phase 1: ENA requires structured queries (e.g., study_title="*IBD*"), not free text. If ENA fails, fall back to MGnify.
Phase 2: GTDB uses its own naming (e.g., s__Bacteroides_A fragilis vs NCBI Bacteroides fragilis). Always note discrepancies. Use GTDB_search_taxon(operation="search_taxon", query=name).
Phase 3 - Quality tiers (MIMAG):
- High: >= 90% complete, <= 5% contamination, rRNA + >= 18 tRNAs
- Medium: >= 50% complete, <= 10% contamination
- Low: below medium -- flag but don't exclude
Phase 4 - Functional interpretation: Don't just list GO terms. Connect to biology:
| Functional Category | Key KEGG Pathways | Significance | |---|---|---| | SCFA production | map00650, map00640 | Gut barrier, anti-inflammatory | | LPS biosynthesis | map00540 | Pro-inflammatory, endotoxemia | | Bile acid metabolism | map00120 | Fat absorption, FXR signaling | | Tryptophan metabolism | map00380 | Serotonin, AhR, immune | | Vitamin biosynthesis | map00730/740/760 | Host nutritional contribution |
Use kegg_search_pathway(keyword=...) (NOT query). Pathway IDs need organism prefix (hsa, ko, eco), NOT bare map.
Phase 5: GMrepo uses MeSH terms: "Crohn Disease" not "IBD", "Colitis, Ulcerative" not "UC", "Colorectal Neoplasms" not "colorectal cancer". Try NCBI taxon IDs if species name fails.
Phase 6 - Evidence grading:
- Strong: Meta-analysis or >5 studies, consistent direction
- Moderate: 2-5 studies consistent, or 1 large cohort
- Preliminary: Single study or conflicting
- Mechanistic only: In vitro/animal, no human epidemiology
Phase 7 - Report: Executive summary, study landscape, GTDB taxonomy, functional interpretation (not GO term lists), clinical relevance with evidence grades, mechanistic model, genome catalog with quality tiers, data gaps.
Edge Cases & Fallbacks
- Taxon not in GTDB: Try partial search or fall back to MGnify (NCBI taxonomy)
- No GMrepo data: Normal for non-gut organisms; use literature
- GMrepo 0 results: Use formal MeSH terms or NCBI taxon IDs
- No KEGG match: Check MetaCyc or literature
Limitations
- GMrepo: Gut-only
- GTDB: Bacteria/Archaea only
- ENA: Raw data only, strict query syntax
- No sequence analysis: Queries databases, not raw FASTQ/FASTA
Related Skills
mims-harvard/tooluniverse-product-safety-surveillance
tools
VerifiedTrustedCommunity
Post-market safety surveillance and recall/adverse-event RETRIEVAL across the full spectrum of FDA-regulated products that are NOT covered by the drug-AE signal skills: medical devices, food / dietary supplements / cosmetics, veterinary drugs, and drug supply (shortages). Orchestrates openFDA endpoints (MAUDE device adverse events + device recalls + 510(k), CAERS food/supplement/ cosmetic adverse events, veterinary adverse events, drug shortages, and cross-product enforcement/recall reports). USE WHEN the user asks: "are there adverse events for [device / pacemaker / infusion pump / insulin pump]", "device recalls for [firm/product]", "supplement / vitamin / cosmetic adverse reactions", "is [drug] in shortage", "what injectables are on shortage", "veterinary / animal adverse events for [drug] in [dog/cat/horse]", "food recall for listeria", "MAUDE report for [device]", "CAERS reactions for [brand]". DO NOT USE for drug adverse-event SIGNAL detection or disproportionality (PRR / ROR / IC) or drug-AE association scoring — that is `tooluniverse-pharmacovigilance` / `tooluniverse-adverse-event-detection`. This skill is multi-product surveillance and retrieval, not drug-AE statistical signal mining.
1,446SKILL.mdUpdated Jun 13, 2026
mims-harvard/skills/tooluniverse-phewas
tools
VerifiedTrustedCommunity
--- name: tooluniverse-phewas description: Cross-ancestry / cross-biobank phenome-wide association (PheWAS) and replication. Given ONE variant (rsID) or ONE gene, look up every phenotype it associates with across European/UK (UKB-TOPMed), Finnish (FinnGen), Japanese (BioBank Japan), and Taiwanese (TPMI) biobanks, plus exome-wide gene-burden PheWAS (Genebass), then judge whether an association replicates across ancestries or is population-specific. Use whenever the user asks "what else is this va
1,446SKILL.mdUpdated Jun 13, 2026
mims-harvard/tooluniverse-natural-product-dereplication
tools
VerifiedTrustedCommunity
Dereplicate a putative natural product and assign its chemical taxonomy. Use to answer "is [compound] a known natural product", "what microbe/organism produces [compound]", "what chemical class is [compound]", "dereplicate this metabolite (by formula/exact mass/InChIKey/SMILES)", or "classify this molecule into ChemOnt". Searches NPAtlas for known microbial natural products (producing organism + literature reference), assigns the ChemOnt kingdom→superclass→class→subclass hierarchy via ClassyFire, resolves systematic IUPAC names to structure via OPSIN, and cross-references identity in PubChem. NOT for general drug/compound identity or ADMET (use tooluniverse-chemical-compound-retrieval / tooluniverse-small-molecule-discovery) and NOT for metabolomics pathway/enrichment analysis (use tooluniverse-metabolomics skills).
1,446SKILL.mdUpdated Jun 13, 2026
mims-harvard/tooluniverse-microbial-genome-characterization
tools
VerifiedTrustedCommunity
Genome-ASSEMBLY discovery, QC, and replicon mapping for any organism (bacteria, archaea, fungi, and beyond) using NCBI Datasets. Resolves an organism name or taxid to assemblies, picks the reference/representative or best-quality assembly, pulls assembly QC metrics (total length, contig/scaffold N50, contig count, GC%, assembly level, RefSeq category), enumerates chromosomes and plasmids via per-replicon sequence reports, and compares candidate assemblies on quality. Use for "what genomes are available for [organism]", "assembly stats / N50 / GC content for [GCF_/GCA_ accession]", "how many plasmids does [strain] have", "compare assemblies for [species]", "find the reference genome for [taxon]", "is this assembly Complete Genome or just contigs". NOT for gene-level orthology/synteny (use tooluniverse-comparative-genomics), plant gene structure (use tooluniverse-plant-genomics), de novo assembly from raw reads (no tool exists), or taxonomy-only name/lineage lookups.
1,446SKILL.mdUpdated Jun 13, 2026