mims-harvard avatar

Tooluniverse Expression Data Retrieval

This pulls gene expression and omics datasets from ArrayExpress and BioStudies, with fallback to GEO and other repositories when needed. You give it a gene, condition, or disease, and it returns experiment metadata, sample annotations, file listings, and quality scores based on replication and completeness. The workflow includes gene symbol disambiguation and a three-tier quality assessment system that flags single-replicate studies or sparse metadata. Useful when you need to find RNA-seq or microarray data for specific tissues or conditions before committing to a download. The skill prioritizes experiments with three or more biological replicates and complete raw plus processed data, which saves time filtering through low-quality submissions.

skills.sh installs
407
GitHub stars
1.8K
last updated
Aug 21, 2026

Install

$ npx -y skills add mims-harvard/tooluniverse --skill tooluniverse-expression-data-retrieval --agent claude-code

Installs into .claude/skills of the current project.

Files

Gene Expression & Omics Data Retrieval

Retrieve gene expression experiments and multi-omics datasets with disambiguation and quality assessment.

IMPORTANT: Always use English terms in tool calls. Respond in the user's language.

LOOK UP DON'T GUESS: Never assume which datasets exist or their accessions. Always search to confirm.

Domain Reasoning

Before retrieving, determine: organism, tissue, experimental design (case-control/time-series/dose-response). These affect which database to search and how to interpret results. RNA-seq provides wider dynamic range; microarray has extensive legacy data. Prioritize experiments with >=3 biological replicates, complete annotations, and both raw+processed data.

Workflow

Phase 0: Clarify (if ambiguous) → Phase 1: Disambiguate → Phase 2: Search & Retrieve → Phase 3: Report

Phase 0: Clarification (When Needed)

Ask ONLY if: gene name ambiguous, tissue/condition unclear, organism not specified. Skip for: specific accessions (E-MTAB-, E-GEOD-, S-BSST*), clear disease/tissue+organism, explicit platform requests.


Phase 1: Query Disambiguation

Sponsors

Details

Repository
github.com/mims-harvard/tooluniverse
Categories
Code Review & Quality, Data Science & ML
First seen
Jun 3, 2026

More from mims-harvard/tooluniverse

All 68
1patricio0312rev avatarcodebase-summarizerpatricio0312rev/skillsScans repository structure and generates comprehensive architecture documentation including system overview, entry points, module relationships, data flow diagr407skills.sh installs
2robdefeo avatarpara-second-brainrobdefeo/agent-skillsUse this skill when the user wants to organize, classify, or maintain a PARA-method second brain. Triggers include asking where to file something, distinguishin407skills.sh installs
3sanky369 avatardirect-response-copysanky369/vibe-building-skillsWrite copy engineered to drive one specific action — landing pages, sales pages, opt-in pages, ads, promotional emails — using an eight-part direct-response arc406skills.sh installs
4block avatarfrontend-designblock/agent-skillsCreate distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applicat405skills.sh installs
5mindfold-ai avatartrellis-metamindfold-ai/trellisUnderstand and customize the local Trellis architecture inside a user project. Use when modifying .trellis plus platform hooks, settings, agents, skills, comman405skills.sh installs
6alirezarezvani avatareu-ai-act-specialistalirezarezvani/claude-skillsEU AI Act (Regulation (EU) 2024/1689) operational compliance for compliance teams. Three Article-level decisions: (1) What's the risk tier of this AI system — p403skills.sh installs