medical-research-skills

Comprehensive tool for computational mass spectrometry using PyOpenMS; use when you need to read/write MS formats (mzML/mzXML/MGF), run signal processing (smoothing/peak picking), detect isotope features, or perform peptide identification in proteomics/metabolomics workflows.

Genomic file toolkit. For reading/writing SAM/BAM/CRAM alignment files, VCF/BCF variant files, FASTA/FASTQ sequences, extracting regions, calculating coverage, suitable for NGS data processing pipelines.

Therapeutics Data Commons (PyTDC) for AI-ready therapeutic ML datasets and benchmarks; use it when you need standardized dataset loading, meaningful splits (e.g., scaffold/cold-start), and consistent evaluation for ADME/Toxicity/DTI/DDI or molecular optimization.

Predict challenging questions for presentations and prepare structured responses.

Designs QTL colocalization studies that connect eQTL, pQTL, sQTL, or related molecular QTL signals with GWAS loci. Always use this skill whenever a user wants to plan, scope, or structure a locus-level study asking whether a GWAS association and a molecular QTL association may reflect the same underlying causal signal. Covers locus definition, QTL/GWAS source architecture, ancestry and LD alignment, single-locus vs multi-locus strategy, candidate-gene prioritization, optional fine-mapping, linked MR/SMR follow-up, and functional annotation. Always output four workload configurations (Lite / Standard / Advanced / Publication+) with a recommended primary plan, stepwise workflow, method rationale, evidence hierarchy, figure plan, minimal executable version, and strictly verified literature guidance with no fabricated references. Never equate colocalization with causality proof, mediation proof, or automatic target validation. Always include the mandatory Dataset Disclaimer immediately before any workflow section that mentions datasets, repositories, consortia, or public resources.

Automated bias assessment for diagnostic accuracy studies using QUADAS-C criteria. Requires full text input.

Automates critical appraisal and quality assessment for research papers by analyzing text against established methodological standards (such as risk of bias tools, quality checklists, or reporting guidelines) and synthesizing a structured evaluation report. Use when you need to assess the methodological quality, internal validity, or reporting completeness of any type of study—including RCTs, observational studies, systematic reviews, qualitative research, or diagnostic accuracy studies.

Evaluates bias in medical literature (prognosis studies) using QUAPAS criteria. Use when the user wants to assess the quality or risk of bias of a medical paper text.

Use when creating radiology educational quizzes, preparing board exam questions, or studying medical imaging cases. Generates interactive quizzes with X-ray, CT, MRI, and ultrasound images for medical education.

Generates randomization sequences for RCTs including simple, blocked, and stratified allocation. Produces sealed randomization lists ready for allocation concealment.

Map patient symptoms to Human Phenotype Ontology terms for gene diagnosis.

Automates Risk of Bias 2 (ROB2) assessment for RCT papers by analyzing text against specific domains and synthesizing a report. Use when you need to assess the quality of a clinical trial paper or evaluate risk of bias.

Automates Risk of Bias 2 (ROB2) assessment for RCT papers by analyzing text against specific domains and synthesizing a report. Use when you need to assess the quality of a clinical trial paper or evaluate risk of bias.

Query the Reactome REST API for pathway content and enrichment analyses; use when you need curated pathway data, reaction details, or overrepresentation results for a gene list.

Scan reagent barcodes or IDs, log expiration dates, and generate multi-level alerts before reagent expiry to support laboratory inventory management.

Find validated alternative reagents based on literature citation data.

Designs a structured real-world evidence study using EHR, claims, or registry data, with explicit handling of time zero, eligibility windows, exposure definitions, outcome windows, censoring, confounding control, and target-trial-emulation logic. Use this skill when the user needs study-type design and protocol framing for an observational clinical study based on routine-care data. Do not invent database fields, follow-up completeness, linkage, coding validity, or causal identifiability.

Use rebuttal letter strategist for academic writing workflows that need structured execution, explicit assumptions, and clear output boundaries.

Helps faculty and mentors draft standardized recommendation letters for.

Automatically finds and ranks PubMed references for each sentence in scientific text; use when you need titles, DOIs, and brief recommendation reasons from the PubMed E-utilities API.

Checks whether manuscript references are accurately matched to claims, appropriately scoped, and not overextended, misquoted, or second-hand cited.

Based on user input, directly find relevant literature or automatically construct PubMed Boolean search queries to retrieve and filter references suitable for citation. Applicable for quickly finding high-quality evidence on specific topics and completing reference lists.

Multi-database literature search and search-strategy design that outputs structured, reproducible result lists; use when you need reference retrieval, systematic searching, review topic selection, or to construct a traceable search strategy.

One-click synchronization and standardization of reference formats in literature management tools, intelligently fixing metadata errors.

Generate medical referral letters with patient summary, reason for referral, key findings, and requested next steps; use when transferring care or communicating with another clinician or department.