medical-research-skills

Medical literature search strategy generator. Given a user's natural-language description (e.g., meta-analysis topic, PICOS elements, research question), automatically extract medical entities (disease, intervention, population, outcomes) and generate professional search queries for seven major databases (PubMed, Cochrane, Embase, Web of Science, CNKI, Wanfang, VIP). Useful for developing search strategies for systematic reviews and meta-analyses.

Generate leave-one-out sensitivity analysis plots for meta-analysis. Input is a CSV file containing meta-analysis data; outputs are a sensitivity forest plot (PNG) and a sensitivity data table (CSV) showing pooled effect estimates after excluding each study in turn.

Generates Meta-Analysis research titles based on user keywords, utilizing PubMed search results if available, or creative generation otherwise. Use when the user wants to brainstorm or generate titles for a meta-analysis, specifically starting from keywords or a topic.

Detects methodological gaps across study design, analysis, validation, bias control, reproducibility, and implementation readiness within a biomedical research area. Use this skill when a user wants to identify what current studies are still methodologically missing, which weaknesses are most consequential, and what upgrade path would produce a stronger next-step study. Always separate design gaps, analysis gaps, validation gaps, and reproducibility gaps. Never treat technical complexity as methodological rigor.

Extract experimental methods from one or more papers into a structured protocol-oriented summary; use when comparing methods across studies or drafting reproducible procedures.

Reverse-engineers the methods section of a biomedical paper into a structured, reproducible workflow. Use this skill when a user wants to understand how a study was actually executed, extract data sources, inclusion/exclusion logic, preprocessing, analytical sequence, software/tools, validation path, and critical parameters, or build a replication checklist from a paper, abstract, DOI, PMID, title, screenshot, or partial methods text. Do not treat this as generic summarization. Focus on reconstructing the operational method pipeline, surfacing missing reproducibility details, and distinguishing explicitly reported steps from inferred or unresolved ones. Never fabricate references, methods details, identifiers, software versions, parameters, datasets, or validation steps.

Turns your protocol and analysis workflow into publication-ready Methods text. Use when writing or revising the Methods section of a biomedical manuscript, ensuring it complies with reporting guidelines (CONSORT, STROBE, PRISMA, TRIPOD), matches what is in the Results section, and satisfies journal-specific word limits and declarations. Also triggers on "write my methods", "revise my methods section", "how to report my statistics", "what do I need to include in methods for [study type]", or "make my methods CONSORT-compliant".

Write and revise the Methods section of research papers to ensure reproducibility; use when preparing an IMRAD manuscript or responding to journal/reporting-guideline requirements (e.g., CONSORT/STROBE/PRISMA).

Interpret Alpha and Beta diversity metrics from 16S rRNA sequencing results.

Add accurate, publication-ready scale bars to microscopy images given pixel-to-unit calibration data.

Generate mindmaps locally/offline with native HTML/CSS/JS (no external libraries); use when you need to parse Plain Text node structures or map LLM outputs into an on-device visualization.

Organize requirements into Markdown/JSON mind map structures; use when you need a hierarchical outline for mind map tools (e.g., XMind, ProcessOn, FreeMind) or for documentation planning.

Generate offline interactive mindmap HTML and convert Markdown, outlines, meeting notes, chapter structures, or JSON trees into markmap-compatible format. Use when organizing long text into mindmaps, converting meeting notes to mindmap pages, generating final HTML via markmap-cli, or adding browsable mindmaps to deliverables.

Generate 3D animation scripts and lay explanations for drug mechanisms.

Use when assessing how well a survival model's predicted probabilities agree with observed outcomes by fitting a Cox model and generating bootstrap calibration curves at one or more prediction horizons from a clinical CSV file. NOT for: nomogram construction, univariate Cox screening, ROC analysis, or decision-curve analysis.

Generates academic reviews for molecules in diseases using PubMed research. Invoke when user needs biomedical literature review with Vancouver citation format.

Generate publication-quality sequence logos for DNA or protein motifs.

Generates complete Mendelian Randomization + single-cell transcriptomics (scRNA-seq) research designs from a user-provided direction. Always use this skill whenever a user wants to design, plan, or build a study combining MR and single-cell data — even if phrased as "help me write a paper on X", "design a bioinformatics study for Y", or "I want to study Z using MR and scRNA". Covers five study patterns (mechanism gene-set, key-cell, candidate-gene reverse validation, exposure-disease-cell triangulation, translational biomarker) and always outputs four workload configs (Lite / Standard / Advanced / Publication+) with recommended primary plan, step-by-step workflow, figure plan, validation strategy, minimal executable version, publication upgrade path, and a strictly verified reference literature retrieval layer with real references only.

Collects candidate biomedical literature across multiple databases, adapts search logic by database, preserves source metadata, and organizes results into a structured, screening-ready candidate pool. Always use this skill when a user wants cross-database literature collection, search strategy construction, candidate paper aggregation, or first-pass evidence organization before deduplication, screening, layered reading, or review planning. Requires real and verifiable literature records only. Every formal literature item must include a real link and DOI when available; never fabricate citations, titles, authors, years, journals, abstracts, PMIDs, or DOIs. If a DOI is unavailable or cannot be verified, state that explicitly rather than inventing one.

Designs complete research plans that integrate clinical variables with multi-omics data from a user-provided biomedical direction. Always use this skill whenever a user wants to design, scope, or structure a study that combines clinical variables with transcriptomics, proteomics, metabolomics, epigenomics, or related omics layers for mechanism interpretation, biomarker development, risk stratification, treatment-response analysis, or translational use. It should define the clinical use case, alignment across data layers, feature-reduction and fusion logic, modeling route, mechanism-interpretation layer, validation ladder, and four workload configurations (Lite / Standard / Advanced / Publication+). Never fabricate datasets, accession numbers, sample counts, metadata completeness, platform coverage, literature references, PMIDs, DOIs, or validation status. Always include the mandatory Dataset Disclaimer immediately before any workflow section that mentions datasets or public resources.

Assemble 6 sub-figures (A–F) into a high-resolution composite figure with consistent labels, padding, and publication-ready DPI.

Integrates multiple news sources into a single, cohesive press release using an inverted pyramid structure and AP style. Use when you have raw news content and a topic, and need a professional press release.

Predict neoantigens that may be recognized by the immune system based.

Draft professional follow-up emails to contacts made at conferences - not too pushy, but memorable.

Generates complete network toxicology + molecular docking research designs from a user-provided toxicant and disease/phenotype. Always use this skill when users want to investigate how an environmental toxicant, endocrine disruptor, heavy metal, food contaminant, pharmaceutical residue, or consumer product chemical may contribute to a disease through shared molecular targets, hub genes, pathways, and docking evidence. Trigger for:"network toxicology study", "toxicology mechanism paper", "target prediction + PPI + docking", "environmental pollutant and disease mechanism", "hub genes and docking for toxicant", "Lite/Standard/Advanced toxicology plan", "CTD + SwissTargetPrediction + GeneCards + STRING", "CB-Dock2 docking study", "triclosan/BPA/cadmium/PFAS + disease". Also triggers for Chinese phrasings:"网络毒理学研究设计"、"毒物机制论文"、"靶点预测+PPI+对接"、"环境污染物与疾病机制". Trigger even for casual phrasings like "I want to study how chemical X affects disease Y" or "help me design a toxicology paper". Always output four workload configurations (Lite / Standard / Advanced / Publication+) with a recommended primary plan, step-by-step workflow, figure plan, validation strategy, minimal executable version, and publication upgrade path.