medical-research-skills

A skill for performing sequence alignment using NCBI BLAST API. Supports nucleotide and protein sequence comparison against major biological databases.

Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Feature importance, dependence plots, interaction effects, and fairness analysis for any black-box model.

Generate structured shift handover summaries from EHR records, highlighting critical events, vital sign changes, and pending tasks for incoming clinical staff.

Generate popular science short video scripts based on topic, duration, and style. Invoke when the user needs to create scripts for short science videos.

Programmatically query public single-cell study metadata from the Broad Institute Single Cell Portal REST API when you need to search and filter datasets by organism, tissue, disease, or cell type without an API key.

Designs complete single-cell research plans from a user-provided biomedical direction. Always use this skill whenever a user wants to design, scope, or structure a single-cell study — including disease-focused, mechanism-focused, biomarker-focused, translational, perturbation-inspired, or validation-aware projects. It should define the research question, choose the best-fit study pattern, recommend sample grouping logic, suggest reference datasets as examples only, specify the core analysis modules, propose a validation ladder, and output four workload configurations (Lite / Standard / Advanced / Publication+). Never fabricate datasets, sample metadata, accession numbers, cohort availability, cell-type labels, external validation resources, or literature references. Always include the mandatory Dataset Disclaimer immediately before any workflow section that mentions datasets or public resources.

Generates complete single-compound network-toxicology research designs from one exposure, one disease or toxic phenotype, and a validation direction. Use when a study centers on one compound–one disease link and needs target collection, overlap construction, enrichment, PPI hub prioritization, docking, optional transcriptomic cross-check, and conservative mechanistic synthesis. Covers five study patterns and always outputs Lite / Standard / Advanced / Publication+ with a recommended primary plan, stepwise workflow, figure plan, validation hierarchy, minimal executable version, publication upgrade path, and strictly verified literature retrieval.

Generates complete reference-grounded single-drug adverse-effect network-pharmacology research designs from a user-provided drug, adverse event, and desired evidence depth. Always use this skill when a user wants to design, plan, or upgrade a conventional network-pharmacology study centered on one fixed drug and one fixed adverse-effect endpoint, using drug-target prediction, adverse-event target collection, overlap analysis, PPI hub prioritization, enrichment interpretation, molecular docking, and optional orthogonal transcriptomic or literature validation. Covers five study patterns (canonical hub-first, cardiotoxicity or electrophysiology-oriented, immune-inflammatory adverse effect, organ-toxicity pathway context, translational validation) and always outputs four workload configs (Lite / Standard / Advanced / Publication+) with a recommended primary plan, dependency/evidence map, step-by-step workflow, figure plan, validation strategy, minimal executable version, publication upgrade path, verified-reference pack, and self-critical risk review.

Generates complete reference-grounded single-drug adverse-effect network-pharmacology research designs from a user-provided drug, adverse event, and desired evidence depth. Always use this skill when a user wants to design, plan, or upgrade a conventional network-pharmacology study centered on one fixed drug and one fixed adverse-effect endpoint, using drug-target prediction, adverse-event target collection, overlap analysis, PPI hub prioritization, enrichment interpretation, molecular docking, and optional orthogonal transcriptomic or literature validation. Covers five study patterns (canonical hub-first, cardiotoxicity or electrophysiology-oriented, immune-inflammatory adverse effect, organ-toxicity pathway context, translational validation) and always outputs four workload configs (Lite / Standard / Advanced / Publication+) with a recommended primary plan, dependency/evidence map, step-by-step workflow, figure plan, validation strategy, minimal executable version, publication upgrade path, verified-reference pack, and self-critical risk review.

Generates complete FAERS pharmacovigilance study designs for one-drug whole-profile safety mapping using signal detection, subgroup analysis, onset/seriousness characterization, and conservative label-gap interpretation.

Generates complete conventional single-gene oncology research designs from a user-provided cancer context, target gene, and validation direction. Use when a study centers on a fixed candidate gene and needs expression, prognosis, clinicopathologic association, functional interpretation, immune context, genomic or epigenetic context, optional drug-response hypotheses, and orthogonal validation. Covers five study patterns and always outputs Lite / Standard / Advanced / Publication+ with a recommended primary plan, stepwise workflow, figure plan, validation hierarchy, minimal executable version, publication upgrade path, and strictly verified literature retrieval.

A comprehensive auditor for any agent skill — including Manus, OpenClaw/ClawHub, Claude, LobeHub, or custom SKILL.md-based skills. Use this skill whenever a user wants to evaluate, audit, review, score, or quality-check an agent skill before publishing, updating, or deploying. Covers two hard veto gates (structural redlines + research integrity redlines), static quality scoring across 25 criteria (ISO 25010 + OpenSSF + Agent), dynamic test input generation, multi-mode execution testing, multi-layer output evaluation with five specialized category rubrics (Evidence Insight / Protocol Design / Data Analysis / Academic Writing / Other), a Research Veto that applies to all four research categories, human eval viewer generation, actionable P0/P1/P2 optimization recommendations, and automatic skill improvement that outputs a polished, production-ready SKILL.md. Also use whenever a user says "audit my skill", "evaluate my skill", "improve my skill", or wants a corrected version after evaluation.

Structures research progress into focused and actionable slides for lab meetings or project reviews without inventing missing content.

Generate professional slide-deck SVG images (not PPTX/PDF) when users ask to “create slides / slide deck / PPT” and need image outputs.

Use smart journal monitor for evidence insight workflows that need structured execution, explicit assumptions, and clear output boundaries.

Analyze data with `smiles-de-salter` using a reproducible workflow, explicit validation, and structured outputs for review-ready interpretation.

Generates high-quality promotional soft articles with structured outlines, tailored introductions, and optimized titles based on product info and hot topics. Use when you need to write promotional content, "soft articles" (), or marketing copy that integrates product highlights with current trends, news, or industry insights.

Write GCP-compliant standard operating procedures for laboratory, clinical, or research workflows; use when a reproducible SOP with roles, steps, and control points is required.

Map spatial transcriptomics data from 10x Genomics Visium/Xenium onto.

Spreadsheet processing and analysis for CSV/Excel; trigger when users ask to merge/clean tabular data, run statistics, add/edit Excel formulas, apply formatting, generate charts, or force workbook recalculation.