aperivue/medsci-skills

Clinical AI model research engineering: choose a paper-grounded architecture, scaffold a reproducible PyTorch training repo, validate the model's split and validation design, document it (Model Card / Datasheet), and evaluate models or LLMs/MLLMs on clinical tasks. Integrates MONAI / nnU-Net, never replaces them.

🔌medsci-submission🔌Plugin

Submission packaging, journal recommendation and profiling, institutional form filling (ICMJE COI, IRB), and grant proposals.

🔌medsci-data🔌Plugin

Study design and validity review, literature-grounded variable operationalization, sample-size planning, data cleaning, de-identification, codebook generation, and dataset versioning.

🔌medsci-literature🔌Plugin

Literature search with anti-hallucination citation verification, full-text retrieval, Zotero/Obsidian sync, and reference-integrity audits.

🔌medsci-presentation🔌Plugin

Academic presentation and PPTX building, PDF/document rendering, environment setup, and skill publishing.

🔌medsci-review🔌Plugin

Pre-submission self-review, peer-review drafting, and reporting-guideline compliance audits against EQUATOR checklists.

🔌medsci-project🔌Plugin

Research orchestration, project intake and management, research-gap and meta-analysis topic discovery, and author-strategy analysis.

🔌medsci-writing🔌Plugin

IMRAD manuscript and IRB-protocol drafting, AI-pattern removal, AI-search optimization, and reviewer-response letters.

🔌medsci-analysis🔌Plugin

Reproducible statistical analysis, publication-ready figures, batch/cross-national/replication analysis, and meta-analysis synthesis.

🏪Marketplaces1

🏪Aperivue/medsci-skills🏪Marketplace

Agent Skills for medical research — literature search, reporting-guideline & citation checks, statistics, publication figures, submission. Works with Claude Code, Codex, Cursor & GitHub Copilot. Built by a physician-researcher, tested on real publications. MIT.

Back to Home