A collection of Claude Code skills designed to automate common academic research workflows. It offers specialized agents for generating literature reviews, transforming papers into slide decks, and drafting PhD research proposals, aiming to significantly accelerate research output for academics and researchers.

How It Works

The repository provides three distinct skills: medical-imaging-review employs a structured 7-phase workflow with domain-specific templates and Zotero integration for systematic literature reviews on medical imaging AI. paper-slide-deck automates the creation of presentation slides from academic PDFs by detecting figures, analyzing content, and leveraging AI (Gemini API) for generation across 17 visual styles. research-proposal assists in crafting PhD proposals using a 5-phase workflow, emulating Nature Reviews' academic writing style, integrating literature from multiple sources (WebSearch, Zotero, arXiv, PubMed), and supporting both English and Chinese.

Quick Start & Requirements

Installation involves copying the desired skill folder (e.g., medical-imaging-review) into your Claude Code skills directory (~/.claude/skills/ or .agents/skills/). Key dependencies include the Gemini API for AI-powered slide generation in the paper-slide-deck skill, and Zotero integration for reference management in the medical-imaging-review and research-proposal skills. Specific Python/TypeScript scripts are utilized within the paper-slide-deck skill for figure detection and slide generation.

Highlighted Details

• Medical Imaging Review: Features a systematic 7-phase workflow, domain-specific templates for various medical imaging areas, standardized academic writing with hedging language, quality checklists, and Zotero integration.
• Paper Slide Deck: Offers automatic figure detection from PDFs, smart figure-to-slide mapping, 17 distinct visual styles, and AI-driven slide generation via the Gemini API, with PPTX/PDF export capabilities.
• Research Proposal: Implements a 5-phase workflow for PhD proposals, adheres to Nature Reviews-style academic writing, integrates literature from multiple sources, supports bilingual (English/Chinese) output, and adapts to STEM, Humanities, and Social Sciences domains.

Maintenance & Community

No specific details regarding maintainers, community channels (like Discord/Slack), or a public roadmap are provided in the README.

Licensing & Compatibility

The project is released under the MIT License, which generally permits broad use, modification, and distribution, including for commercial purposes, with minimal restrictions.

Limitations & Caveats

The skills are explicitly designed for "Claude Code," suggesting a dependency on the Claude AI platform or its specific execution environment, potentially limiting standalone use. The paper-slide-deck skill requires access to the Gemini API, which may involve API key management and associated costs. The README does not detail support for alternative AI models or platforms.