dr-cook

Orchestrate academic research pipelines across literature review, writing, and analysis.

7|1|Updated Mar 9, 2026
One-click install
npx skills add https://github.com/wen-chen/dr-cook --skill dr-cook
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: dr-cook
Source: https://github.com/wen-chen/dr-cook/tree/main
Command: npx skills add https://github.com/wen-chen/dr-cook --skill dr-cook

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

Dr. Cook is a modular AI skill suite for academic researchers. It orchestrates end-to-end research tasks—ranging from literature review and gap analysis to manuscript writing, peer review, and bioinformatics analysis—without requiring users to re-enter context between steps. By loading SKILL.md frontmatter instructions and domain-specific references, it enables reproducible pipelines in bilingual English/Chinese contexts.

Core Features & Use Cases

  • 16 independent modules that can run standalone or be chained into pipelines.
  • A central router class that classifies intent and loads the correct module automatically.
  • A standardized context_output data contract that preserves context across modules, so users don’t have to paste content repeatedly.
  • Preset pipelines for common workflows (grant writing, manuscript submission, reviews) and free-form custom module sequences.
  • Domain-aware defaults and bilingual support for English/Chinese input.
  • Direct module invocation (dr-cook:<module>) to bypass the router when needed.
  • Easy installation: clone into Claude Code skills directory and start using immediately.

Quick Start

  1. Clone the repository into Claude Code’s skills directory.
  2. Use the top-level command dr-cook to see available modules and pipelines, or invoke a specific module like dr-cook:paper-writer.

Frequently Asked Questions about dr-cook

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate literature review and manuscript writing without re-entering context in Claude Code?▼

Academic research workflows can be automated using a modular AI skill suite that preserves context across stages. It loads domain-specific references to chain literature reviews, gap analysis, and manuscript writing without re-entering context.

Can I run bioinformatics data analysis and grant writing pipelines in a bilingual environment?▼

Bilingual bioinformatics data analysis and grant writing pipelines are supported natively. The suite provides domain-aware defaults for English and Chinese inputs, enabling reproducible end-to-end research automation.

How to chain multiple academic research modules into a custom pipeline?▼

To chain academic research modules, use the central router to classify intent and load modules automatically. A standardized context_output data contract passes information between stages, allowing custom module sequences for grant writing or manuscript submission.

Does this modular research workflow suite require specific dependencies or external libraries?▼

This modular research workflow suite requires no external dependencies. You simply clone the repository into the Claude Code skills directory to install and start orchestrating end-to-end research tasks immediately.

What is the best way to bypass the router and invoke a specific module for peer review?▼

The best way to bypass the router for peer review is direct module invocation. You can call specific modules like dr-cook:paper-writer directly to execute targeted academic tasks without automatic intent classification.

Why does context need to be preserved across different academic research stages?▼

Context must be preserved across academic research stages to prevent manual data re-entry between literature reviews, gap analysis, and writing. A shared context schema enables pipeline automation and ensures consistent sum of context retention.