Galaxy-Dawn/claude-scholar

Semi-automated research assistant for academic research and software development. Supports Claude Code, Codex CLI, Kimi Code CLI, and OpenCode across ideation, coding, experiments, writing, and publication.

What it solves

Claude Scholar is a semi-automated research assistant designed to accelerate the heavy, repetitive, and structure-sensitive parts of academic research and software development. It specifically targets computer science and AI researchers who need a structured workflow to manage the transition from initial ideation and literature review to experimentation, analysis, and final publication, without replacing the human researcher's decision-making process.

How it works

The project provides a set of skills, agents, commands, and hooks that integrate with AI CLI tools like Claude Code, Codex CLI, Kimi Code CLI, and OpenCode. It implements a traceable research pipeline: question -> evidence -> experiment -> analysis -> claim -> writing.

Key technical components include:

  • Skill-based architecture: Specialized modules for tasks like literature review, scientific writing, and result analysis.
  • Integration ecosystem: Connects with Zotero (via MCP) for paper management and Obsidian for project knowledge management.
  • ** uma publication-grade production stack**: Uses pubfig and pubtab for creating scientific figures and tables.
  • Persistence layers: Uses on-disk planning and progress tracking to maintain state across complex tasks.

Who it’s for

  • Computer science and AI/ML researchers who balance coding, experiments, and paper writing.
  • Research engineers and graduate students seeking a structured workflow for academic projects.
  • Software-heavy academic projects that require reproducible project memory and CLI automation.

Highlights

  • Multi-CLI Support: Compatible with Claude Code, Codex CLI, Kimi Code CLI, and OpenCode.
  • Zotero & Obsidian Integration: Streamlines the flow from paper ingestion to a structured knowledge base.
  • Publication-Ready Artifacts: Integrated tools for generating professional scientific figures and tables.
  • Evidence-Gated Workflow: Implements a strict contract for evidence records and claim promotion to ensure scientific rigor.
  • Comprehensive Skill Set: Includes specialized agents for paper mining, bug detection, and scientific writing.

Related

  • Project
    luwill/research-skills

    A collection of Claude Code skills designed to automate academic research workflows, including exhaustive literature retrieval, verified proposal writing, and high-fidelity slide generation.

  • Project
    claesbackman/AI-research-feedback

    A collection of Claude Code skills that provide multi-agent academic reviews for research papers, grant proposals, and pre-analysis plans, including paper-code reproducibility checks.

  • Project
    K-Dense-AI/claude-scientific-writer

    An AI-powered research and writing tool that generates publication-ready scientific papers, grant proposals, and reports backed by real-time literature search and verified citations.

  • Project
    pedrohcgs/claude-code-my-workflow

    A fork‑ready framework that uses Anthropic Claude Code to automate academic tasks (slides, papers, data analysis, etc.) via specialised agents, a ten‑gate quality suite, and extensible skills; includes setup scripts, pre‑commit hooks, and detailed documentation.

  • Project
    Weizhena/Deep-Research-skills

    A structured research workflow for Claude Code, OpenCode, and Codex that enables systematic outline generation, deep web investigation, and automated report creation.