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.
Claude Scholar is a collection of Claude Code subagents and skills designed to support computer science and AI researchers across the full arc of academic work, from literature discovery to manuscript submission. The main branch runs on Claude Code, with parallel branches for Codex CLI, Kimi Code CLI, and OpenCode. Core capabilities include a Zotero-integrated literature ingestion pipeline, an evidence-gated research contract system that tracks claim strength and promotion gates, and a structured writing stack built around Nature-journal conventions via dedicated skills such as `nature-writing`, `nature-polishing`, and `nature-response`. The `expression-skill` enforces a conclusion-first discipline across planning and reporting tasks, while `planning-with-files` handles on-disk progress tracking for long-running experiments. Publication output is handled through companion packages `pubfig` and `pubtab`, which produce formatted figures and Excel-to-LaTeX table workflows. An Obsidian-based knowledge base ties project notes, promoted claims, and paper sources into a vault-first navigation system. Researchers producing papers for top venues are the primary audience.
- ✓Open-source license (MIT)
- ✓Actively maintained (<30d)
- ✓Healthy fork ratio
- ✓Clear description
- ✓Topics declared
- ✓Documented (README)
git clone https://github.com/Galaxy-Dawn/claude-scholar && cp claude-scholar/*.md ~/.claude/agents/24 items in this repository
Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code. MUST BE USED for all code changes.
Use this agent when the user provides a Kaggle competition URL or asks to learn from Kaggle winning solutions. Examples:
Use this agent when the user asks to "conduct literature review", "search for papers", "analyze research papers", "identify research gaps", "review related work", or mentions starting a research project. This agent integrates with Zotero for automated paper collection, organization, and full-text analysis. Examples:
Use this agent when the user provides a research paper (PDF/DOCX/arXiv link) or asks to learn writing patterns from papers, extract venue-specific writing signals, study paper structure, or mine rebuttal strategies. The agent writes extracted knowledge into the active installed paper-miner writing memory for ml-paper-writing. It does not maintain project-specific writing memory.
Use this agent when the user asks to "write rebuttal", "respond to reviewers", "analyze review comments", or needs help with academic paper review response. This agent specializes in systematic rebuttal writing with professional tone and structured responses.
Test-driven development guide for writing tests first, implementing the smallest passing change, and keeping verification tight. Use when the user explicitly wants TDD or when a task should be driven by failing tests before code.
Run a blocker-first post-experiment workflow: validate evidence, produce strict statistical analysis when possible, and generate a decision-oriented results report only when the analysis bundle is sufficient. Uses results-analysis + results-report as a gated two-stage workflow.
Commit changes following Conventional Commits format (local only, no push).
Archive, detach, purge, or rename KB objects while keeping registry, index, and links consistent.
Refresh the auto index block inside 02-Index.md without overwriting curated content.
Ingest external material into Sources/* inside the bound project KB, then update registry, index, and daily note as needed.
Initialize or rebuild a vault-first, project-scoped Obsidian KB under Research/{project-slug}/ for the current repository.
Repair or strengthen wikilinks among canonical KB notes without generating extra artifact sprawl.
Run the project-scoped literature workflow from Sources/Papers into Knowledge, Writing, and Maps/literature.canvas.
Update the current project Daily note and, when needed, the plan, hub, and runtime binding summary.
Generate or repair derived KB artifacts such as literature.canvas, optional Bases, or other explicit map outputs.
Promote durable content from Daily or source notes into canonical Knowledge, Experiments, Results, Results/Reports, or Writing notes.
Summarize the current bound project KB status, including registry counts and key project note paths.
Run deterministic KB maintenance to refresh scaffold integrity, registry, index, daily note, and runtime binding summary.
Read one or more papers and update the active installed paper-miner writing memory with reusable writing patterns, structure signals, reusable phrasing, venue-specific signals, and rebuttal-friendly language.
Restate requirements, assess risks, and create step-by-step implementation plan. WAIT for user CONFIRM before touching any code.
Subagents overview
What people ask about claude-scholar
What is Galaxy-Dawn/claude-scholar?
+
Galaxy-Dawn/claude-scholar is subagents for the Claude AI ecosystem. 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. It has 4.3k GitHub stars and was last updated 7d ago.
How do I install claude-scholar?
+
You can install claude-scholar by cloning the repository (https://github.com/Galaxy-Dawn/claude-scholar) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is Galaxy-Dawn/claude-scholar safe to use?
+
Our security agent has analyzed Galaxy-Dawn/claude-scholar and assigned a Trust Score of 100/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.
Who maintains Galaxy-Dawn/claude-scholar?
+
Galaxy-Dawn/claude-scholar is maintained by Galaxy-Dawn. The last recorded GitHub activity is from 7d ago, with 4 open issues.
Are there alternatives to claude-scholar?
+
Yes. On ClaudeWave you can browse similar subagents at /categories/agents, sorted by popularity or recent activity.
Deploy claude-scholar to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/galaxy-dawn-claude-scholar)<a href="https://claudewave.com/repo/galaxy-dawn-claude-scholar"><img src="https://claudewave.com/api/badge/galaxy-dawn-claude-scholar" alt="Featured on ClaudeWave: Galaxy-Dawn/claude-scholar" width="320" height="64" /></a>More Subagents
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
The agent that grows with you
Java 面试 & 后端通用面试指南,覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Production-ready platform for agentic workflow development.
The agent engineering platform.
🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.