Semi-automated research assistant for academic research and software development, especially for computer science and AI researchers. Supports Claude Code, Codex CLI, Kimi Code CLI, and OpenCode across literature review, coding, experiments, reporting, writing, and project knowledge management.
Branch note: the main branch is the Claude Code workflow. If you use Codex CLI, please see the codex branch. If you use Kimi Code CLI, please see the kimi branch. If you use OpenCode, please see the opencode branch.
| Sponsor | Description |
|---|---|
 |
OfoxAI: Model APIs for research, code and writing: Access Claude, GPT, Gemini and DeepSeek text models with one API key for literature reading, experiment code and academic writing. Image, video and speech models are also available for research presentations and communication. |
 |
Thanks to APIMart for sponsoring this project! APIMart is a low-cost API platform for AI image & video generation — GPT-Image-2 from $0.006/image, 160+ images per dollar. One async API covers both image and video: submit a task, get an ID, fetch results via polling or callback. Batch tens of thousands of images without timeouts, switch models without changing code. Pay-as-you-go with no monthly fee — sign up here to get started. |
 |
Thanks to the Kimi team for their strong support of this project! Official links: Kimi Code · Platform CN · Platform Global. |
- 2026-06-03: Kimi Code CLI branch added with strong support from Kimi — added the
kimibranch as the Kimi Code CLI edition of Claude Scholar and thank the Kimi team for their strong support of this project. - 2026-05-14:
expression-skillmade the communication core,planning-with-filesrestored as the default persistence layer, and the Nature writing stack expanded — madeexpression-skillthe explicit conclusion-first discipline for reporting, planning, file operations, and multi-step technical work; reintroducedplanning-with-filesas the default on-disk planning and progress-tracking workflow for complex tasks; introducednature-writingfor section drafting and argument construction; refreshednature-polishingto the latest upstream article-pattern release; and keptnature-responseplusnature-datain the journal-writing stack. - 2026-05-13: Evidence-gated research workflow and
Sources/Papersrouting tightened — added a sharedresearch-contract.mdfor Evidence Records, claim strength, and Claim Promotion Gates; connected research ideation, Zotero ingestion, literature synthesis, results reporting, writing, and rebuttal workflows to that contract; and clarified that project paper notes live underSources/Papersbefore promoted claims move intoKnowledgeorWriting. - 2026-04-24: Project-scoped Obsidian KB workflow consolidated — rebuilt Obsidian project knowledge management into a vault-first workflow, consolidated the older overlapping memory skills into four focused skills, kept repo-local project binding metadata as a runtime layer, and made project navigation human-first instead of a machine registry dump.
- 2026-04-22: Lean core, pruned default agents, safer install lifecycle, and cleaner paper discovery — replaced large always-on
CLAUDE.md/AGENTS.mdfiles with compact core instructions, pruned the default agent set to the retained core agents, added safe install-state based uninstall support, generalizeddaily-paper-generatorto broader topics with arXiv / bioRxiv support and a fixed Top 10 -> Top 3 -> Top 1 selection flow. - 2026-04-15: pubfig and pubtab introduced — introduced
pubfig, a Python package for publication-grade scientific figures, andpubtab, a Python package for publication-ready tables and Excel↔LaTeX workflows. Together they provide a cleaner production stack for paper figures, benchmark tables, export control, and final artifact QA.
View older changelog
-
2026-04-15:
publication-chart-skillintegrated into Claude Scholar — wrappedpubfig+pubtabintopublication-chart-skill, added the skill to the repository, and connected it to Claude Scholar's analysis and writing boundaries so publication-grade figure/table work now has an explicit handoff route instead of being mixed into general analysis or prose skills. -
2026-03-31: Zotero smart-import workflow docs aligned — updated Claude Scholar's research-facing docs around the latest
zotero-mcppublic surface:zotero_add_items_by_identifieris now the default paper-import path,zotero_reconcile_collection_duplicatesis the standard post-import cleanup step, source-aware PDF cascade behavior is documented more accurately, and public vs internal diagnostics are now clearly separated. -
2026-03-31: README onboarding refreshed — clarified that Claude Scholar is especially well-suited to computer science and AI researchers, added practical getting-started scenarios after installation, improved prerequisite and branch guidance, and made the “existing local md files must be manually merged” expectation much more explicit.
-
2026-03-31: Installer and hook behavior tightened — the installer now preserves existing local
CLAUDE.mdwhile installing the repo-managed version asCLAUDE.scholar.md, and the default hook summaries were trimmed to reduce noisy temp-file / uncommitted-file output while keeping safer write-guard behavior. -
2026-03-31: Japanese documentation added — added Japanese docs for the main README plus
AGENTS,MCP_SETUP, andOBSIDIAN_SETUP, so the OpenCode branch now has a more complete multilingual documentation surface. -
2026-02-25: Codex CLI support — added
codexbranch supporting OpenAI Codex CLI with config.toml, 40 skills, 14 agents, and sandbox security -
2026-02-23: Added
setup.shinstaller — backup-aware incremental updates for existing~/.opencode, auto-backupopencode.jsonc, additiveagent/mcp/permission/pluginmerge -
2026-02-21: OpenCode support — Claude Scholar now supports OpenCode as an alternative CLI; switch to the
opencodebranch for OpenCode-compatible configuration -
2026-02-20: Bilingual docs — maintained English and Chinese entry documents for broader readability
-
2026-02-15: Zotero MCP integration — added
/zotero-reviewand/zotero-notescommands, updatedresearch-ideationskill with Zotero integration guide, enhancedliterature-revieweragent with Zotero MCP support for automated paper import, collection management, full-text reading, and citation export -
2026-02-14: Hooks optimization — restructured
security-guardto two-tier system (Block + Confirm),skill-forced-evalnow groups skills into 6 categories with silent scan mode,session-startlimits display to top 5,session-summaryadds 30-day log auto-cleanup,stop-summaryshows separate added/modified/deleted counts; removed deprecated shell scripts (lib/common.sh, lib/platform.sh) -
2026-02-11: Major update — added 10 new skills (research-ideation, results-analysis, citation-verification, review-response, paper-self-review, post-acceptance, daily-coding, frontend-design, ui-ux-pro-max, web-design-reviewer), 7 new agents, 8 research workflow commands, 2 new rules (security, experiment-reproducibility); restructured the main configuration docs; 89 files changed
-
2026-01-26: Rewrote all Hooks to cross-platform Node.js; completely rewrote README; expanded ML paper writing knowledge base; merged PR #1 (cross-platform support)
-
2026-01-25: Project open-sourced, v1.0.0 released with 25 skills (architecture-design, bug-detective, git-workflow, kaggle-learner, scientific-writing, etc.), 2 agents (paper-miner, kaggle-miner), 30+ commands (including SuperClaude suite), 5 Shell Hooks, and 2 rules (coding-style, agents)
| Section | What it helps with |
|---|---|
| Why Claude Scholar | Understand the project positioning and target use cases. |
| Core Workflow | See the end-to-end research pipeline from ideation to publication. |
| Quick Start | Install Claude Scholar in full, minimal, or selective mode. |
| Getting Started Scenarios | See a few realistic first-use scenarios after installation. |
| Integrations | Learn how Zotero, Obsidian, and optional X promotion fit into the workflow. |
| Primary Workflows | Browse the main research and development workflows. |
| Supporting Workflows | See the background systems that strengthen the main workflow. |
| Documentation | Jump to setup docs, configuration, and templates. |
| Citation | Cite Claude Scholar in papers, reports, or project docs. |
Claude Scholar is not an end-to-end autonomous research system that tries to replace the researcher.
Its core idea is simple:
human decision-making stays at the center; the assistant accelerates the workflow around it.
That means Claude Scholar is designed to help with the heavy, repetitive, and structure-sensitive parts of research — literature organization, note-taking, experiment analysis, reporting, and writing support — while still keeping the key judgments in human hands:
- which problem is worth pursuing,
- which papers actually matter,
- which hypotheses are worth testing,
- which results are convincing,
- and what should be written, submitted, or abandoned.
In other words, Claude Scholar is a semi-automated research assistant, not a “fully automated scientist.”
Claude Scholar is especially well-suited to:
- computer science researchers who move between literature review, coding, experiments, and paper writing,
- AI / ML researchers who need one assistant workflow spanning ideation, implementation, analysis, reporting, and rebuttal,
- research engineers and graduate students who want stronger workflow structure without giving up human judgment,
- and software-heavy academic projects that benefit from Zotero, Obsidian, CLI automation, and reproducible project memory.
It can still help in other research settings, but its current workflow design is most aligned with computer science, AI, and adjacent computational research.
Claude Scholar routes research work through a traceable path:
question -> evidence -> experiment -> analysis -> claim -> writing.
Each stage should preserve what is known, what is uncertain, and what decision should happen next.
- Ideation: turn a vague topic into concrete questions, research gaps, and an initial plan.
- Literature: search, import, organize, and read papers through Zotero collections.
- Paper notes: convert papers into structured reading notes and reusable claims.
- Knowledge base: route durable knowledge into Obsidian across
Sources / Knowledge / Experiments / Results / Results/Reports / Writing / Daily / Maps. - Experiments: track hypotheses, experiment lines, run history, findings, and next actions.
- Analysis: generate strict statistics, real scientific figures, and analysis artifacts with
results-analysis. - Reporting: produce a complete post-experiment report with
results-report, then write it back into Obsidian. - Writing and publication: carry stable findings into literature reviews, papers, rebuttals, slides, posters, and promotion.
- Claude Code
- Git
- (Optional) Python + uv for Python development
- (Optional) Zotero + Galaxy-Dawn/zotero-mcp for literature workflows
- (Optional) Obsidian for project knowledge-base workflows
git clone https://github.com/Galaxy-Dawn/claude-scholar.git /tmp/claude-scholar
bash /tmp/claude-scholar/scripts/setup.shWindows: please use Git Bash or WSL to run the installer.
The installer is backup-aware and incremental-update friendly:
- updates repo-managed
skills/commands/agents/rules/hooks/scripts/CLAUDE*.md, - backs up overwritten files to
~/.claude/.claude-scholar-backups/<timestamp>/, - backs up
settings.jsontosettings.json.bak, - preserves an existing
~/.claude/CLAUDE.mdand installs the repo-managed version as~/.claude/CLAUDE.scholar.md, - preserves an existing
~/.claude/CLAUDE.zh-CN.mdand installs the repo-managed version as~/.claude/CLAUDE.zh-CN.scholar.md, - preserves your existing
env, model/provider settings, API keys, permissions, and currentmcpServersvalues, - adds missing hook entries instead of replacing your entire hook set.
Important CLAUDE note: if you already maintain your own ~/.claude/CLAUDE.md or ~/.claude/CLAUDE.zh-CN.md, review ~/.claude/CLAUDE.scholar.md and ~/.claude/CLAUDE.zh-CN.scholar.md after installation and manually merge the Claude Scholar sections you want into your own files. Do not assume the sidecar files are applied automatically.
To update later:
cd /tmp/claude-scholar
git pull --ff-only
bash scripts/setup.shTo uninstall later:
cd /tmp/claude-scholar
bash scripts/uninstall.shThe installer now writes:
~/.claude/.claude-scholar-manifest.txtfor the exact files managed by Claude Scholar~/.claude/.claude-scholar-install-statefor install ownership metadata used by safe uninstall
The uninstaller removes only files and settings entries recorded in that install state. It does not guess ownership from the current repo checkout.
Install only a small research-focused subset:
git clone https://github.com/Galaxy-Dawn/claude-scholar.git /tmp/claude-scholar
mkdir -p ~/.claude/hooks ~/.claude/skills
cp /tmp/claude-scholar/hooks/*.js ~/.claude/hooks/
cp -r /tmp/claude-scholar/skills/ml-paper-writing ~/.claude/skills/
cp -r /tmp/claude-scholar/skills/research-ideation ~/.claude/skills/
cp -r /tmp/claude-scholar/skills/results-analysis ~/.claude/skills/
cp -r /tmp/claude-scholar/skills/results-report ~/.claude/skills/
cp -r /tmp/claude-scholar/skills/review-response ~/.claude/skills/
cp -r /tmp/claude-scholar/skills/writing-anti-ai ~/.claude/skills/
cp -r /tmp/claude-scholar/skills/git-workflow ~/.claude/skills/
cp -r /tmp/claude-scholar/skills/bug-detective ~/.claude/skills/Post-install: minimal/manual install does not auto-merge settings.json; copy only the hooks or MCP entries you want from settings.json.template. If you already have your own ~/.claude/CLAUDE.md or ~/.claude/CLAUDE.zh-CN.md, also merge the relevant sections from this repo's Claude files into yours instead of blindly overwriting them.
Copy only the parts you need:
git clone https://github.com/Galaxy-Dawn/claude-scholar.git /tmp/claude-scholar
cd /tmp/claude-scholar
cp hooks/*.js ~/.claude/hooks/
cp -r skills/latex-conference-template-organizer ~/.claude/skills/
cp -r skills/architecture-design ~/.claude/skills/
cp agents/paper-miner.md ~/.claude/agents/
cp rules/coding-style.md ~/.claude/rules/
cp rules/agents.md ~/.claude/rules/Post-install: selective/manual install does not auto-merge settings.json; copy only the hooks or MCP entries you actually want from settings.json.template. If you already have your own ~/.claude/CLAUDE.md or ~/.claude/CLAUDE.zh-CN.md, merge the relevant sections from this repo's Claude files into yours instead of blindly overwriting them.
Step 1: Install the Plugin
/plugin marketplace add Galaxy-Dawn/claude-scholar
/plugin install claude-scholar@claude-scholarThis auto-loads all skills, commands, agents, and hooks. During installation, you can choose the scope: user (all projects) or project (single project).
Step 2: Install Rules (Required)
Claude Code plugins cannot distribute rules automatically. Install them manually:
git clone https://github.com/Galaxy-Dawn/claude-scholar.git /tmp/claude-scholar
# User-level (all projects)
mkdir -p ~/.claude/rules
cp /tmp/claude-scholar/rules/*.md ~/.claude/rules/
# Or project-level (current project only)
mkdir -p .claude/rules
cp /tmp/claude-scholar/rules/*.md .claude/rules/Post-install: plugin installation does not auto-load CLAUDE.md or configure settings.json; if you already have your own ~/.claude/CLAUDE.md or ~/.claude/CLAUDE.zh-CN.md, merge the relevant Claude Scholar sections into yours instead of assuming the plugin applies them automatically. If you need Zotero MCP or other integrations, see the Integrations section for manual setup.
After installation, the simplest way to begin is to describe your task in natural language. You do not need to memorize the whole system first. Below are a few realistic starting points.
You can say:
Help me start research on [your topic]. I want a literature-grounded plan, the key open questions, and the next concrete steps.
What Claude Scholar will typically help with:
- clarify the topic and narrow the research question,
- identify promising literature directions,
- suggest an initial plan or hypothesis list,
- optionally route the work into Zotero or Obsidian if you use them.
You can say:
Review my Zotero collection on brain foundation models and summarize the main directions, gaps, and promising next steps.
Typical output:
- paper grouping by theme,
- a short literature synthesis,
- gap analysis,
- candidate research directions worth pursuing next.
You can say:
Analyze the results in this experiment folder, check what changed across runs, and write a decision-oriented summary.
Typical output:
- metric comparison,
- ablation or error-analysis suggestions,
- a result summary that highlights what is solid, what is weak, and what to run next.
You can say:
Help me draft the related work section for this project based on the current findings and paper notes.
or:
Help me write a rebuttal draft for these reviewer comments.
Typical output:
- a structured section draft,
- improved argument flow,
- clearer claims and evidence mapping,
- follow-up points that still need support or verification.
- Start with one concrete task, not a vague request for "everything."
- If you already maintain your own local
CLAUDE.mdfiles, merge the Claude Scholar sections you want into them instead of assuming sidecar files apply automatically. - Zotero and Obsidian are optional, but they become much more useful when you want durable literature notes or project memory rather than one-off chat output.
Claude Scholar is maintained for:
- Claude Code — the primary installation target.
- Codex CLI — supported workflow and documentation are available in this repo ecosystem.
- OpenCode — supported as an alternative CLI workflow.
The top-level workflow is the same: research, coding, experiments, reporting, and project knowledge management.
Use Zotero when you want Claude Scholar to help with:
- paper import via DOI / arXiv / URL,
- collection-based reading workflows,
- full-text access through Zotero MCP,
- detailed paper notes and literature synthesis.
See MCP_SETUP.md.
Use Obsidian when you want Claude Scholar to maintain a filesystem-first research knowledge base:
Sources/Knowledge/Experiments/Results/Results/Reports/Writing/Daily/Maps/
See OBSIDIAN_SETUP.md.
Use Xquik when /promote needs bounded public X research, draft analysis, or
publishing from an approved connected account. Claude Scholar keeps retrieved
posts outside scholarly evidence and requires a complete preview plus explicit
approval before each write.
See MCP_SETUP.md for client setup and
xquik-promotion.md
for the promotion workflow.
Complete academic research lifecycle — 7 stages from idea to publication.
End-to-end research startup from idea generation to literature management.
| Type | Name | One-line explanation |
|---|---|---|
| Skill | research-ideation |
Turn vague topics into structured questions, gap analysis, and an initial research plan. |
| Agent | literature-reviewer |
Search, classify, and synthesize papers into an actionable literature picture. |
| Command | /research-init |
Start a new topic with literature search, Zotero organization, research question cards, and proposal drafting only when the evidence gate passes. |
| Command | /zotero-review |
Review an existing Zotero collection and generate a structured literature synthesis. |
| Command | /zotero-notes |
Batch-read a Zotero collection and create structured paper reading notes. |
How it works
- 5W1H Brainstorming: turn a vague topic into structured questions (
What / Why / Who / When / Where / How). - Literature Search & Import: search papers, extract DOI/arXiv/URLs, import them into Zotero, and organize them into themed collections.
- PDF & Full Text: attach PDFs when available, read full text when possible, and fall back to abstract-level analysis when necessary.
- Gap Analysis: identify literature, methodological, application, interdisciplinary, or temporal gaps.
- Research Question & Planning: convert the review into concrete questions, initial hypotheses, and next-step planning.
- Evidence Gate: keep weak sources, project hypotheses, and missing evidence explicit before promoting