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.
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code $ npx degit Galaxy-Dawn/claude-scholar/agents ./rig-claude-scholar/agents $ npx degit Galaxy-Dawn/claude-scholar/commands ./rig-claude-scholar/commands $ npx degit Galaxy-Dawn/claude-scholar/skills ./rig-claude-scholar/skills $ npx degit Galaxy-Dawn/claude-scholar/hooks ./rig-claude-scholar/hooks
MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit Galaxy-Dawn/claude-scholar/skills/agent-identifier .claude/skills/agent-identifier $ npx degit Galaxy-Dawn/claude-scholar/skills/architecture-design .claude/skills/architecture-design $ npx degit Galaxy-Dawn/claude-scholar/skills/bug-detective .claude/skills/bug-detective $ npx degit Galaxy-Dawn/claude-scholar/skills/citation-verification .claude/skills/citation-verification $ npx degit Galaxy-Dawn/claude-scholar/skills/code-review-excellence .claude/skills/code-review-excellence $ npx degit Galaxy-Dawn/claude-scholar/skills/command-development .claude/skills/command-development $ npx degit Galaxy-Dawn/claude-scholar/skills/daily-coding .claude/skills/daily-coding $ npx degit Galaxy-Dawn/claude-scholar/skills/daily-paper-generator .claude/skills/daily-paper-generator $ npx degit Galaxy-Dawn/claude-scholar/skills/defuddle .claude/skills/defuddle $ npx degit Galaxy-Dawn/claude-scholar/skills/doc-coauthoring .claude/skills/doc-coauthoring $ npx degit Galaxy-Dawn/claude-scholar/skills/expression-skill .claude/skills/expression-skill $ npx degit Galaxy-Dawn/claude-scholar/skills/frontend-design .claude/skills/frontend-design $ npx degit Galaxy-Dawn/claude-scholar/skills/git-workflow .claude/skills/git-workflow $ npx degit Galaxy-Dawn/claude-scholar/skills/hook-development .claude/skills/hook-development $ npx degit Galaxy-Dawn/claude-scholar/skills/kaggle-learner .claude/skills/kaggle-learner $ npx degit Galaxy-Dawn/claude-scholar/skills/latex-conference-template-organizer .claude/skills/latex-conference-template-organizer $ npx degit Galaxy-Dawn/claude-scholar/skills/mcp-integration .claude/skills/mcp-integration $ npx degit Galaxy-Dawn/claude-scholar/skills/ml-paper-writing .claude/skills/ml-paper-writing $ npx degit Galaxy-Dawn/claude-scholar/skills/nature-data .claude/skills/nature-data $ npx degit Galaxy-Dawn/claude-scholar/skills/nature-polishing .claude/skills/nature-polishing $ npx degit Galaxy-Dawn/claude-scholar/skills/nature-response .claude/skills/nature-response $ npx degit Galaxy-Dawn/claude-scholar/skills/nature-writing .claude/skills/nature-writing $ npx degit Galaxy-Dawn/claude-scholar/skills/obsidian-kb-artifacts .claude/skills/obsidian-kb-artifacts $ npx degit Galaxy-Dawn/claude-scholar/skills/obsidian-literature-workflow .claude/skills/obsidian-literature-workflow $ npx degit Galaxy-Dawn/claude-scholar/skills/obsidian-project-kb-core .claude/skills/obsidian-project-kb-core $ npx degit Galaxy-Dawn/claude-scholar/skills/obsidian-source-ingestion .claude/skills/obsidian-source-ingestion $ npx degit Galaxy-Dawn/claude-scholar/skills/paper-self-review .claude/skills/paper-self-review $ npx degit Galaxy-Dawn/claude-scholar/skills/planning-with-files .claude/skills/planning-with-files $ npx degit Galaxy-Dawn/claude-scholar/skills/plugin-structure .claude/skills/plugin-structure $ npx degit Galaxy-Dawn/claude-scholar/skills/post-acceptance .claude/skills/post-acceptance $ npx degit Galaxy-Dawn/claude-scholar/skills/publication-chart-skill .claude/skills/publication-chart-skill $ npx degit Galaxy-Dawn/claude-scholar/skills/research-ideation .claude/skills/research-ideation $ npx degit Galaxy-Dawn/claude-scholar/skills/results-analysis .claude/skills/results-analysis $ npx degit Galaxy-Dawn/claude-scholar/skills/results-report .claude/skills/results-report $ npx degit Galaxy-Dawn/claude-scholar/skills/review-response .claude/skills/review-response $ npx degit Galaxy-Dawn/claude-scholar/skills/skill-development .claude/skills/skill-development $ npx degit Galaxy-Dawn/claude-scholar/skills/skill-improver .claude/skills/skill-improver $ npx degit Galaxy-Dawn/claude-scholar/skills/skill-quality-reviewer .claude/skills/skill-quality-reviewer $ npx degit Galaxy-Dawn/claude-scholar/skills/ui-ux-pro-max .claude/skills/ui-ux-pro-max $ npx degit Galaxy-Dawn/claude-scholar/skills/uv-package-manager .claude/skills/uv-package-manager
$ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/Galaxy-Dawn/claude-scholar/main/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/kaggle-miner.md https://raw.githubusercontent.com/Galaxy-Dawn/claude-scholar/main/agents/kaggle-miner.md $ curl -fsSL --create-dirs -o .claude/agents/literature-reviewer.md https://raw.githubusercontent.com/Galaxy-Dawn/claude-scholar/main/agents/literature-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/paper-miner.md https://raw.githubusercontent.com/Galaxy-Dawn/claude-scholar/main/agents/paper-miner.md $ curl -fsSL --create-dirs -o .claude/agents/rebuttal-writer.md https://raw.githubusercontent.com/Galaxy-Dawn/claude-scholar/main/agents/rebuttal-writer.md $ curl -fsSL --create-dirs -o .claude/agents/tdd-guide.md https://raw.githubusercontent.com/Galaxy-Dawn/claude-scholar/main/agents/tdd-guide.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 6,413 rigs:
{
"permissions": {
"deny": [
"Read(~/.ssh/**)",
"Read(**/.env)",
"Bash(rm -rf *)",
"Read(./.env)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(**/*.pem)",
"Bash(rm -rf /*)",
"Read(~/.aws/**)",
"Bash(rm -rf:*)",
"Read(.env)",
"Bash(git push --force*)",
"Read(**/*.key)",
"Read(./.env.*)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(gh pr merge *)",
"Bash(chown *)",
"Bash(docker *)"
]
}
} Skills (45)
agent-identifierarchitecture-designbug-detectivecitation-verificationcode-review-excellencecommand-developmentdaily-codingdaily-paper-generatordefuddledoc-coauthoringexpression-skillfrontend-designgit-workflowhook-developmentkaggle-learnerlatex-conference-template-organizermcp-integrationml-paper-writingnature-datanature-polishingnature-responsenature-writingobsidian-kb-artifactsobsidian-literature-workflowobsidian-project-kb-coreobsidian-source-ingestionpaper-self-reviewplanning-with-filesplugin-structurepost-acceptancepublication-chart-skillresearch-ideationresults-analysisresults-reportreview-responseskill-developmentskill-improverskill-quality-reviewerui-ux-pro-maxuv-package-managerverification-loopweb-design-reviewerwebapp-testingwriting-anti-aizotero-obsidian-bridge
Subagents (6)
| code-reviewer model: opus | 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. |
| kaggle-miner model: inherit | Use this agent when the user provides a Kaggle competition URL or asks to learn from Kaggle winning solutions. Examples: |
| literature-reviewer model: inherit | 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 proje |
| paper-miner model: inherit | 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 rebut |
| rebuttal-writer model: inherit | 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 rebutt |
| tdd-guide model: inherit | 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 |
Slash commands (64)
/analyze-results/build-fix/checkpoint/code-review/commit/create_project/kb-archive/kb-index/kb-ingest/kb-init/kb-links/kb-lint/kb-literature-review/kb-log/kb-map/kb-promote/kb-status/kb-sync/learn/mine-writing-patterns/plan/poster/presentation/promote/rebuttal/refactor-clean/research-init/sc/agent/sc/analyze/sc/brainstorm/sc/build/sc/business-panel/sc/cleanup/sc/design/sc/document/sc/estimate/sc/explain/sc/git/sc/help/sc/implement/sc/improve/sc/index-repo/sc/load/sc/pm/sc/recommend/sc/reflect/sc/research/sc/save/sc/sc/sc/select-tool/sc/spawn/sc/spec-panel/sc/task/sc/test/sc/troubleshoot/sc/workflow/setup-pm/tdd/update-github/update-memory/update-readme/verify/zotero-notes/zotero-review
Similar rigs
Clay-HHK/claude-config
Personal Claude Code harness configuration: agents, commands, rules, hooks, skills, and docs
YOLO Cowboy 12.3k tok ·
anthropics/claude-code
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.
Skill Collector 1.4k tok ·
LING71671/Open-ClaudeCode
Research archive of Claude Code source and runtime artifacts reconstructed from published npm source maps.
Skill Collector 8.5k tok ·
aiskillstore/marketplace
Security-audited skills for Claude, Codex & Claude Code. One-click install, quality verified.
Skill Collector 2.6k tok ·