Vepricov/claude-brainlab
A research lab's Claude Code setup: 67 skills, hooks and rules, plus a knowledge base in plain git — GitHub for ideas. A question goes in, knowledge comes out.
field: ProductivityAI / ML workflow: Planning & specsFrontend & designPR / code reviewResearchTesting & TDD
stack: Python
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 Vepricov/claude-brainlab/agents ./rig-claude-brainlab/agents $ npx degit Vepricov/claude-brainlab/commands ./rig-claude-brainlab/commands $ npx degit Vepricov/claude-brainlab/skills ./rig-claude-brainlab/skills $ npx degit Vepricov/claude-brainlab/hooks ./rig-claude-brainlab/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 Vepricov/claude-brainlab/skills/academic-plotting .claude/skills/academic-plotting $ npx degit Vepricov/claude-brainlab/skills/agent-identifier .claude/skills/agent-identifier $ npx degit Vepricov/claude-brainlab/skills/architecture-design .claude/skills/architecture-design $ npx degit Vepricov/claude-brainlab/skills/astar-paper-review .claude/skills/astar-paper-review $ npx degit Vepricov/claude-brainlab/skills/bug-detective .claude/skills/bug-detective $ npx degit Vepricov/claude-brainlab/skills/call-notes .claude/skills/call-notes $ npx degit Vepricov/claude-brainlab/skills/caveman .claude/skills/caveman $ npx degit Vepricov/claude-brainlab/skills/citation-verification .claude/skills/citation-verification $ npx degit Vepricov/claude-brainlab/skills/code-ingest .claude/skills/code-ingest $ npx degit Vepricov/claude-brainlab/skills/code-library .claude/skills/code-library $ npx degit Vepricov/claude-brainlab/skills/code-review-excellence .claude/skills/code-review-excellence $ npx degit Vepricov/claude-brainlab/skills/command-development .claude/skills/command-development $ npx degit Vepricov/claude-brainlab/skills/create-project .claude/skills/create-project $ npx degit Vepricov/claude-brainlab/skills/daily-coding .claude/skills/daily-coding $ npx degit Vepricov/claude-brainlab/skills/defuddle .claude/skills/defuddle $ npx degit Vepricov/claude-brainlab/skills/diagnose .claude/skills/diagnose $ npx degit Vepricov/claude-brainlab/skills/doc-coauthoring .claude/skills/doc-coauthoring $ npx degit Vepricov/claude-brainlab/skills/experiment-runs .claude/skills/experiment-runs $ npx degit Vepricov/claude-brainlab/skills/frontend-design .claude/skills/frontend-design $ npx degit Vepricov/claude-brainlab/skills/git-guardrails-claude-code .claude/skills/git-guardrails-claude-code $ npx degit Vepricov/claude-brainlab/skills/git-workflow .claude/skills/git-workflow $ npx degit Vepricov/claude-brainlab/skills/google-workspace-mcp .claude/skills/google-workspace-mcp $ npx degit Vepricov/claude-brainlab/skills/grill-me .claude/skills/grill-me $ npx degit Vepricov/claude-brainlab/skills/grill-with-docs .claude/skills/grill-with-docs $ npx degit Vepricov/claude-brainlab/skills/handoff-to-jarvis .claude/skills/handoff-to-jarvis $ npx degit Vepricov/claude-brainlab/skills/handoff .claude/skills/handoff $ npx degit Vepricov/claude-brainlab/skills/hook-development .claude/skills/hook-development $ npx degit Vepricov/claude-brainlab/skills/improve-codebase-architecture .claude/skills/improve-codebase-architecture $ npx degit Vepricov/claude-brainlab/skills/json-canvas .claude/skills/json-canvas $ npx degit Vepricov/claude-brainlab/skills/kaggle-learner .claude/skills/kaggle-learner $ npx degit Vepricov/claude-brainlab/skills/lab-knowledge .claude/skills/lab-knowledge $ npx degit Vepricov/claude-brainlab/skills/latex-conference-template-organizer .claude/skills/latex-conference-template-organizer $ npx degit Vepricov/claude-brainlab/skills/mcp-integration .claude/skills/mcp-integration $ npx degit Vepricov/claude-brainlab/skills/ml-paper-writing .claude/skills/ml-paper-writing $ npx degit Vepricov/claude-brainlab/skills/obsidian-bases .claude/skills/obsidian-bases $ npx degit Vepricov/claude-brainlab/skills/obsidian-cli .claude/skills/obsidian-cli $ npx degit Vepricov/claude-brainlab/skills/obsidian-experiment-log .claude/skills/obsidian-experiment-log $ npx degit Vepricov/claude-brainlab/skills/obsidian-markdown .claude/skills/obsidian-markdown $ npx degit Vepricov/claude-brainlab/skills/operon-obsidian-setup .claude/skills/operon-obsidian-setup $ npx degit Vepricov/claude-brainlab/skills/paper-ingest .claude/skills/paper-ingest
$ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/Vepricov/claude-brainlab/main/agents/architect.md $ curl -fsSL --create-dirs -o .claude/agents/bug-analyzer.md https://raw.githubusercontent.com/Vepricov/claude-brainlab/main/agents/bug-analyzer.md $ curl -fsSL --create-dirs -o .claude/agents/build-error-resolver.md https://raw.githubusercontent.com/Vepricov/claude-brainlab/main/agents/build-error-resolver.md $ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/Vepricov/claude-brainlab/main/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/dev-planner.md https://raw.githubusercontent.com/Vepricov/claude-brainlab/main/agents/dev-planner.md $ curl -fsSL --create-dirs -o .claude/agents/kaggle-miner.md https://raw.githubusercontent.com/Vepricov/claude-brainlab/main/agents/kaggle-miner.md $ curl -fsSL --create-dirs -o .claude/agents/literature-reviewer.md https://raw.githubusercontent.com/Vepricov/claude-brainlab/main/agents/literature-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/obsidian-hub-creator.md https://raw.githubusercontent.com/Vepricov/claude-brainlab/main/agents/obsidian-hub-creator.md $ curl -fsSL --create-dirs -o .claude/agents/paper-miner.md https://raw.githubusercontent.com/Vepricov/claude-brainlab/main/agents/paper-miner.md $ curl -fsSL --create-dirs -o .claude/agents/refactor-cleaner.md https://raw.githubusercontent.com/Vepricov/claude-brainlab/main/agents/refactor-cleaner.md $ curl -fsSL --create-dirs -o .claude/agents/story-generator.md https://raw.githubusercontent.com/Vepricov/claude-brainlab/main/agents/story-generator.md $ curl -fsSL --create-dirs -o .claude/agents/tdd-guide.md https://raw.githubusercontent.com/Vepricov/claude-brainlab/main/agents/tdd-guide.md $ curl -fsSL --create-dirs -o .claude/agents/ui-sketcher.md https://raw.githubusercontent.com/Vepricov/claude-brainlab/main/agents/ui-sketcher.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (67)
academic-plottingagent-identifierarchitecture-designastar-paper-reviewbug-detectivecall-notescavemancitation-verificationcode-ingestcode-librarycode-review-excellencecommand-developmentcreate-projectdaily-codingdefuddlediagnosedoc-coauthoringexperiment-runsfrontend-designgit-guardrails-claude-codegit-workflowgoogle-workspace-mcpgrill-megrill-with-docshandoff-to-jarvishandoffhook-developmentimprove-codebase-architecturejson-canvaskaggle-learnerlab-knowledgelatex-conference-template-organizermcp-integrationml-paper-writingobsidian-basesobsidian-cliobsidian-experiment-logobsidian-markdownoperon-obsidian-setuppaper-ingestpaper-searchpaper-to-socialpaper-venue-formattingpdf-readerplanning-with-filesplugin-structurepresentationpresenter-modeprototyperesearch-cycleresearch-ideationrestore-sessionresults-analysisresults-reportreverse-outline-flow-checkreview-responsesetup-pre-commitskill-developmenttddui-ux-pro-maxuv-package-managerverification-loopwant-2-readweb-design-reviewerwebapp-testingwriting-anti-aizoom-out
Subagents (13)
| architect model: sonnet | ML project architecture specialist for code structure, module design, and pattern consistency. Use PROACTIVELY when modifying code structure, adding new modules, or maintaining architectural patterns. |
| bug-analyzer model: sonnet | Expert debugger specialized in deep code execution flow analysis and root cause investigation. Use when you need to analyze code execution paths, build execution chain diagrams, trace variable state c |
| build-error-resolver model: sonnet | Build and Python type error resolution specialist. Use PROACTIVELY when build fails or type errors occur. Fixes build/type errors only with minimal diffs, no architectural edits. Focuses on getting th |
| code-reviewer model: sonnet | 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. |
| dev-planner model: sonnet | Expert development planner for feature implementation, roadmaps, and task decomposition. Use when you need to plan feature implementation, create development roadmaps, or organize complex development |
| kaggle-miner model: sonnet | Use this agent when the user provides a Kaggle competition URL or asks to learn from Kaggle winning solutions, extract ML competition techniques, or study top Kaggle solutions. |
| literature-reviewer model: sonnet | Use this agent when the user asks to conduct a literature review, search for papers, analyze research papers, identify research gaps, or review related work. Integrates with Zotero for automated paper |
| obsidian-hub-creator model: haiku | | |
| paper-miner model: sonnet | Use this agent when the user provides a research paper or asks to learn writing patterns from papers, extract venue-specific writing signals, study paper structure, or mine rebuttal strategies. |
| refactor-cleaner model: sonnet | Dead code cleanup and consolidation specialist. Use PROACTIVELY for removing unused code, duplicates, and refactoring. Runs analysis tools (vulture, pip-audit, pyflakes) to identify dead code and safe |
| story-generator model: sonnet | Use this agent when you need to generate user stories with acceptance criteria from git diffs, conversation history, PRD documents, or any requirements that need to be structured into story format. |
| tdd-guide model: sonnet | Test-Driven Development specialist enforcing write-tests-first methodology. Use PROACTIVELY when writing new features, fixing bugs, or refactoring code. Ensures 80%+ test coverage. |
| ui-sketcher model: sonnet | Universal UI Blueprint Engineer that transforms any functional requirement into visual ASCII interface designs, user stories, and interaction specifications. Excels at converting brief descriptions in |
Slash commands (10)
/analyze-results/checkpoint/commit/conversations/hypothesize/limits/memory-status/memory-sync/mine-writing-patterns/update-memory
Similar rigs
shkodnik1917/claude-brainlab
A research lab's Claude Code setup: 67 skills, hooks and rules, plus a knowledge base in plain git — GitHub for ideas. A question goes in, knowledge comes out.
Orchestrator 9.1k tok · · Q0
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.
Orchestrator 5.4k tok · · Q3
Clay-HHK/claude-config
Personal Claude Code harness configuration: agents, commands, rules, hooks, skills, and docs
YOLO Cowboy 12.3k tok · · Q5
MagicKidd/Rokid-agentic-workflow
探索在日常开发中,让 AI 编程助手保持上下文连贯与执行纪律的协作工作流。Exploring practical collaboration patterns for AI coding assistants.
Skill Collector 2.6k tok · · Q0