@math-mentor/agent-skills

An MCP (Model Context Protocol) extension for Claude Code that helps you deeply explore hard math papers. Drop a PDF into your project, and use slash commands to extract theorems, generate depth analyses, run interactive Q&A sessions, and more -- all calibrated to your math level.

Quick Start

Prerequisites: Node.js >= 18, Claude Code

# In your project directory:
npx @math-mentor/agent-skills init

This runs an interactive wizard that:

1. Asks your math level (high school / undergraduate / graduate)
2. Configures your papers directory
3. Scaffolds all commands, agents, and skills into .claude/
4. Registers the MCP server in .mcp.json

Then:

1. Drop PDF papers into your papers/ directory
2. Open Claude Code in the project
3. Run /mcp to verify the mathmentor server is connected
4. Try: /extract <paper name>

Commands

| Command | Description | |---------|-------------| | /extract <paper> | Extract all theorems, definitions, and algorithms from a paper | | /summary <paper> | Generate a concise summary | | /depth <paper> | In-depth research-question-focused analysis | | /debate <paper> | Interactive Q&A tutoring session | | /prerequisites <paper> | List prerequisite knowledge needed to understand the paper | | /compare <paper1> <paper2> | Compare two papers side by side | | /reading-graph | View your reading progress and connections between papers |

All outputs are calibrated to your configured math level and saved to mathmentor/ for future reference.

How It Works

The package provides:

• MCP Server with 5 tools (find_paper, get_config, update_reading_graph, get_reading_graph, list_artifacts)
• 7 slash commands for Claude Code
• 3 specialized agents (extraction, depth analysis, debate)
• 3 skills (paper finding, question formulation, math level calibration)

License

MIT