By matsengrp
Collection of specialized agents for scientific writing, code review, and technical documentation
Use this agent to scan code for specific architectural antipatterns and violations of clean code principles. This agent focuses on pattern detection and identification rather than comprehensive review. Examples: <example>Context: User wants to check if their codebase has common antipatterns before refactoring. user: 'Can you scan this module for any antipatterns?' assistant: 'I'll use the antipattern-scanner agent to check for specific architectural violations and clean code antipatterns in your module.' <commentary>The user wants targeted antipattern detection, so use the antipattern-scanner to identify specific violations.</commentary></example> <example>Context: User is reviewing code and wants to identify potential problem areas. user: 'I suspect this code has some design issues. Can you scan for antipatterns?' assistant: 'Let me use the antipattern-scanner agent to identify specific antipatterns and design violations in your code.' <commentary>Perfect use case for the antipattern-scanner to detect specific problematic patterns.</commentary></example>
Use this agent when you need expert code review focused on clean code principles, maintainability, and software craftsmanship. Examples: <example>Context: The user has just written a new function and wants it reviewed for clean code principles. user: 'I just wrote this function to calculate user permissions. Can you review it?' assistant: 'I'll use the clean-code-reviewer agent to analyze your function for clean code principles, DRY violations, and maintainability issues.' <commentary>Since the user is requesting code review, use the clean-code-reviewer agent to provide expert analysis focused on Uncle Bob's clean code principles.</commentary></example> <example>Context: The user has completed a feature implementation and wants comprehensive review. user: 'Here's my implementation of the payment processing module. Please review it thoroughly.' assistant: 'Let me use the clean-code-reviewer agent to conduct a thorough review of your payment processing module, focusing on clean code principles and best practices.' <commentary>The user wants thorough code review, so use the clean-code-reviewer agent to analyze the code for maintainability, clarity, and adherence to clean code principles.</commentary></example>
Use this agent to perform gentle code smell detection, identifying maintainability hints and readability improvements in a supportive, mentoring tone. This agent focuses on semantic issues that static analyzers miss, suggesting areas where code could be more expressive or maintainable. Examples: <example>Context: User wants a gentle review of their code for improvement opportunities. user: 'Can you check this module for any code smells or areas that could be improved?' assistant: 'I'll use the code-smell-detector agent to identify gentle improvement hints for your code.' <commentary>The user wants supportive feedback on code quality, perfect for the code-smell-detector's mentoring approach.</commentary></example> <example>Context: User is refactoring and wants to identify areas that need attention. user: 'I'm cleaning up this old code - can you spot any smells that suggest where to focus?' assistant: 'Let me use the code-smell-detector agent to identify areas that might benefit from refactoring attention.' <commentary>Code smell detection helps prioritize refactoring efforts by identifying maintainability issues.</commentary></example>
Use this agent when preparing a scientific manuscript for journal submission to perform final quality checks on repositories, references, and bibliographic information. Examples: (1) Context: User has completed a research paper and needs to verify all external resources before submission. User: 'I've finished my paper on machine learning methods. Can you check if everything is ready for journal submission?' Assistant: 'I'll use the journal-submission-checker agent to verify your repositories are open, check if preprints have been published, and ensure complete bibliographic information.' (2) Context: User is responding to reviewer comments that mentioned missing repository links. User: 'The reviewers want to make sure our code is accessible. Can you verify our repository status?' Assistant: 'Let me use the journal-submission-checker agent to verify repository accessibility and completeness of your submission materials.'
Use this agent when you need to create mathematical summaries of statistical/computational content in pull requests. Examples: <example>Context: User has just completed a PR with new clustering algorithms and wants mathematical documentation. user: 'I've finished implementing a new distance metric for phylogenetic trees in my PR. Can you help document the mathematical approach?' assistant: 'I'll use the math-pr-summarizer agent to analyze your PR and create mathematical documentation for the new distance metric.' <commentary>The user needs mathematical documentation of their PR content, so use the math-pr-summarizer agent to create .md files with LaTeX explaining the statistical/mathematical approaches.</commentary></example> <example>Context: User has a PR with multiple Jupyter notebooks containing statistical analyses. user: 'My PR has several .ipynb files with new statistical methods. I need corresponding .md files explaining the math.' assistant: 'I'll use the math-pr-summarizer agent to create mathematical summaries for each major file in your PR.' <commentary>The user needs mathematical documentation for their statistical PR content, so use the math-pr-summarizer agent.</commentary></example>
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimnpx claudepluginhub matsengrp/plugins --plugin matsengrp-agentsBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A collection of specialized agents for scientific writing, code review, and technical documentation.
This plugin collection provides specialized agents designed to enhance your development workflow, particularly for:
Comprehensive pre-PR quality checklist that guides you through:
Run before creating any pull request to ensure code quality standards are met.
Get native macOS notifications when Claude needs your input or completes tasks.
Prerequisites:
brew install terminal-notifier
Included notifications:
Notifications are automatically enabled when you install the plugin (if terminal-notifier is available).
To install and manage plugins, use the /plugin command which opens an interactive menu:
/plugin
This will present you with options to:
matsengrp/plugins or https://github.com/matsengrp/plugins when prompted)For more information about plugins:
These agents will be available as specialized subagents that Claude Code can invoke automatically based on your task context, or you can invoke them manually using the Task tool.
Use slash commands directly in your conversation:
/pre-pr-check - Run comprehensive pre-PR quality checklistplugins/
├── .claude-plugin/
│ └── plugin.json # Plugin manifest
├── agents/ # Agent definitions
├── commands/ # Custom slash commands
│ └── pre-pr-check.md # Pre-PR quality checklist
├── hooks/ # Event handlers
│ └── hooks.json # Desktop notifications (terminal-notifier)
└── skills/ # Agent skills (future)
This plugin is designed to replace the legacy claude-code-agents repository with the new Claude Code plugin system.
MIT
Erick Matsen & Matsen Group
Research-team agents for Claude Code: supervisor, analysis-implementer, paper-writer, figure-descriptor, reviewer, literature-curator.
Semi-automated research assistant for academic research and software development, with skills for literature review, experiments, analysis, writing, and project knowledge management
Multi-agent orchestrator for academic writing: 12 specialist agents and 30 writing principles for review, research, drafting, polishing, bibliography auditing, and literature surveys.
Academic paper writing skills for ML conferences (NeurIPS, ICML, ICLR, AAAI)
Scientific writing, citations, grants, posters, and academic career (13 skills)
学术论文写作 — 12 agent 协作:结构设计、段落写作、引用合规、双语摘要、格式排版