explanatory-output-style

Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification

Interactive learning mode that requests meaningful code contributions at decision points (mimics the unshipped Learning output style)

Easily create custom hooks to prevent unwanted behaviors by analyzing conversation patterns or from explicit instructions. Define rules via simple markdown files.

Development kit for working with the Claude Agent SDK

Marketplace

Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review

Comprehensive toolkit for developing Claude Code plugins. Includes 7 expert skills covering hooks, MCP integration, commands, agents, and best practices. AI-assisted plugin creation and validation.

Commands for git commit workflows including commit, push, and PR creation

Automated code review for pull requests using multiple specialized agents with confidence-based scoring to filter false positives

Migrate your code and prompts from Sonnet 4.x and Opus 4.1 to Opus 4.5.