Agent Plugins

Refines recently changed code for clarity and consistency while preserving observable behavior.

Audits a repository and recommends a small, evidence-based set of Claude Code automations.

Assess legacy systems, map architecture and business rules, plan modernization, and verify rewrites or version uplifts against existing behavior.

Audit CLAUDE.md project instructions against the codebase and capture durable session learnings without turning the file into a transcript.

Automate common Git workflows with commands for creating commits, pushing branches, opening pull requests, and cleaning stale local branches.

Generates and publishes living project status pages as interactive HTML artifacts with workstream tracking, progress updates, and team collaboration features for complex multi-phase initiatives.

Specialized skills for designing and building Model Context Protocol servers with guidance on deployment models, tool design patterns, authentication, and interactive MCP applications.

Comprehensive toolkit with seven specialized skills and guided workflow for developing Claude Code plugins including hooks, MCP integration, agents, commands, and marketplace publishing.

Comprehensive toolkit for creating and verifying Claude Agent SDK applications in Python and TypeScript with scaffolding, best practices validation, and automated verification agents.

Simplifies creation of custom Claude Code hooks through markdown configuration files and conversation analysis, preventing unwanted behaviors without editing complex JSON schemas.