🔌 Claude Code Plugins

Comprehensive toolkit for developing Claude Code plugins with 7 expert skills and AI-assisted creation.

• /plugin-dev:create-plugin 8-phase guided workflow
• Skills: Hook development, MCP integration, agent development, plugin settings, structure, skill dev, command dev
• Agents: agent-creator, plugin-validator, skill-reviewer

Development kit for working with the Claude Agent SDK. Interactive setup and validation tools.

• /new-sdk-app Interactive setup for new Agent SDK projects
• Agents: agent-sdk-verifier-py, agent-sdk-verifier-ts

Easily create custom hooks to prevent unwanted behaviors by analyzing conversation patterns or explicit instructions.

• Commands: /hookify, /hookify:list, /hookify:configure, /hookify:help
• Agent: conversation-analyzer
• Skill: writing-rules (hookify rule syntax)

Comprehensive PR review with specialized agents for comments, tests, error handling, type design, code quality, and simplification.

• /pr-review-toolkit:review-pr Multi-aspect review
• Agents: comment-analyzer, pr-test-analyzer, silent-failure-hunter, type-design-analyzer, code-reviewer, code-simplifier

Automated PR code review using multiple specialized agents with confidence-based scoring to filter false positives.

• /code-review Automated PR review workflow
• Agents: CLAUDE.md compliance, bug detection, historical context, PR history, code comments

Security reminder hook that warns about potential security issues when editing files.

• Monitors: Command injection, XSS, eval usage, dangerous HTML, pickle deserialization, os.system calls

Comprehensive feature development workflow with a structured 7-phase approach.

• /feature-dev Guided feature development workflow
• Agents: code-explorer (analysis), code-architect (design), code-reviewer (quality)

Git workflow automation for committing, pushing, and creating pull requests.

• /commit Smart git commit
• /commit-push-pr Commit, push, and create PR
• /clean_gone Clean up gone branches

Interactive self-referential AI loops for iterative development. Claude works on the same task repeatedly until completion.

• /ralph-loop Start autonomous iteration
• /cancel-ralph Stop iteration loop
• Hook: Intercepts exit attempts to continue

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

• Skill: Automated migration of model strings, beta headers, and prompt adjustments

Create distinctive, production-grade frontend interfaces that avoid generic AI aesthetics.

• Auto-invoked for frontend work
• Guidance: Bold design choices, typography, animations, visual details

Adds educational insights about implementation choices and codebase patterns (mimics the deprecated Explanatory output style).

• Hook: Injects educational context at session start

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

• Encourages: Users to write 5-10 lines at decision points
• Provides: Educational insights throughout