Plugin Development

This skill documents how to create user-configurable Claude Code plugins using .local.md files with YAML frontmatter. It provides bash utilities for parsing settings files and examples of hooks that adapt their behavior based on project-specific configuration.

A comprehensive guide for creating skills in Claude Code plugins. It covers skill anatomy, progressive disclosure principles, writing style requirements, and provides step-by-step workflows for planning, creating, validating, and iterating on skills.

Comprehensive toolkit for developing Claude Code plugins with 7 specialized skills covering hooks, MCP integration, plugin structure, settings, commands, agents, and skill development. Includes validation utilities, working examples, and detailed documentation following progressive disclosure principles.

A comprehensive educational skill that teaches developers how to structure Claude Code plugins. It covers directory layout conventions, plugin.json manifest configuration, component organization (commands, agents, skills, hooks), the ${CLAUDE_PLUGIN_ROOT} portable path variable, and best practices with examples ranging from minimal to enterprise-grade plugins.

This skill provides complete guidance for integrating MCP (Model Context Protocol) servers into Claude Code plugins. It covers all four server types (stdio, SSE, HTTP, WebSocket), authentication patterns (OAuth, tokens, environment variables), tool naming conventions, and security best practices for connecting plugins to external services.

This skill teaches developers how to create autonomous agents for Claude Code plugins. It provides comprehensive documentation on agent file structure, YAML frontmatter fields, system prompt design patterns, and triggering conditions with concrete examples. Includes a bash validation script to check agent files for correct structure.

This skill provides comprehensive guidance on creating Claude Code slash commands, including YAML frontmatter configuration, dynamic arguments ($1, $2, $ARGUMENTS), file references with @ syntax, bash execution, and plugin-specific features like ${CLAUDE_PLUGIN_ROOT}. It covers interactive commands using AskUserQuestion, multi-step workflows, testing strategies, and marketplace distribution considerations.

A comprehensive guide for creating Claude Code plugin hooks that automate validation, context loading, and workflow enforcement. Includes working example scripts for validating file writes and bash commands, plus utility scripts for testing and linting hook implementations before deployment.

This skill provides AI assistants with deep knowledge about the Addax open-source ETL tool. It covers the project's architecture, plugin system for 20+ data sources (MySQL, PostgreSQL, MongoDB, Kafka, HDFS, etc.), job configuration format, data transformation capabilities, and development guidelines for building custom reader/writer plugins.

This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.

This skill provides comprehensive guidance for creating Claude Code plugins, covering directory structure, manifest configuration (plugin.json), component organization patterns, and best practices. It includes examples from minimal single-command plugins to enterprise-grade deployments with MCP server integration, Kubernetes operations, and CI/CD automation.

This skill should be used when the user asks about "plugin settings", "store plugin configuration", "user-configurable plugin", ".local.md files", "plugin state files", "read YAML frontmatter", "per-project plugin settings", or wants to make plugin behavior configurable. Documents the .claude/plugin-name.local.md pattern for storing plugin-specific configuration with YAML frontmatter and markdown content.

This skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${CLAUDE_PLUGIN_ROOT} with MCP", or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.

This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.

This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.