Hook Development

8.9

358

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.

hooks

8.9

Rating

Installs

Backend Development

Quick Review

Excellent hook development skill with comprehensive coverage of Claude Code plugin hooks. The description clearly triggers on relevant keywords (hook types, events, validation). The SKILL.md is exceptionally thorough with complete examples for both prompt-based and command hooks, clear explanations of all hook events (PreToolUse, PostToolUse, Stop, etc.), security best practices, debugging guidance, and proper use of environment variables like ${CLAUDE_PLUGIN_ROOT}. Structure is very well organized with quick reference tables, clear sections, and appropriate references to external files (patterns.md, advanced.md, example scripts) for deeper details. The skill addresses a moderately complex domain (event-driven plugin development with LLM-based validation) that would require significant token usage for a CLI agent to handle from scratch, especially around the nuances of hook configuration formats, parallel execution, lifecycle limitations, and security considerations. Minor improvement could be made in the description to mention configuration format differences, but overall this is a high-quality, production-ready skill.