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.
8.7
Rating
0
Installs
Backend Development
Category
Excellent comprehensive skill for Claude Code plugin hook development. The description clearly identifies trigger phrases and use cases. SKILL.md provides thorough coverage of hook types (prompt-based vs command), all event types, configuration formats, security best practices, and debugging workflows. Strong task knowledge with concrete examples, code snippets, and references to detailed files in references/ and examples/ directories. Well-structured with clear sections, quick reference tables, and logical progression from basics to advanced topics. High novelty as implementing event-driven hooks with LLM-based validation, security checks, and proper error handling would be complex and token-intensive for a CLI agent to accomplish without guidance. Minor room for improvement in explicitly calling out the two-format distinction (plugin vs settings) earlier, but overall this is a production-ready, well-documented skill.
Loading SKILL.md…

Skill Author