kitt-create-hooks

Create, configure, and validate Claude Code hooks for CLI workflows.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/utahdws/webteam-ai-tools --skill kitt-create-hooks
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: kitt-create-hooks
Source: https://github.com/utahdws/webteam-ai-tools/tree/main/.ai-cli/shared/skills/kitt-create-hooks
Command: npx skills add https://github.com/utahdws/webteam-ai-tools --skill kitt-create-hooks

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Expert guidance for creating, configuring, and using Claude Code hooks to enforce consistent, secure, and maintainable automation across development workflows.

Core Features & Use Cases

  • Detailed guidance on designing hook objects (PreToolUse, PostToolUse, Stop, SessionStart, UserPromptSubmit) and selecting appropriate matcher patterns.
  • Practical examples of command vs prompt hooks, input/output schemas, and safety best practices to reduce misconfiguration and risk.
  • Step-by-step workflows to compose multi-hook chains, test with --debug, and integrate with MCP tools across servers.

Quick Start

Configure a basic PreToolUse Bash hook that logs the command and approves it.

Frequently Asked Questions about kitt-create-hooks

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create Claude Code hooks for PreToolUse and PostToolUse events?

To create Claude Code hooks, you design hook objects for events like PreToolUse and PostToolUse, selecting appropriate matcher patterns and defining input/output schemas. This ensures reliable, safe automation across your CLI workflows.

What is the difference between command and prompt hooks in Claude Code?

Command hooks execute shell commands directly, while prompt hooks pass context to the model for processing. Choosing between them depends on whether your automation requires deterministic execution or flexible reasoning within your workflow.

Can I use Claude Code hooks with MCP tools and servers?

Yes, Claude Code hooks integrate with MCP tools across servers. You can configure matcher patterns to target specific MCP tools, applying safety checks and validation to ensure secure automation across your tool integrations.

How do I test and debug multi-hook chains in Claude Code?

You test multi-hook chains by composing them step-by-step and running with the --debug flag. This validates your hook definitions, verifies matcher patterns, and ensures safe workflow composition before deployment.

What matcher patterns should I use for Bash and Write tool hooks?

Matcher patterns for Bash and Write tools target specific tool invocations by event type. You configure these patterns within your hook definitions to ensure your safety checks and validation logic apply to the correct operations.

When should I use SessionStart and UserPromptSubmit hooks in my workflow?

SessionStart hooks initialize environment context when a session begins, while UserPromptSubmit hooks validate or modify user inputs before processing. Use them to enforce consistent, secure automation boundaries across development workflows.