multiAI Summary Pending

hooks-management

Use PROACTIVELY when you need to create, update, configure, or validate Claude hooks for various events and integrations

231 stars

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/hooks-management/SKILL.md --create-dirs "https://raw.githubusercontent.com/aiskillstore/marketplace/main/skills/emz1998/hooks-management/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/hooks-management/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How hooks-management Compares

Feature / Agenthooks-managementStandard Approach
Platform SupportmultiLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Use PROACTIVELY when you need to create, update, configure, or validate Claude hooks for various events and integrations

Which AI agents support this skill?

This skill is compatible with multi.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

**Goal**: Create, update or troubleshoot Claude Code hook scripts

## Workflow

- Read hook documentation from `.claude/skills/hooks-management/references/hooks.md`
- Read hook input patterns from `.claude/skills/hooks-management/references/input-patterns.md`
- Review existing hooks in `.claude/hooks/` and settings in `.claude/settings.local.json`
- Create or update the hook script following the input patterns
- Troubleshoot the hook script if needed
- Verify hook execution using `echo` to pipe JSON input
- Review for security and performance issues
- Provide report to main agent

## Rules

- **NEVER** hardcode credentials or modify critical system files
- **NEVER** write hooks that can cause infinite loops
- **NEVER** bypass security validations
- **DO NOT** use multiline comments in hook scripts. Only use single line comments.
- **MUST** include proper error handling
- **MUST** prefer readability over performance
- **MUST** prefer Python over shell scripts
- **MUST** write semantic and idiomatic code

## Acceptance Criteria

- Hook executes successfully on target event
- Hook handles invalid/malformed input gracefully
- No security vulnerabilities
- Hook follows dispatcher pattern (for new hook logic)