What types of events can trigger a Hookify rule?

Rules can be triggered by 'bash' commands, 'file' edits (writes/edits), 'stop' events (when Claude wants to finish), and 'prompt' events (user inputs).

Do I need to restart Claude to apply new rules?

No, rules are read dynamically and changes take effect immediately on the next tool use or event trigger.

Where are Hookify rules stored in a project?

They are stored in the .claude/ directory using the naming convention .claude/hookify.{rule-name}.local.md.

What are Hookify rules?

Hookify rules are Markdown files with YAML frontmatter that define specific patterns Claude should monitor and respond to during bash, file, or prompt operations.

Can I block specific commands using this skill?

Yes, by setting the action field to 'block' in the rule frontmatter, you can prevent specific operations or commands from executing.

Hookify Rule Architect

Name: Hookify Rule Architect
Author: Activer007

byActiver007

•

安全与测试

Simplifies the creation and management of Hookify rules to monitor, warn, and block specific patterns in Claude Code workflows.

The Hookify Rule Architect skill provides comprehensive guidance for designing and implementing Hookify rules, which are specialized markdown files used to intercept and evaluate Claude's actions. By defining regex patterns and YAML frontmatter, developers can create automated safeguards that monitor bash commands, file edits, and session completions. Whether you need to prevent dangerous shell operations, enforce coding standards like removing debug logs, or create mandatory pre-flight checklists, this skill offers the syntax patterns and best practices needed to maintain a secure and disciplined development environment within Claude Code.

主要功能

015 GitHub stars

02Standardized YAML frontmatter generation for Hookify rules

03Regex pattern guidance for bash commands and file operations

04Best practices for clear, actionable warning and error messages

05Multi-condition rule building using advanced field operators

06Event-specific triggering for bash, file, stop, and prompt events

使用场景

01Creating mandatory pre-stop checklists to ensure tests and documentation are updated

02Enforcing the removal of debug logs or sensitive credentials before file commits

03Preventing accidental execution of dangerous shell commands like 'rm -rf'

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add activer007/ordinary-claude-skills rule-identifier

For use in Claude.ai and ChatGPT

Download Skill