How do Claude Code hooks function?

Skills utilize the UserPromptSubmit hook to inject context before a prompt is processed and the PreToolUse or Stop hooks to validate actions or provide reminders after a tool executes.

What is the 500-line rule for Claude Skills?

The 500-line rule is a best practice requiring SKILL.md files to stay under 500 lines. Detailed documentation should be moved to reference files to maintain AI focus and performance.

What are intent patterns in skill triggers?

Intent patterns use regex to detect the user's underlying goal (like 'creating a component') even if specific keywords aren't used, allowing for more natural skill activation.

How can I test my new Claude Skill?

You can manually test hooks using npx tsx commands to pipe mock JSON sessions into your activation and verification scripts to ensure triggers fire correctly.

What are the different enforcement levels?

Skills support BLOCK (physically prevents execution until conditions are met), SUGGEST (injects helpful context), and WARN (provides advisory reminders).

Claude Skill Developer

Name: Claude Skill Developer
Author: Microck

byMicrock

•

開発者ツール

Orchestrates the creation, management, and optimization of specialized Claude Code skills following Anthropic's architectural best practices.

概要

The Claude Skill Developer serves as a comprehensive framework for building and maintaining domain-specific capabilities within the Claude Code environment. It provides a structured approach to implementing the two-hook architecture—UserPromptSubmit for proactive suggestions and PreToolUse for critical guardrails—ensuring that AI agents adhere to project-specific patterns and safety rules. By leveraging trigger patterns in skill-rules.json and enforcing the 500-line rule for documentation, this skill helps developers create highly efficient, auto-activating assistants that scale with complex codebases.

主な機能

Standardized SKILL.md template generation with YAML frontmatter management
Automated trigger configuration for keywords, intent patterns, and file paths
81 GitHub stars
Two-hook architecture support for proactive context injection and safety blocks
Integrated testing and debugging workflows for skill activation logic
Session-aware enforcement levels to prevent repetitive AI prompting

ユースケース

Managing complex skill hierarchies using progressive disclosure and reference patterns
Establishing project-wide coding guardrails to prevent common architectural mistakes
Developing domain-specific documentation that surfaces automatically based on developer intent

概要

主な機能

Standardized SKILL.md template generation with YAML frontmatter management
Automated trigger configuration for keywords, intent patterns, and file paths
81 GitHub stars
Two-hook architecture support for proactive context injection and safety blocks
Integrated testing and debugging workflows for skill activation logic
Session-aware enforcement levels to prevent repetitive AI prompting

ユースケース

Managing complex skill hierarchies using progressive disclosure and reference patterns
Establishing project-wide coding guardrails to prevent common architectural mistakes
Developing domain-specific documentation that surfaces automatically based on developer intent