How do skill triggers work in Claude Code?

Skills are activated through keywords in prompts, specific user intents, file path glob patterns, or regex patterns detected within file contents.

What is the difference between a guardrail and a domain skill?

Guardrail skills enforce critical safety rules and can block actions, while domain skills provide advisory best practices and architectural guidance.

How do hooks enhance Claude's capabilities?

Hooks like UserPromptSubmit inject context before Claude sees a prompt, while PreToolUse allows for validation or blocking of tools before they execute.

What is the 500-line rule for Claude skills?

It is a performance best practice requiring SKILL.md files to be under 500 lines to ensure Claude processes instructions efficiently without wasting tokens.

Claude Skill Developer Guide

Name: Claude Skill Developer Guide
Author: chriskrycho

bychriskrycho

•

开发者工具

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

关于

The Skill Developer Guide is a meta-utility designed to help developers build and maintain custom capabilities within Claude Code. It provides a standardized framework for implementing the two-hook architecture—UserPromptSubmit for proactive suggestions and PreToolUse for resource validation—ensuring that custom skills are both performant and non-intrusive. By enforcing the 500-line rule and progressive disclosure patterns, this skill ensures that domain-specific guidance remains concise and effective while managing complex trigger patterns and session-aware guardrails.

主要功能

Advanced trigger systems using keywords, intent patterns, and regex content detection
Multi-level enforcement including block, suggest, and warn mechanisms
PreToolUse validation to prevent excessive token usage and large file reads
Session tracking and file markers to prevent repetitive AI notifications
1 GitHub stars
Comprehensive templates for creating SKILL.md and skill-rules.json files

使用场景

Developing custom domain-specific guidance for private enterprise repositories
Implementing safety guardrails to prevent accidental database or infrastructure errors
Standardizing documentation and coding patterns across large engineering teams

关于

主要功能

Advanced trigger systems using keywords, intent patterns, and regex content detection
Multi-level enforcement including block, suggest, and warn mechanisms
PreToolUse validation to prevent excessive token usage and large file reads
Session tracking and file markers to prevent repetitive AI notifications
1 GitHub stars
Comprehensive templates for creating SKILL.md and skill-rules.json files

使用场景

Developing custom domain-specific guidance for private enterprise repositories
Implementing safety guardrails to prevent accidental database or infrastructure errors
Standardizing documentation and coding patterns across large engineering teams