What is the 500-line rule in Claude Code skills?

The 500-line rule is an Anthropic best practice requiring the main SKILL.md file to stay under 500 lines. Detailed documentation should be moved to reference files to ensure Claude processes the skill quickly and efficiently.

How do triggers work for these skills?

Skills are activated through four primary trigger types: explicit keywords, regex-based intent patterns, specific file path globs, or content detection patterns found within your code files.

How can I prevent a skill from nagging me repeatedly?

The system uses session tracking to remember if a skill has already been triggered in the current session. Additionally, you can use the '// @skip-validation' marker in specific files to permanently bypass skill checks.

What is the difference between BLOCK and SUGGEST enforcement?

BLOCK enforcement physically prevents a tool from executing (like 'Edit') until a requirement is met, ideal for safety guardrails. SUGGEST enforcement injects advice into the prompt context without stopping the developer's workflow.

Claude Skill Developer

Name: Claude Skill Developer
Author: Activer007

byActiver007

0•

开发者工具

Streamlines the creation and management of custom Claude Code skills using Anthropic best practices and automated trigger patterns.

This skill provides a comprehensive framework for developers to extend Claude Code's capabilities through custom-built skills and guardrails. It guides users through the two-hook architecture—proactive suggestions via UserPromptSubmit and reactive reminders via Stop hooks—ensuring that domain-specific guidance is delivered at the right moment. By enforcing standards like the 500-line rule and progressive disclosure, it helps maintain high performance while providing robust documentation for complex coding environments and safety protocols.

主要功能

01Dual-hook architecture implementation for proactive and reactive guidance

02CLI-based testing utilities for validating trigger patterns and hook execution

030 GitHub stars

04Comprehensive management of skill-rules.json for keyword and intent triggers

05Session-aware state management to prevent repetitive notifications

06Standardized skill structure generation with YAML frontmatter

使用场景

01Building domain-specific documentation sets that activate automatically based on file paths

02Standardizing team-wide coding patterns through automated suggestions and enforcement levels

03Creating custom guardrails to prevent critical database or security errors during development

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add activer007/ordinary-claude-skills skill-developer

For use in Claude.ai and ChatGPT

Download Skill