skill-developer

Create and manage Claude Code skills with YAML frontmatter and skill-rules.json triggers.

6|8|Updated May 7, 2026
One-click install
npx skills add https://github.com/TorchedHat/ai-marketplace --skill skill-developer-torchedhat
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-developer
Source: https://github.com/TorchedHat/ai-marketplace/tree/main/deterministic-hook/skills/skill-developer
Command: npx skills add https://github.com/TorchedHat/ai-marketplace --skill skill-developer-torchedhat

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps developers create, configure, test, and troubleshoot Claude Code skills without losing track of structure, activation behavior, or enforcement rules.

Core Features & Use Cases

  • Skill Structure Guidance: Create valid skills with YAML frontmatter, focused instructions, progressive disclosure, and the 500-line rule.
  • Trigger Configuration: Define and refine keyword, intent, file-path, and content-pattern triggers in skill-rules.json.
  • Hook and Guardrail Debugging: Understand UserPromptSubmit and PreToolUse hooks, exit-code behavior, session tracking, skip conditions, and common activation failures.
  • Use Case: When a new domain skill does not activate reliably, use this guide to inspect its metadata, refine matching patterns, validate configuration, and test the hooks against realistic prompts and files.

Quick Start

Use the skill-developer skill to create or troubleshoot a Claude Code skill and verify its triggers, frontmatter, hook behavior, and progressive-disclosure structure.

Frequently Asked Questions about skill-developer

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I configure Claude Code skill triggers so they activate reliably?

To configure Claude Code skill triggers, define keyword, intent, file-path, and content-pattern matching rules in skill-rules.json. Refining these patterns ensures the skill activates reliably against realistic user prompts and files.

What is progressive disclosure and the 500-line rule when building Claude Code skills?

Progressive disclosure structures Claude Code skills with focused instructions and valid YAML frontmatter, while the 500-line rule limits skill length to maintain operational guidance and enforcement reliability without overwhelming context.

Why does my Claude Code skill hook not activate or skip unexpectedly?

Claude Code skill hooks fail or skip unexpectedly due to incorrect exit-code behavior, invalid session tracking, or unmet skip conditions in UserPromptSubmit and PreToolUse hooks. Inspect hook configurations to validate execution paths.

How do I create valid YAML frontmatter and skill-rules.json for a new Claude Code skill?

Create valid YAML frontmatter for Claude Code skills by defining required metadata fields, then ensure skill-rules.json consistency by mapping triggers and guardrails directly to those declared metadata properties.

Can I debug UserPromptSubmit and PreToolUse hooks for Claude Code skills?

You can debug UserPromptSubmit and PreToolUse hooks by validating exit-code behavior, checking session-aware enforcement rules, and testing skip conditions against realistic prompts to isolate common activation failures.