skill-developer

Create and configure Claude Code skills with trigger rules and hook-based activation.

Updated Dec 1, 2025
One-click install
npx skills add https://github.com/Boulea7/ohmyclaude --skill skill-developer-boulea7
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-developer
Source: https://github.com/Boulea7/ohmyclaude/tree/main/src/ohmyclaude/templates/skills/skill-developer
Command: npx skills add https://github.com/Boulea7/ohmyclaude --skill skill-developer-boulea7

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Building effective Claude Code skills requires understanding YAML frontmatter, trigger configuration, hook mechanics, and enforcement levels, and mistakes in skill-rules.json cause skills to never activate or fire incorrectly. ## Core Features & Use Cases - Skill Authoring Guidance: Step-by-step process for creating SKILL.md files with proper frontmatter, the 500-line rule, and progressive disclosure via reference files. - Trigger Configuration: Complete reference for keywords, intent regex patterns, file path globs, and content patterns in skill-rules.json, plus a copy-paste pattern library. - Hook Mechanics & Debugging: Deep documentation of UserPromptSubmit and PreToolUse hook flows, exit code behavior, session state tracking, and a full troubleshooting guide. - Use Case: When adding a new guardrail skill that blocks Prisma edits until schema verification, use this Skill to write the SKILL.md, configure block enforcement with skip conditions, and test the hooks with npx tsx commands. ## Quick Start Ask the AI to create a new Claude Code skill with trigger rules for a specific topic using the skill-developer guide.

Frequently Asked Questions about skill-developer

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

FAQPage Schema
How do I create a new Claude Code skill?▼

Create a SKILL.md file in .claude/skills/{name}/ with YAML frontmatter containing name and description, then add a matching entry to skill-rules.json with trigger conditions. Test the triggers with npx tsx against the hook scripts and keep the file under 500 lines.

How do skill trigger patterns work in skill-rules.json?▼

Triggers include keywords for case-insensitive substring matching, intentPatterns as regex for implicit actions, pathPatterns as globs for file locations, and contentPatterns as regex matched against file contents. Combine them per skill depending on whether it is a guardrail or domain skill.

What is the difference between block, suggest, and warn enforcement?▼

Block uses the PreToolUse hook with exit code 2 to physically prevent Edit or Write until the skill is used. Suggest injects a reminder via UserPromptSubmit before Claude sees the prompt. Warn is a low-priority advisory that is rarely used.

Why is my skill not triggering in Claude Code?▼

Common causes are keywords missing from the prompt, overly specific intent regex, a name mismatch between SKILL.md and skill-rules.json, or invalid JSON. Validate the JSON with jq and test the hook manually by piping a sample prompt to skill-activation-prompt.ts.

How do I stop a guardrail skill from blocking repeatedly?▼

Session tracking automatically allows edits after the skill is used once per session. You can also add a // @skip-validation marker to a file or set an environment variable like SKIP_SKILL_GUARDRAILS for an emergency override.