skill-developer

Generate semantic metadata from Skill Unit documents for RAG retrieval.

111|21|Updated Sep 17, 2025
One-click install
npx skills add https://github.com/Dimon94/cc-devflow --skill skill-developer-dimon94
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-developer
Source: https://github.com/Dimon94/cc-devflow/tree/main/.claude/skills/skill-developer
Command: npx skills add https://github.com/Dimon94/cc-devflow --skill skill-developer-dimon94

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides a comprehensive guide for creating, managing, and debugging Claude Code skills, ensuring they follow Anthropic's best practices. It streamlines the process of extending AI capabilities and maintaining a high-quality, efficient skill ecosystem.

Core Features & Use Cases

  • Skill Creation Workflow: Guides users through creating new skills, defining triggers (keywords, intent, file paths, content), and configuring enforcement levels (block, suggest, warn).
  • Hook Mechanism Deep Dive: Explains how UserPromptSubmit and PreToolUse hooks work for proactive suggestions and real-time guardrails, including critical exit code behavior.
  • Best Practices & Troubleshooting: Enforces the "500-line rule," progressive disclosure, and offers detailed debugging steps for skill activation issues.
  • Use Case: A developer wants to create a new skill to enforce specific code review guidelines. This skill provides the exact steps, templates, and best practices to build, test, and deploy that new skill effectively.

Quick Start

To create a new skill, start by creating a SKILL.md file in .claude/skills/{skill-name}/ and then add its configuration to skill-rules.json.

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 from scratch?

Create a new skill by starting with a `SKILL.md` file in `.claude/skills/{skill-name}/`, then add its configuration to `skill-rules.json`. The skill creation workflow guides you through defining triggers (keywords, intent, file paths, content) and configuring enforcement levels (block, suggest, warn).

What are hook mechanisms and how do they enforce guardrails in real time?

Hook mechanisms use `UserPromptSubmit` and `PreToolUse` hooks to apply proactive suggestions and real-time guardrails. They intercept requests at critical points, including exit code behavior, enabling precise control over skill activation and enforcement.

Why is the 500-line rule important when building skills?

The 500-line rule enforces progressive disclosure and maintains skill efficiency. Following this best practice ensures skills remain focused, performant, and easier to debug when activation issues arise.

How do I troubleshoot a skill that isn't activating properly?

Troubleshooting involves extracting semantic metadata from `SKILL.md`, `TROUBLESHOOTING.md`, and `HOOK_MECHANISMS.md` documents, then validating the request paragraph, agent decision logic, and toxicity assessment output formats.

Can I apply best practices from Anthropic when designing custom skills?

Yes. This skill provides a comprehensive guide aligned with Anthropic's best practices for skill creation, management, and debugging, ensuring your custom skills follow production-grade standards for the skill ecosystem.

What metadata structure is required for skill-based AI automation?

Skills require semantic metadata including a request field (three declarative sentences), a description field following the [Action] [Input] to produce [Output] pattern, and a toxicity_check field with is_toxic and toxic_reason for RAG-based retrieval and reasoning.