skill-creator

Creates Skill .md files with optimized metadata and layered Swiss Army knife-style packaging for LLM agents.

Updated May 4, 2026
One-click install
npx skills add https://github.com/234194027-cpu/xianclaw --skill skill-creator-234194027-cpu
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/234194027-cpu/xianclaw/tree/main/resources/skills/skill-creator
Command: npx skills add https://github.com/234194027-cpu/xianclaw --skill skill-creator-234194027-cpu

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) and scripts (resource) components.

What problem does it solve?

This skill helps you design and write high-quality SKILL.md packages with clear triggers, efficient instructions, and properly organized optional resources so Claude can use them reliably.

Core Features & Use Cases

  • Skill discovery-ready metadata: Ensures the required YAML frontmatter includes a precise name and description for correct activation.
  • Efficient context design: Guides you to keep SKILL.md concise and to use progressive disclosure (metadata → body → bundled resources) to minimize context bloat.
  • Reusable structure planning: Recommends when to use scripts for deterministic tasks, references for in-depth documentation, and assets for output templates/files.

Quick Start

Use the skill guidance to write a new SKILL.md for your custom capability and package it into a distributable .skill file after completing the YAML frontmatter.

Frequently Asked Questions about skill-creator

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

FAQPage Schema
How do I create a SKILL.md package for Claude?

To create a SKILL.md package, you define required YAML frontmatter for skill discovery, structure concise instructions in the body, and bundle optional resources like scripts or references. This ensures reliable activation and progressive disclosure to minimize context bloat.

What is progressive disclosure in skill authoring?

Progressive disclosure in skill authoring is a design pattern that structures context delivery from metadata to body to bundled resources. It minimizes context bloat by loading detailed references only when needed, keeping the core SKILL.md concise for efficient Claude activation.

When should I use scripts versus references in a custom skill?

Use scripts for deterministic tasks that require reliable execution and references for in-depth documentation. Scripts handle fixed operations while references provide specialized knowledge, ensuring your skill package uses concise context efficiently without redundant processing.

How do I package a custom skill into a distributable file?

You package a custom skill into a distributable file by completing the YAML frontmatter and structuring the SKILL.md body. After defining triggers and bundling resources, the skill is compiled into a distributable package meeting repository validation expectations.

Does skill authoring require specific dependencies or frameworks?

Skill authoring requires no external dependencies or frameworks. You build skills by writing YAML frontmatter and markdown instructions, optionally bundling scripts, references, and assets to extend Claude with specialized workflows and tool integrations.

Why does my custom skill fail to activate reliably in Claude?

Custom skills fail to activate reliably when the YAML frontmatter lacks a precise name and description for skill discovery. Effective skill authoring requires clear triggers and concise context design to ensure Claude processes the instructions correctly.