skill-creator

Design, test, and package Claude skills with SKILL.md files.

15|6|Updated May 7, 2026
One-click install
npx skills add https://github.com/MinhThang1009/dotclaude --skill skill-creator-minhthang1009
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/MinhThang1009/dotclaude/tree/main/plugins/skill-creator/skills/skill-creator
Command: npx skills add https://github.com/MinhThang1009/dotclaude --skill skill-creator-minhthang1009

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps teams design, test, and optimize Claude skills by guiding the full lifecycle from drafting SKILL.md to evaluating and iterating through feedback.

Core Features & Use Cases

  • Capture Intent: Understand user goals and decide how the skill should behave.
  • SKILL.md Crafting: Define a clear, front-mattered entry point and a detailed body with instructions.
  • Evaluation Loop: Run trigger evaluations and gather results to measure how well a skill triggers.
  • Iteration & Improvement: Use feedback to refine the description and behavior, then repeat.
  • Reporting & Packaging: Produce summaries, reports, and optionally package as a distributable skill file.

Quick Start

Draft a new SKILL.md that defines the skill's name and description, then run trigger evaluations and iterate based on the results.

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 Claude skill from scratch?

To create a Claude skill, you draft a SKILL.md file that defines the skill's name, description, and frontmatter schema, then write a detailed instruction body to support reliable triggering and repeatable testing across teams.

What is the best way to structure a SKILL.md file for prompt engineering?

The best way to structure a SKILL.md file is to define a clear frontmatter schema for the entry point and a detailed body with instructions, ensuring the skill's scope and intent are captured for reliable evaluation and iteration.

How do I evaluate and iterate on automation workflows for Claude skills?

You evaluate and iterate on Claude skills by running trigger evaluations to gather results, then using that feedback to refine the description and behavior in the SKILL.md file, repeating the loop to measure and improve triggering performance.

Do I need any dependencies to build and package Claude skills?

No dependencies are required to build and package Claude skills. You can independently draft the SKILL.md file, run trigger evaluations, and generate distributable skill files or reports without any external frameworks.

Can I use skill-creator to generate documentation for existing workflows?

Yes, you can use it to generate documentation by capturing user goals and defining the skill's scope, producing summaries and reports that package the workflow into a clear, front-mattered entry point for team distribution.

Why are my Claude skills not triggering reliably in the evaluation loop?

Skills may not trigger reliably if the description and behavior lack precision. You must iterate based on evaluation feedback, refining the frontmatter schema and instruction body in the SKILL.md file to support reliable triggering.