skills.rest
lucasmiachon-blip
lucasmiachon-blipCOMMUNITY
Explore all skills by this author →
GitHub

skill-creator

Define, test, and iterate Claude Skills with frontmatter-driven workflows.

Updated Jan 25, 2026
Search Tags:#workflow#evaluation#packaging#iteration#skill-creation#prompt-engineering
One-click install
npx skills add https://github.com/lucasmiachon-blip/organizacao --skill skill-creator-lucasmiachon-blip
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/lucasmiachon-blip/organizacao/tree/main/.claude/skills/skill-creator
Command: npx skills add https://github.com/lucasmiachon-blip/organizacao --skill skill-creator-lucasmiachon-blip

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pyyaml.

What problem does it solve?

This Skill provides a structured workflow to design, test, and iterate Claude Skills from discovery to deployment, reducing time to first working skill and improving reliability.

Core Features & Use Cases

  • Frontmatter-driven discovery: define a skill's identity and description in SKILL.md.
  • Trigger-evaluation loop: run evals, analyze results, and iterate using the built-in improve_description workflow.
  • Benchmarking and description optimization: generate reports, compare configurations, and optimize triggering accuracy.
  • Packaging and distribution: validate, bundle, and publish .skill artifacts for reuse.

Quick Start

Create SKILL.md with a name and description, then run the evaluation loop to iterate until triggering is reliable.

Frequently Asked Questions about skill-creator

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

FAQPage Schema
How do I create and iterate Claude Skills using a frontmatter-driven workflow?▼

To create and iterate Claude Skills, you define a skill's identity and description in a SKILL.md file, run trigger evaluations, analyze the results, and refine the description until triggering is reliable.

What is the best way to evaluate triggering accuracy for prompt engineering workflows?▼

The best way to evaluate triggering accuracy is to run automated evals that test the skill's description against various inputs, generate reports, and guide iterative improvements for optimal performance.

How do I package and share skills as portable .skill files?▼

You package and share skills by validating the SKILL.md configuration, bundling the artifacts, and exporting them as portable .skill files for distribution and reuse across different environments.

Do I need pyyaml to define and test skills using this workflow?▼

Yes, you need the pyyaml dependency installed in your environment to parse the frontmatter-driven configuration files required to define, test, and iterate on skills.

When should I use automated evals for skill-creation and description optimization?▼

You should use automated evals for skill-creation when you need to benchmark triggering accuracy, compare different configuration setups, and systematically optimize how reliably a skill is discovered.

Related Skills

Explore More Software Engineering Skills→
coreyjacoreyja
12

skill-writer

Draft SKILL.md frontmatter and structure guidance for Claude Code skills.

Community
Basic
CHENyiru3CHENyiru3

skill-creator

Automate end-to-end creation, evaluation, and refinement of Claude Code skills.

Community
Advanced
slowman2084slowman2084
6

meta-retrospective

Analyze prompt histories to detect anti-patterns and generate retrospective reports.

Community
Advanced
PatkikPatkik

skill-creator

Automate Claude Skill design, testing, and refinement workflows.

Community
Advanced