skills.rest
leodinhsa
leodinhsaCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

skill-creator

Create, test, and iterate AI skills with evaluation cycles.

1|Updated Mar 4, 2026
Search Tags:#automation#iteration#skill-creation#prompt-engineering#evals#ai-skills
One-click install
npx skills add https://github.com/leodinhsa/skillops --skill skill-creator-leodinhsa
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/leodinhsa/skillops/tree/main/.kiro/skills/skill-creator
Command: npx skills add https://github.com/leodinhsa/skillops --skill skill-creator-leodinhsa

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires anthropic, PyYAML, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

Automates the end-to-end process of creating, testing, and iterating AI skills, reducing manual guesswork and speeding up refinement.

Core Features & Use Cases

  • Skill creation and iteration: Scaffold new skills, iterate with live evals, and measure performance.
  • Evals, benchmarking, and improvement loop: Run trigger evaluations, compare against baselines, and improve skill descriptions.
  • Tooling and packaging: Includes scripts for validation, benchmarking, and packaging into deployable skill bundles.

Quick Start

Start by providing an initial SKILL.md and a basic eval set to seed the iterative improvement loop.

Frequently Asked Questions about skill-creator

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

FAQPage Schema
How do I automate AI skill creation and testing?▼

Automate AI skill creation by providing an initial SKILL.md and a basic eval set to seed the iterative improvement loop. This reduces manual guesswork and accelerates refinement across multiple evaluation cycles.

What is the best way to iterate on prompt engineering and evaluate AI skills?▼

The best way to iterate on prompt engineering is running live trigger evaluations, comparing against baselines, and measuring performance. This automated improvement loop systematically refines skill descriptions and resources.

Do I need Python dependencies to run evals and benchmark AI skills?▼

Yes, you need Python dependencies including the anthropic library and PyYAML to run evals and benchmark AI skills. These packages support the scripts required for validation and performance measurement.

Can I use automation to package and deploy AI skills?▼

Yes, you can use automation to package AI skills into deployable bundles. The system includes scripts for validation and benchmarking, ensuring the skill metadata and resources are fully refined before deployment.

Why does manual skill creation slow down AI prompt refinement?▼

Manual skill creation slows down AI prompt refinement because it relies on guesswork without automated benchmarking. Iterative evaluation loops are required to systematically measure performance and refine metadata across cycles.

Related Skills

Explore More Software Engineering Skills→
saahilvasdevsaahilvasdev

skill-creator

Automate Claude Skill creation and iterative improvement via eval-driven loops.

Community
Advanced
OpenElementsLabsOpenElementsLabs

skill-creator

Automate the end-to-end lifecycle of Claude Code skills.

Official
Advanced
romiluz13romiluz13
161

skill-authoring

Author AI Skills with valid SKILL.md structure and metadata.

Community
Basic
yasuwrldhyperyasuwrldhyper

skill-creator

Create and refine AI skills with SKILL.md metadata and benchmark testing.

Community
Advanced