skill-creator

Draft and evaluate AI skills with YAML frontmatter and SKILL.md structure.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/Nima-MM/agentic-consultant --skill skill-creator-nima-mm
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/Nima-MM/agentic-consultant/tree/main/.agents/skills/shared/skill-creator
Command: npx skills add https://github.com/Nima-MM/agentic-consultant --skill skill-creator-nima-mm

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires anthropic, google-generativeai, pyyaml, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

Skill authors need a repeatable, testable process to create, evaluate, and improve AI skills. This description helps teams accelerate crafting robust SKILL.md files, scripts, and references while maintaining clarity and safety.

Core Features & Use Cases

  • End-to-end skill creation workflow (draft, test prompts, evaluate, iterate)
  • Built-in guidance for testing, evals, benchmarking, and triggering optimization
  • Support for modular resources (scripts, references, assets) to extend capabilities
  • Scales from simple to advanced skills with structured loading and progressive disclosure

Quick Start

Draft a new skill, run an initial eval, and begin an iteration loop to refine the description and triggering behavior.

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 evaluate AI skills using a structured prompt-engineering workflow?

To create and evaluate AI skills, you draft modular units with YAML frontmatter and a SKILL.md body, then apply iterative evaluation and benchmarking to ensure robust activation across contexts.

What is the best way to structure AI skills for maintainability and progressive disclosure?

The best way to structure AI skills is organizing content in a maintainable repository, leveraging optional scripts, references, and assets to extend capabilities while scaling from simple to advanced configurations.

Can I use Anthropic and Google Generative AI models to benchmark skill triggering behavior?

Yes, you can use Anthropic and Google Generative AI dependencies to run evaluations and benchmark skill triggering behavior, optimizing performance across various contexts.

How do I run an iteration loop to refine AI workflow descriptions and triggering optimization?

You run an iteration loop by drafting a new skill, executing an initial evaluation, and continuously refining the SKILL.md description and triggering behavior based on benchmarking results.

Do I need YAML configuration to build modular AI skills with scripts and references?

Yes, you need YAML frontmatter to define modular AI skills, alongside a detailed SKILL.md body, to properly integrate optional scripts, references, and assets into your workflow.