skill-creator

Draft, evaluate, and iterate on AI skills with structured evals.

Updated Mar 13, 2026

Search Tags:#automation #workflow #evaluation #iteration #quality-assurance #skill-creation #prompt-engineering

Ready to run

npx skills add https://github.com/marinvch/ai-os --skill skill-creator-marinvch

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/marinvch/ai-os/tree/main/skill-creator
Command: npx skills add https://github.com/marinvch/ai-os --skill skill-creator-marinvch

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill enables teams and individuals to create new skills, iteratively improve existing ones, and measure performance with structured evals and benchmarking, reducing iteration time and increasing reliability.

Core Features & Use Cases

Draft and package SKILL.md frontmatter and body for a skill, including optional bundled resources.
Run automated eval loops that spawn with-skill and baseline runs, collect results, and compute metrics.
Iterate against feedback: generate improved descriptions, test prompts, and refine the skill through multiple iterations.
Benchmark outcomes across configurations to guide optimization and decision-making.

Quick Start

Use the run_loop workflow to draft, evaluate, and iterate on this Skill until it meets your needs.

Frequently Asked Questions about skill-creator

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

FAQPage Schema

How do I iterate on prompt engineering to improve AI skill quality?▼

To improve AI skill quality, run automated evaluation loops that spawn baseline and with-skill runs, collect performance metrics, and refine descriptions or test prompts across multiple iterations.

What is the process for packaging a new AI skill with reproducible guardrails?▼

Packaging an AI skill involves drafting the SKILL.md frontmatter and body, bundling optional resources, and applying structured evaluations to ensure reproducible guardrails and measurement across iterations.

Can I benchmark skill performance across different configurations?▼

Yes, you can benchmark skill performance across different configurations to guide optimization and decision-making by comparing outcomes from automated evaluation loops.

Does this skill creation workflow require external dependencies?▼

No, this skill creation workflow requires no external dependencies, allowing teams and individuals to draft, evaluate, and iterate on capabilities immediately without environment setup barriers.

What's the best way to reduce iteration time when modifying an existing skill?▼

The best way to reduce iteration time is using the run_loop workflow to generate improved descriptions, test prompts against baselines, and apply feedback through structured automated evaluations.