skill-creator

Guide creation of SKILL.md files and coordinate evals, benchmarks, and iteration.

38|3|Updated Apr 8, 2026

Search Tags:#workflow #evaluation #iteration #benchmark #skill #prompt-engineering

Ready to run

npx skills add https://github.com/pipixia-labs/creative-claw --skill skill-creator-pipixia-labs

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/pipixia-labs/creative-claw/tree/main/skills/skill-creator
Command: npx skills add https://github.com/pipixia-labs/creative-claw --skill skill-creator-pipixia-labs

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pyyaml, and includes scripts (resource) components.

What problem does it solve?

The Skill Creator guides teams to craft, iterate, and enhance Claude skills by providing a repeatable flow for writing SKILL.md, running evals, benchmarking, and optimizing descriptions to improve triggering accuracy.

Core Features & Use Cases

Create and modify skills with structured SKILL.md frontmatter and instructional body.
Run evals and benchmarks to measure trigger accuracy, performance, and reliability.
Iterate and optimize skill descriptions, prompts, and supporting scripts based on results, and package skills for deployment.

Quick Start

Draft SKILL.md, run evals and benchmarks, review results, and 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 test a Claude skill from scratch?▼

Create a Claude skill by drafting a SKILL.md file with frontmatter and instructions, then run evals and benchmarks to measure trigger accuracy and iterate until performance is reliable.

What is a SKILL.md file and how does it control skill triggering?▼

A SKILL.md file uses structured frontmatter and an instructional body to define trigger conditions and execution instructions, enabling Claude to accurately identify when to apply the skill.

How do I run evals and benchmarks to measure prompt-engineering accuracy?▼

Run evals and benchmarks through a repeatable loop that tests trigger accuracy and reliability across iterations, collects metrics, and generates reports to guide prompt optimization.

Do I need pyyaml to build and benchmark skills?▼

Yes, pyyaml is a required dependency for the Skill Creator, used to parse and manage the structured YAML frontmatter in SKILL.md files during the creation and iteration workflow.

What is the best way to optimize skill descriptions for better triggering?▼

The best way to optimize skill descriptions is to iterate through a loop of running evals, reviewing benchmark reports, and refining SKILL.md content and test prompts based on collected performance metrics.

Why does my skill fail to trigger reliably across different prompts?▼

Unreliable skill triggering usually stems from poorly defined SKILL.md descriptions, which you can fix by running benchmarks, analyzing metric reports, and iterating on trigger instructions until accuracy improves.