skill-creator

Create and refine Claude skills through iterative drafting, testing, and evaluation.

1|Updated Apr 2, 2026
One-click install
npx skills add https://github.com/775266553/aispeak --skill skill-creator-775266553
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/775266553/aispeak/tree/main/skills/skill-creator
Command: npx skills add https://github.com/775266553/aispeak --skill skill-creator-775266553

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pyyaml.

What problem does it solve?

Automates the end-to-end workflow for designing, testing, and refining Claude skills through iterative evaluation, saving time and improving triggering accuracy.

Core Features & Use Cases

  • Create new skills, modify existing ones, run evals, benchmark performance, and iterate based on results.
  • Provides a library-style workflow to handle prompts, test prompts, and manage iterations.
  • Supports description optimization and evidence-based improvements.

Quick Start

Draft your skill, run an initial eval loop, review results, and iterate until performance stabilizes.

Frequently Asked Questions about skill-creator

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

FAQPage Schema
How do I automate Claude skill creation and evaluation?

Automate Claude skill creation and evaluation by drafting a skill, running an initial eval loop, reviewing benchmarking results, and iterating until triggering performance stabilizes.

What is the best way to optimize Claude skills for accurate triggering?

The best way to optimize Claude skills for accurate triggering is through an iterative workflow of testing, benchmarking performance, and refining descriptions based on evaluation evidence.

Can I benchmark existing Claude skills to improve their performance?

Yes, you can benchmark existing Claude skills by running evaluation loops, analyzing test prompt results, and applying evidence-based modifications to improve overall performance.

Do I need pyyaml to run iterative skill evaluations?

Yes, pyyaml is required as a dependency to support the evaluation workflow and manage the YAML-based configuration files used during skill iteration and testing.

How does the skill iteration workflow handle documentation?

The skill iteration workflow handles documentation by generating vector-friendly SKILL.md files and optional bundled resources to streamline skill usage and retrieval.

Why should I use an iterative evaluation loop for Claude skills instead of manual testing?

An iterative evaluation loop replaces manual testing by automating test prompt execution, benchmarking results, and providing evidence-based improvements to refine skill accuracy systematically.