skills.rest
oto1720
oto1720COMMUNITY
Explore all skills by this author →
GitHub

skill-creator

Scaffold, test, and refine Claude Skills with SKILL.md frontmatter and trigger evaluations.

1|Updated Feb 23, 2026
Search Tags:#automation#testing#markdown#evaluation#iteration#skill#prompt-engineering
One-click install
npx skills add https://github.com/oto1720/claude-agents-skills --skill skill-creator-oto1720
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/oto1720/claude-agents-skills/tree/main/skills/skill-creator
Command: npx skills add https://github.com/oto1720/claude-agents-skills --skill skill-creator-oto1720

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

The Skill Creator enables teams to quickly scaffold, test, and iteratively improve Claude Skills by providing a structured workflow to capture intents, design SKILL.md frontmatter, run trigger evaluations, and refine descriptions based on evaluation results.

Core Features & Use Cases

  • Draft new skills with a formal SKILL.md frontmatter and a detailed instruction body.
  • Run trigger evaluations, capture metrics, and compare configurations (with_skill vs without_skill).
  • Iterate on skill descriptions and test prompts to improve triggering accuracy and robustness.
  • Package skills into distributable .skill files and validate integrity before distribution.

Quick Start

Describe a skill goal and use the Skill Creator to scaffold a SKILL.md, run a first round of trigger evaluations, and iteratively refine the description and tests 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 scaffold a new Claude skill with proper markdown frontmatter?▼

To create a Claude skill, you scaffold a formal SKILL.md file with structured frontmatter and a detailed instruction body to define the skill's intents and behavior.

How do I evaluate and test Claude skill triggering accuracy?▼

You evaluate Claude skill triggering by running trigger evaluations that capture metrics, comparing configurations with and without the skill to measure and improve triggering accuracy.

What is the best way to iteratively refine prompt descriptions for better skill activation?▼

The best way to refine skill activation is to iterate on skill descriptions and test prompts based on evaluation results, ensuring robust triggering accuracy and comprehensive test coverage.

Can I package and validate markdown skills for distribution as .skill files?▼

Yes, you can package skills into distributable .skill files and validate their integrity before distribution to ensure they are ready for deployment.

Do I need anthropic and pyyaml dependencies to run skill evaluations?▼

Yes, you need the anthropic and pyyaml dependencies installed in your environment to scaffold, run trigger evaluations, and manage the SKILL.md frontmatter processing.

Why does my Claude skill fail to trigger reliably during prompt testing?▼

Unreliable triggering happens when descriptions are poorly aligned with intents; you resolve this by running iterative trigger evaluations and refining descriptions based on captured metrics.

Related Skills

Explore More Software Engineering Skills→
Fudan-SMI-labFudan-SMI-lab
39

torch-npu-pyyaml-preinstall

Preinstall PyYAML before torch-npu to prevent transitive dependency failures.

Official
Intermediate
cogni-daocogni-dao
4

skill-creator

Draft and refine Claude skill descriptions with evaluation loops and benchmarking.

Official
Advanced
danielscholldanielscholl
23

test-framework

Validate plugin skills across four layers with dry-run and JSON CI outputs.

Community
Advanced
l395624064l395624064

skill-creator

Create, modify, and evaluate Claude skills from draft to deployment.

Community
Advanced