skills.rest
UnicomAI
UnicomAICOMMUNITY
Explore all skills by this author →
GitHub

skill-creator

Create, test, and refine AI skills defined in SKILL.md files.

2.6k|130|Updated Jun 6, 2025
Search Tags:#skill development#testing#prompt engineering#AI agent#evaluation#iteration
One-click install
npx skills add https://github.com/UnicomAI/wanwu --skill skill-creator-unicomai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/UnicomAI/wanwu/tree/main/configs/microservice/bff-service/configs/agent-skills/anthropics/skill-creator
Command: npx skills add https://github.com/UnicomAI/wanwu --skill skill-creator-unicomai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill streamlines the entire process of creating, improving, and evaluating AI skills, making it easier to build powerful custom AI capabilities.

Core Features & Use Cases

  • Skill Creation: Guides users through defining intent, writing SKILL.md, and structuring skill resources.
  • Iterative Improvement: Facilitates testing, evaluation, and refinement of skills based on performance metrics and user feedback.
  • Description Optimization: Enhances skill triggering accuracy by testing and optimizing the description field.
  • Use Case: A developer wants to create a new skill to summarize meeting transcripts. They use this Skill to draft the SKILL.md, write test cases, run evaluations, analyze the results, and iterate on the skill's description and logic until it performs optimally.

Quick Start

Use the skill-creator to help me build a new skill that can summarize text documents.

Frequently Asked Questions about skill-creator

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

FAQPage Schema
How do I build and test an AI skill from scratch?▼

To build and test an AI skill, you define its intent and logic in a SKILL.md file, then use automated testing with baselines to evaluate performance and iterate on the results.

What is the best way to improve AI agent triggering accuracy?▼

Improving AI agent triggering accuracy involves testing and optimizing the description field within your skill definition, ensuring the prompt engineering aligns with quantitative evaluation metrics.

Can I run quantitative evaluations on my prompt engineering logic?▼

Yes, you can run quantitative evaluations on prompt engineering logic by integrating with execution environments to measure performance against established baselines during the iteration process.

How does iterative refinement work for AI skill development?▼

Iterative refinement for AI skill development works by analyzing performance metrics from automated testing, allowing you to continuously adjust the SKILL.md and skill resources until optimal behavior is reached.

Do I need specific dependencies to structure skill resources?▼

No specific dependencies are required to structure skill resources; you can organize your scripts, references, and assets natively while defining the core logic within the SKILL.md file.

Related Skills

Explore More Software Engineering Skills→
coreyjacoreyja
12

skill-writer

Draft SKILL.md frontmatter and structure guidance for Claude Code skills.

Community
Basic
SnakeOSnakeO
9

debug:angular

Diagnose Angular runtime errors using DevTools, ng.probe, and console utilities.

Community
Advanced
HerxinsasaHerxinsasa
1

skill-creator

Automate AI skill creation, evaluation, and iterative improvement workflows.

Community
Advanced
bmsull560bmsull560

evals

Evaluate agent performance and extraction accuracy in LangGraph pipelines.

Community
Advanced