skills.rest
ErrDivine
ErrDivineCOMMUNITY
Explore all skills by this author →
GitHub

skill-creator

Create, modify, and optimize AI skills with evaluation and feedback.

Updated Mar 18, 2026
Search Tags:#skill development#AI agent#evaluation#skill optimization#description optimization
One-click install
npx skills add https://github.com/ErrDivine/LiteCode --skill skill-creator-errdivine
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/ErrDivine/LiteCode/tree/main/skills/system/anthropic/skill-creator
Command: npx skills add https://github.com/ErrDivine/LiteCode --skill skill-creator-errdivine

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires eval-viewer, generate_review.py, aggregate_benchmark.py, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill helps users create, modify, and improve AI skills, optimizing their performance and triggering accuracy.

Core Features & Use Cases

  • Skill Creation: Start from scratch or modify existing skills to suit specific use cases.
  • Evaluation: Run evaluations to test skill performance, including quantitative benchmarks and user feedback.
  • Optimization: Use description optimization to enhance triggering accuracy and refine skill behaviors.
  • Use Case: If you're developing a skill to automatically analyze and summarize technical documentation, use this Skill to create the initial draft, evaluate its performance, and refine the description for better triggering accuracy.

Quick Start

Create a new skill for analyzing technical documentation and set up an evaluation using the provided guidelines.

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 optimize skills for AI agents?▼

To build and optimize AI agent skills, use this Skill to handle the full development lifecycle, facilitating creation, modification, and iteration based on evaluation feedback to optimize performance and triggering accuracy.

What is the best way to evaluate AI skill performance and triggering accuracy?▼

Evaluating AI skill performance involves running quantitative benchmarks and gathering user feedback. This Skill facilitates evaluation to test behaviors, refine descriptions, and enhance triggering accuracy for specific use cases.

How do I refine AI skill descriptions for better triggering accuracy?▼

Refining AI skill descriptions requires description optimization techniques. This Skill helps modify and optimize descriptions to enhance triggering accuracy, ensuring the AI agent activates correctly for specific use cases.

Can I modify existing AI skills instead of creating them from scratch?▼

Yes, you can modify existing AI skills to suit specific use cases. This Skill facilitates skill modification, allowing you to draft, test, and iterate based on evaluation feedback rather than starting from scratch.

Do I need prior knowledge of skill structure to develop AI agents?▼

Understanding skill structure and AI interaction is required for optimal results. This Skill facilitates creation and optimization, but requires prerequisite knowledge of the skill structure to effectively draft, test, and iterate.

Why does my AI agent skill fail to trigger accurately in technical documentation tasks?▼

Inaccurate triggering often stems from unoptimized descriptions. Use this Skill to run evaluations, gather user feedback, and apply description optimization to refine the skill behaviors and enhance triggering accuracy.

Related Skills

Explore More Software Engineering Skills→
intuitemintuitem
4.3k

ciso-assistant-bootstrap

Guide new users through initial CISO Assistant setup using MCP server tools.

Official
Advanced
MisLinkMisLink

skill-creator

Draft SKILL.md files, generate test prompts, and run with-skill versus baseline evaluations.

Community
Advanced
Eva813Eva813
2

skill-creator

Create and improve Claude-compatible skills with SKILL.md and eval runs.

Community
Advanced
Clouder0Clouder0

agent-workflow

Coordinate multi-agent development workflows across five lifecycle phases.

Community
Advanced