skills.rest
ishi253
ishi253COMMUNITY
Explore all skills by this author →
GitHub

skill-creator

Create and optimize AI skills with SKILL.md files and test cases.

Updated Mar 12, 2026
Search Tags:#skill development#prompt engineering#optimization#AI agent#evaluation#LLM
One-click install
npx skills add https://github.com/ishi253/byteDanceApplication --skill skill-creator-ishi253
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/ishi253/byteDanceApplication/tree/main/deer-flow/skills/public/skill-creator
Command: npx skills add https://github.com/ishi253/byteDanceApplication --skill skill-creator-ishi253

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 lifecycle of creating and refining AI capabilities, from initial concept to performance optimization, making AI development accessible and efficient.

Core Features & Use Cases

  • Skill Creation: Guides users through defining intent, interviewing for edge cases, and writing SKILL.md for new AI functionalities.
  • Iterative Improvement: Facilitates testing, evaluation, and refinement of existing skills based on user feedback and performance metrics.
  • Description Optimization: Enhances skill discoverability and triggering accuracy through automated testing and LLM-driven prompt engineering.
  • Use Case: A user wants to build a skill that summarizes meeting transcripts. This Skill will help them define the skill's purpose, write the initial SKILL.md, generate test cases, run evaluations, analyze results, and optimize the description for better triggering.

Quick Start

Use the skill creator to help me build a new skill that can extract key information from user-provided meeting notes.

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 AI skills from scratch?▼

To build AI skills, define the intent, draft the SKILL.md file, generate test cases, and run evaluations. This skill facilitates the end-to-end creation process by guiding intent definition and iterative testing.

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

Optimizing AI skill descriptions involves running automated tests and leveraging LLM-driven prompt engineering. This improves skill discoverability and triggering accuracy based on benchmark results and evaluation metrics.

How do I evaluate LLM performance for an existing prompt engineering project?▼

Evaluating LLM performance requires generating test cases and analyzing benchmark results. This skill integrates with evaluation frameworks to support iterative development and quality assurance for existing prompts.

Do I need prior prompt engineering experience to modify an AI agent?▼

No prior experience is required to modify an AI agent. The skill streamlines the entire lifecycle from initial concept to performance optimization, making AI development accessible through guided interviews and automated testing.

Why does my AI skill fail to trigger accurately in production?▼

Inaccurate triggering often stems from poorly optimized descriptions. Use LLM-driven prompt engineering and automated testing to analyze benchmark results and refine the SKILL.md content for improved discoverability.

Related Skills

Explore More Software Engineering Skills→
lostitonce420-beeplostitonce420-beep

ai-secretary

Draft emails, manage calendar scheduling, and prepare meeting agendas.

Community
Intermediate
ddarkrddarkr
5

oma-pdf

Convert PDF files into structured Markdown with text, tables, headings, and images.

Community
Intermediate
spideynolovespideynolove
2

llm-evaluation

Evaluate LLM outputs with automated metrics and human evaluation checklists.

Community
Advanced
yasuwrldhyperyasuwrldhyper

skill-creator

Create and refine AI skills with SKILL.md metadata and benchmark testing.

Community
Advanced