skills.rest
atro2829-hub
atro2829-hubCOMMUNITY
Explore all skills by this author →
GitHub

skill-creator

Draft skill instructions, design evals, and analyze benchmark results.

Updated Jun 1, 2026
Search Tags:#benchmarking#skills#evaluation#iteration#skill.md#triggering
One-click install
npx skills add https://github.com/atro2829-hub/APPLE-NET-NEW --skill skill-creator-atro2829-hub
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/atro2829-hub/APPLE-NET-NEW/tree/main/skills/skill-creator
Command: npx skills add https://github.com/atro2829-hub/APPLE-NET-NEW --skill skill-creator-atro2829-hub

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill helps you create new skills, refine existing ones, and measure whether the skill actually works on realistic tasks instead of relying on guesswork.

Core Features & Use Cases

  • Skill drafting: Turn an idea or rough workflow into a usable SKILL.md with clear triggering guidance and operational instructions.
  • Evaluation design: Create realistic test prompts, run them with and without the skill, and compare the results.
  • Iterative improvement: Use qualitative review, quantitative benchmarks, and feedback from test runs to revise the skill until it behaves consistently.
  • Description tuning: Optimize the frontmatter description so the skill triggers in the right situations more reliably.

Quick Start

Use the skill-creator skill to draft a new skill for my task, generate a small eval set, and tell me how you would test whether it triggers correctly.

Frequently Asked Questions about skill-creator

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

FAQPage Schema
How do I create a skill from scratch using a SKILL.md file?▼

To create a skill from scratch, you draft a structured SKILL.md file containing clear triggering guidance and operational instructions. This skill helps draft the initial instructions and designs realistic evals to validate the behavior.

How do I test if my skill triggers accurately in the right situations?▼

To test skill triggering accuracy, you optimize the frontmatter description and run comparative evaluations with and without the skill active. Analyzing benchmark results isolates whether the skill activates appropriately for specific prompts.

What is the best way to evaluate and benchmark custom skills?▼

The best way to benchmark custom skills is by generating realistic test prompts, running comparative tests with and without the skill, and analyzing the aggregated results. This approach replaces guesswork with measurable evaluation data.

Can I iteratively improve an existing skill based on benchmark results?▼

Yes, you can iteratively improve an existing skill by applying qualitative review, quantitative benchmarks, and test run feedback to revise the skill. This validation workflow continues until the skill behaves consistently across scenarios.

Do I need any external dependencies to build and run skill evaluations?▼

No external dependencies are required to build and run skill evaluations. The process relies on self-contained structured skill files, eval generation scripts, and run aggregation references to support iterative validation workflows.

Related Skills

Explore More Software Engineering Skills→
jaydubya818jaydubya818

product-marketing-context

Create and update product marketing context documents from codebase analysis.

Community
Intermediate
vnmoorthyvnmoorthy
2

canary

Monitor live apps for console errors and performance regressions post-deploy.

Community
Advanced
KunCheng-HeKunCheng-He
8

skill-creator

Create, refine, and benchmark custom AI skills with Python-based test cases.

Community
Advanced
csuzngjhcsuzngjh
1

inject-rule

Appends user-provided rule arguments to the Ad-hoc Rules section of USER_CONTEXT.md.

Community
Basic