skills.rest
BaGyun0107
BaGyun0107COMMUNITY
Explore all skills by this author →
WebsiteGitHub

skill-creator

Draft, test, and benchmark AI skills in a cohesive workflow.

Updated Mar 27, 2026
Search Tags:#testing#prompt engineering#skill creation#benchmarking#evaluation
One-click install
npx skills add https://github.com/BaGyun0107/harness-starterkit --skill skill-creator-bagyun0107
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/BaGyun0107/harness-starterkit/tree/main/.agents/skills/skill-creator
Command: npx skills add https://github.com/BaGyun0107/harness-starterkit --skill skill-creator-bagyun0107

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill streamlines the creation, editing, and performance measurement of other skills, enabling rapid development and optimization cycles for AI capabilities.

Core Features & Use Cases

  • Skill Development: Design new skills from scratch or enhance existing ones through iterative prompts.
  • Testing & Evaluation: Generate test prompts, run evaluations, and analyze results to improve accuracy.
  • Benchmarking: Compare skill performance against benchmarks, with variance analysis for robust assessment.

Quick Start

Use this skill to craft a new skill and test its effectiveness on sample prompts.

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 test AI skills through prompt engineering?▼

AI skill creation involves drafting iterative prompts, generating test cases, and running evaluations to refine accuracy. This workflow enables systematic construction by allowing you to test prompts and measure performance effectively.

What is the best way to benchmark AI skill performance?▼

Skill benchmarking compares performance against established standards and includes variance analysis for robust assessment. This process measures accuracy and identifies areas for improvement during the optimization cycle.

Can I evaluate and refine existing AI skills instead of starting from scratch?▼

Yes, you can enhance existing skills through iterative prompt testing and evaluation. The workflow supports editing current designs by generating new test prompts and analyzing the results to improve overall accuracy.

Do I need specific testing frameworks to run skill evaluations?▼

No external testing frameworks are required as dependencies. The skill provides built-in scripts and references to generate test prompts, run evaluations, and analyze results independently within a cohesive workflow.

How does iterative prompt testing improve AI skill accuracy?▼

Iterative prompt testing improves accuracy by allowing you to generate test cases, evaluate responses, and refine prompts based on performance data. This cycle ensures continuous skill optimization and robust assessment.

Related Skills

Explore More Content & Communication Skills→
Fr-e-dFr-e-d
157

architecture-extract

Analyze project directory structures to generate architectural summaries.

Community
Basic
Ronin15Ronin15
14

hammer-benchmark-regression

Compare SDL3 HammerEngine metrics against baselines to flag performance regressions.

Community
Intermediate
thenslsthensls

braintrust-evals

Orchestrate Braintrust experiments, datasets, and scoring for LLM evaluations.

Official
Advanced
leonardoteodorooleonardoteodoroo

llm-evaluation

Evaluate LLM outputs with automated metrics, human feedback, and benchmarking.

Community
Advanced