skills.rest
iani-kuli
iani-kuliCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

skill-creator

Draft, test, and benchmark custom AI skills with automated subagent workflows.

Updated May 5, 2026
Search Tags:#automation#workflow#testing#optimization#ai development#benchmarking
One-click install
npx skills add https://github.com/iani-kuli/harness_bro --skill skill-creator-iani-kuli
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/iani-kuli/harness_bro/tree/main/.claude/skills/curated/skill-creator
Command: npx skills add https://github.com/iani-kuli/harness_bro --skill skill-creator-iani-kuli

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill streamlines the complex process of developing, evaluating, and refining custom AI skills, ensuring they are robust, accurate, and ready for production use.

Core Features & Use Cases

  • Iterative Development: Provides a structured loop for drafting, testing, and improving skill instructions based on real-world performance.
  • Quantitative Benchmarking: Automates the generation of test cases, execution of subagents, and aggregation of performance metrics to validate skill reliability.
  • Trigger Optimization: Uses a dedicated loop to refine skill descriptions, ensuring the AI triggers the skill only when appropriate and with high accuracy.
  • Use Case: If you need to create a specialized skill for complex data analysis, this tool helps you draft the initial logic, run it against a suite of test prompts, analyze the results, and optimize the description so the AI knows exactly when to use it.

Quick Start

Use the skill-creator skill to help me draft a new skill for automating my weekly project status reports.

Frequently Asked Questions about skill-creator

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

FAQPage Schema
How do I benchmark AI skills against baseline behaviors?▼

To benchmark AI skills, you can automate the generation of test cases, execute subagent workflows, and aggregate performance metrics to compare new skills against baseline behaviors for actionable improvement insights.

What's the best way to optimize AI skill triggering descriptions?▼

Optimizing AI skill triggering descriptions involves using a dedicated iterative loop to refine instructions, ensuring the AI triggers the skill only when appropriate and with high accuracy for improved model reliability.

Can I automate the end-to-end lifecycle of AI skill development?▼

Yes, automating the end-to-end lifecycle of AI skill development is possible, facilitating everything from initial drafting and iterative testing to performance benchmarking and final production readiness.

How do I create a quantitative evaluation suite for testing AI workflows?▼

Creating a quantitative evaluation suite for testing AI workflows involves automating test case generation and aggregating execution metrics to validate skill reliability and measure performance accurately.

Does iterative testing improve AI development reliability?▼

Iterative testing improves AI development reliability by providing a structured loop to draft, test, and refine skill instructions based on real-world performance and quantitative benchmarking results.

Related Skills

Explore More Software Engineering Skills→
yu13130122297yu13130122297

scout

Identify uncertainties in research framing, datasets, metrics, and baselines.

Community
Intermediate
mwolff328-stackmwolff328-stack
1

skill-creator

Develop, test, and refine custom AI skills through iterative evaluation loops.

Community
Advanced
phuhao00phuhao00
12

skill-creator

Develop, test, and optimize custom AI skills with Python-based benchmarking.

Community
Advanced
BaGyun0107BaGyun0107

skill-creator

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

Community
Intermediate