skills.rest
CommonCapital
CommonCapitalCOMMUNITY
Explore all skills by this author →
GitHub

skill-creator

Design, test, and refine AI skills with evaluation feedback loops.

2|Updated Jun 21, 2026
Search Tags:#skill creation#benchmarking#AI development#evaluation#skill refinement
One-click install
npx skills add https://github.com/CommonCapital/Manus-ai_clone --skill skill-creator-commoncapital
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/CommonCapital/Manus-ai_clone/tree/main/public/deep-agent/skills/skill-creator
Command: npx skills add https://github.com/CommonCapital/Manus-ai_clone --skill skill-creator-commoncapital

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill streamlines the process of creating, refining, and optimizing AI skills, enabling users to build robust and efficient AI agents.

Core Features & Use Cases

  • Skill Creation: Guide users through the process of defining and implementing new AI skills.
  • Skill Refinement: Iterate on existing skills by running evaluations, benchmarking performance, and optimizing descriptions.
  • Use Case: If you have a draft of a skill and need to test it or improve its accuracy, this Skill can help you through the process, including setting up test cases, running evaluations, and iterating on feedback.

Quick Start

Create a new skill by describing the desired action and output format. Then, define the skill's trigger conditions and input requirements.

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 for an agent workflow?▼

To create and test AI skills, you define the desired action, output format, and trigger conditions, then set up test cases and run evaluations to measure agent performance. This iterative loop facilitates ongoing skill refinement.

What is the best way to refine an AI skill that is producing inaccurate outputs?▼

The best way to refine an AI skill is to run evaluations and benchmark its performance using iterative feedback loops. By setting up targeted test cases, you can identify inaccuracies and optimize the skill descriptions for better accuracy.

Do I need knowledge of evaluation metrics to design AI skills?▼

Yes, designing AI skills requires knowledge of AI agent workflows and evaluation metrics. This foundational understanding is necessary to effectively set up test cases, run benchmarks, and interpret feedback for skill refinement.

How do I set up test cases for AI skill benchmarking?▼

You set up test cases for AI skill benchmarking by defining specific trigger conditions and input requirements within the skill definition. Running these evaluations generates performance data for iterative refinement.

Can I optimize existing AI agent workflows without rewriting the entire skill definition?▼

Yes, you can optimize existing AI agent workflows by iterating on the current skill definitions. The process involves running targeted evaluations, benchmarking performance metrics, and refining descriptions rather than rebuilding from scratch.

Related Skills

Explore More Software Engineering Skills→
yu13130122297yu13130122297

scout

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

Community
Intermediate
panaversitypanaversity
55

skill-validator

Validate a Skill Unit against nine quality criteria and generate a structured report.

Official
Advanced
HelloWorldSunginHelloWorldSungin
2

your-skill-name

Create customizable AI skills with structured frontmatter and workflow sections.

Community
Basic
mneves75mneves75
74

writing-skills

Apply Test-Driven Development to create and test AI skills.

Community
Intermediate