skills.rest
iyaki
iyakiCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

skill-creator

Coordinate end-to-end creation and refinement of Claude skills via SKILL.md and evaluation loops.

Updated Sep 25, 2025
Search Tags:#automation#workflow#testing#claude#evaluation#iteration#skill-creation
One-click install
npx skills add https://github.com/iyaki/opencode-base-template --skill skill-creator-iyaki
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/iyaki/opencode-base-template/tree/main/.agents/skills/skill-creator
Command: npx skills add https://github.com/iyaki/opencode-base-template --skill skill-creator-iyaki

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires yaml, and includes scripts (resource) components.

What problem does it solve?

The Skill Creator provides a structured workflow to craft, test, and improve AI skills so that users can quickly build reliable agents.

Core Features & Use Cases

  • Create new skills, modify and improve existing skills, and measure performance with evals and the eval-viewer.
  • Iterate through prompts, tests, and feedback cycles to refine triggering accuracy and robustness.
  • Use history and results to drive scripted improvements and bundle reusable components.

Quick Start

Define your skill in SKILL.md, run the evaluation loop to test triggering, review results, and iterate until the description reliably triggers for relevant 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 Claude skills to ensure accurate triggering?▼

To create and test Claude skills, you can draft a SKILL.md file and run an evaluation loop to test triggering accuracy. The workflow analyzes results and iterates descriptions to improve performance and reliability.

What is the best way to iterate on AI agent descriptions for better evaluation results?▼

Iterating on AI agent descriptions involves running prompt tests and feedback cycles. You analyze the evaluation results to drive scripted improvements, refining the description until it reliably triggers for relevant prompts.

Do I need YAML to use this skill creation workflow?▼

Yes, YAML is a required dependency for this skill creation workflow. You need it to define configurations and bundle reusable components within your automated testing environment.

Can I modify existing AI skills instead of building new ones from scratch?▼

Yes, you can modify and improve existing AI skills. The workflow supports refining current descriptions and testing them through evaluation loops to measure performance and robustness.

Why does my AI skill fail to trigger for relevant prompts during testing?▼

If your AI skill fails to trigger, the description lacks accuracy or robustness. You should run the evaluation loop, review the test results, and iterate the prompt descriptions until triggering becomes reliable.

How do I bundle reusable components when building automation workflows?▼

You can bundle reusable components by using the test history and evaluation results. This data drives scripted improvements, allowing you to package reliable elements for future skill creation and automation workflows.

Related Skills

Explore More Software Engineering Skills→
yu13130122297yu13130122297

scout

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

Community
Intermediate
vnmoorthyvnmoorthy
2

canary

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

Community
Advanced
creamgod45creamgod45

skill-creator

Automate drafting, evaluating, and iterating Claude Code skills with SKILL.md.

Community
Advanced
csuzngjhcsuzngjh
1

inject-rule

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

Community
Basic