skills.rest
cloga
clogaCOMMUNITY
Explore all skills by this author →
GitHub

skill-creator

Convert conversations into reusable Skill Units and evaluate triggering coverage.

3|2|Updated Mar 6, 2026
Search Tags:#claude#evaluation#iteration#benchmark#skill#skill-creation#prompt-engineering
One-click install
npx skills add https://github.com/cloga/optimus-code --skill skill-creator-cloga
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/cloga/optimus-code/tree/main/optimus-plugin/skills/skill-creator
Command: npx skills add https://github.com/cloga/optimus-code --skill skill-creator-cloga

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Drafting and refining Claude skills is complex, error-prone, and hard to scale; this guide helps convert conversations into reusable Skill Units and provides a repeatable evaluation loop.

Core Features & Use Cases

  • Capture Intent: turn user goals into SKILL.md frontmatter and structured instructions.
  • Iterative Improvement: run prompts, gather feedback, and iteratively improve coverage, triggering, and test sets.
  • Benchmarking & Deployment: generate evals, run baselines, analyze results, and update skill assets for reliability.

Quick Start

Begin by drafting a Skill Creator skill, then follow the guided loop to draft, test, evaluate, and iterate.

Frequently Asked Questions about skill-creator

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

FAQPage Schema
How do I create reusable Claude skills from chat conversations?▼

Creating reusable Claude skills involves capturing user goals from conversations and transforming them into structured SKILL.md frontmatter and instructions, forming a baseline skill unit for future use.

What is the best way to evaluate Claude skill triggering and coverage?▼

Evaluating Claude skill triggering and coverage is best achieved by applying a rigorous evaluation loop, running prompts, gathering feedback, and iteratively improving the test sets.

How do I benchmark Claude skills for reliable deployment?▼

Benchmarking Claude skills for reliable deployment requires generating evaluation sets, running baselines, analyzing results, and updating skill assets to ensure consistent performance.

Do I need prior prompt engineering experience to iterate on skill units?▼

Iterating on skill units does not require extensive prior prompt engineering experience, as the guided evaluation loop helps you draft, test, evaluate, and improve coverage step by step.

Why does my Claude skill fail to trigger correctly in conversations?▼

A Claude skill failing to trigger correctly often stems from insufficient coverage or poorly defined instructions, requiring you to run evaluation loops and update the SKILL.md frontmatter.

Related Skills

Explore More Content & Communication Skills→
AzrinPutraAzrinPutra

intent-capture

Guide exploratory conversations to elicit project requirements and generate an intent brief.

Community
Intermediate
0xHoneyJar0xHoneyJar
1

eval

Execute Loa framework test suites and output per-trial JSONL results.

Official
Advanced
iani-kuliiani-kuli

prompt-optimizer

Optimize AI prompts through iterative evaluation and refinement loops.

Community
Advanced
CeeKay1901CeeKay1901

skill-creator

Draft, test, and refine reusable skills with evaluation and trigger optimization.

Community
Advanced