skills.rest
wsxwj123
wsxwj123COMMUNITY
Explore all skills by this author →
GitHub

skill-creator

Draft Claude skills, evaluate prompts, and iterate on trigger descriptions.

7|Updated Jan 27, 2026
Search Tags:#automation#workflow#evaluation#iteration#skill#prompt-engineering
One-click install
npx skills add https://github.com/wsxwj123/opencode-skills-backup --skill skill-creator-wsxwj123
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/wsxwj123/opencode-skills-backup/tree/main/skill-creator
Command: npx skills add https://github.com/wsxwj123/opencode-skills-backup --skill skill-creator-wsxwj123

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires anthropic, pyyaml, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

The Skill Creator guides you through crafting new Claude skills, iterating on designs, and evaluating performance to accelerate your ability to deliver effective skills.

Core Features & Use Cases

  • End-to-end skill development: draft, test prompts, and iterate on skill quality.
  • Evaluation loop: run trigger tests, benchmark results, and refine skill instructions.
  • Description optimization: improve trigger phrases to maximize activation and usefulness.

Quick Start

Start by drafting a new skill concept, then run the evaluation loop to validate triggering and iterate toward a solid production-ready skill.

Frequently Asked Questions about skill-creator

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

FAQPage Schema
How do I automate prompt evaluation and iteration for Claude skills?▼

Automating prompt evaluation involves running trigger tests, benchmarking results, and refining instructions. This end-to-end workflow allows you to continuously improve skill quality based on direct feedback.

What is the best way to optimize skill descriptions for accurate triggering?▼

Optimizing skill descriptions requires refining trigger phrases to maximize activation accuracy and usefulness. This ensures the skill launches correctly based on user intent and context.

How do I draft and test prompts for new automation workflows?▼

Drafting and testing prompts requires defining a skill concept and executing an evaluation loop. This validates triggering, benchmarks effectiveness, and iterates toward a production-ready automation workflow.

Do I need Python and pyyaml to run the skill development workflow?▼

The skill development workflow requires Python and pyyaml to process configurations. These dependencies support the automation scripts needed for testing, evaluating, and iterating on prompts.

Can I use this evaluation loop for prompt-engineering tasks at scale?▼

This evaluation loop supports prompt-engineering tasks at scale by providing automated testing and benchmarking. It handles continuous improvement across multiple skill iterations efficiently.

Related Skills

Explore More Software Engineering Skills→
cruzanstxcruzanstx
6

prompt-executor

Execute prompts from ./prompts/ against AI models with optional worktrees and verification loops.

Community
Advanced
binfen1binfen1

canary

Monitor live apps for console errors, performance regressions, and page failures.

Community
Advanced
felipesantiago-coderfelipesantiago-coder

skill-creator

Create AI skills with structured evaluation and benchmarking workflows for GLM Code.

Community
Advanced
easyspace-aieasyspace-ai

skill-creator

Create, evaluate, and optimize Claude Skills with templates and benchmark loops.

Community
Advanced