skills.rest
etewe333
etewe333COMMUNITY
Explore all skills by this author →
GitHub

skill-creator

Coordinate end-to-end Claude skill design from intent capture to SKILL.md drafting and eval-driven iteration.

Updated Mar 18, 2026
Search Tags:#automation#evaluation#benchmark#skill-development#prompt-engineering#skill-creator
One-click install
npx skills add https://github.com/etewe333/eda_first --skill skill-creator-etewe333
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/etewe333/eda_first/tree/main/.claude/skills/skill_creator
Command: npx skills add https://github.com/etewe333/eda_first --skill skill-creator-etewe333

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill helps teams design, test, and iteratively improve Claude skills from draft to deployment, enabling rapid experimentation and measurable improvements.

Core Features & Use Cases

  • Capture user intent, write SKILL.md, and structure automated evals to validate triggering and performance.
  • Run iterative evaluation loops (train/test) with automatic metrics, visuals, and guidance to rewrite skills based on results.
  • Package skills as portable .skill bundles with optional scripts, references, and assets for reproducible deployment.

Quick Start

Draft a new skill, write its SKILL.md, define a basic eval set, and run the end-to-end loop to 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 and test a Claude skill end to end?▼

To create a Claude skill, you capture user intent, draft a SKILL.md file, define evaluation prompts, run trigger evaluations, and iterate based on the results to ensure robust performance.

What is a SKILL.md file and how does it structure automation workflows?▼

A SKILL.md file defines the core instructions and trigger logic for a Claude skill, organizing the automation workflow with references, scripts, and assets for reproducible deployment.

How do I set up automated evaluation benchmarks for prompt engineering?▼

You set up automated evaluation benchmarks by defining a set of test prompts within the skill workflow, running iterative train and test loops, and measuring performance with automatic metrics.

Can I package automation scripts and references into a portable skill bundle?▼

Yes, you can package automation scripts, references, and assets into portable .skill bundles, enabling reproducible deployment and scaling across multiple domains.

Do I need pyyaml to run skill development workflows?▼

Yes, pyyaml is a required dependency for running the skill development workflow, specifically to handle configuration parsing and YAML structured data within the automation scripts.

Why are my skill trigger evaluations not working properly?▼

Trigger evaluations fail when the SKILL.md lacks clear intent capture or the evaluation prompts are misaligned, requiring you to iterate and rewrite the skill based on the automated metrics.

Related Skills

Explore More Software Engineering Skills→
Fudan-SMI-labFudan-SMI-lab
39

torch-npu-pyyaml-preinstall

Preinstall PyYAML before torch-npu to prevent transitive dependency failures.

Official
Intermediate
eco2-teameco2-team
3

skill-creator

Create or update Claude skills with standardized scaffolds and packaging scripts.

Official
Intermediate
AidenSbVevoAidenSbVevo
1

skill-creator

Create, evaluate, and optimize custom AI skill units with automated testing.

Community
Advanced
christofferbergjchristofferbergj
5

skill-creator

Automate drafting, testing, and refining Claude skills with evaluation loops.

Community
Advanced