skills.rest
Shockwave2k
Shockwave2kCOMMUNITY
Explore all skills by this author →
GitHub

skill-creator

Draft SKILL.md files and run evaluation loops to measure trigger accuracy.

Updated Apr 22, 2026
Search Tags:#automation#evaluation#packaging#benchmark#claude-code#skill-creation
One-click install
npx skills add https://github.com/Shockwave2k/team-claude-skills --skill skill-creator-shockwave2k
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/Shockwave2k/team-claude-skills/tree/main/skills/shared/skill-creator
Command: npx skills add https://github.com/Shockwave2k/team-claude-skills --skill skill-creator-shockwave2k

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill helps teams craft and iteratively improve Claude Skills, providing a repeatable workflow from SKILL.md authoring through evaluation, benchmarking, and packaging.

Core Features & Use Cases

  • End-to-end skill creation pipeline from SKILL.md authoring to evals, benchmarking, and packaging
  • Built-in evaluation loop and benchmark tooling to measure trigger accuracy and stability
  • Descriptive optimization and optional history to track improvements over time
  • Packaging and distribution with validation and references/scripts/assets management

Quick Start

Draft a new skill by filling SKILL.md, then run the evaluation loop to iterate and package.

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 evaluate Claude skills for trigger accuracy?▼

To create and evaluate Claude skills, you draft a SKILL.md with a clear name and description, then run the built-in evaluation loop to measure trigger accuracy and iterate improvements until the description is optimized.

What is the process for benchmarking Claude skill configurations?▼

Benchmarking Claude skill configurations involves using the built-in benchmark tooling to compare different setups, capture evaluation results, and identify the best performing description for your skill.

How do I package and distribute a Claude skill as a .skill file?▼

Packaging a Claude skill as a .skill file uses built-in validation to bundle your SKILL.md alongside optional references, scripts, and assets into a single distributable archive.

Do I need pyyaml to author and test Claude skills?▼

Yes, pyyaml is a required dependency for running the skill-creation pipeline, providing the necessary environment to author SKILL.md files and execute the evaluation and benchmarking scripts.

What's the best way to refine SKILL.md descriptions for better trigger stability?▼

The best way to refine SKILL.md descriptions is to run the evaluation loop, use descriptive optimization with optional history tracking to measure trigger stability, and iterate based on captured benchmark results.

Related Skills

Explore More Software Engineering Skills→
tuliosouza99tuliosouza99

skill-creator

Create and iteratively improve SKILL.md-based agent skills with Python eval scripts.

Community
Advanced
mcs-climcs-cli
92

techpack-creator

Package Claude Code configurations into distributable MCS techpack.yaml files.

Official
Intermediate
ccstudentccccstudentcc

skill-creator

Create, modify, and benchmark Claude skills with SKILL.md workflows.

Community
Advanced
Mattyreed1Mattyreed1

skill-creator

Create, test, and optimize AI agent skills with quantitative benchmarks.

Community
Advanced