skills.rest
tazagame
tazagameOFFICIAL
Explore all skills by this author →
GitHub

skill-creator

Draft SKILL.md files and run evaluations to improve triggering and quality metrics.

Updated Apr 15, 2026
Search Tags:#automation#workflow#evaluation#packaging#iteration#skill
One-click install
npx skills add https://github.com/tazagame/claude-setting-v0.1-fsd-next-etc --skill skill-creator-tazagame
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/tazagame/claude-setting-v0.1-fsd-next-etc/tree/main/.claude/skills/skill-creator
Command: npx skills add https://github.com/tazagame/claude-setting-v0.1-fsd-next-etc --skill skill-creator-tazagame

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Provides a structured framework and tooling to create new Claude skills, then test, evaluate, and iteratively improve them from draft to deployment.

Core Features & Use Cases

  • Structured workflow to draft, test, and iteratively improve skills
  • Built-in evaluation, benchmarking, and trigger optimization
  • Packaging and distribution utilities for sharing skills

Quick Start

Draft a new skill, run an evaluation loop, and iterate until you reach a stable, well-described skill.

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 a new Claude skill from scratch?▼

Benchmarking a Claude skill involves running evaluations to measure triggering accuracy, coverage, and overall performance. You iterate on the SKILL.md draft until these metrics meet your defined targets for stable deployment.

What is the workflow for iteratively refining a skill's trigger accuracy?▼

The skill iteration workflow involves drafting, testing, and refining. You run automated evaluations to measure triggering and coverage, then update the skill description until performance metrics reach a stable, defined threshold.

Do I need PyYAML to draft and package automation skills?▼

PyYAML is required as a dependency to support the skill-creator framework. It handles the YAML configuration processing needed to structure your skill definitions, run evaluations, and package the final output.

How do I package a skill for distribution after benchmarking?▼

After benchmarking confirms your skill meets performance targets, use the built-in packaging utilities to bundle the SKILL.md and associated scripts. This prepares a distributable format for sharing your Claude skill.

What are the limitations of automating skill evaluation and iteration?▼

The evaluation framework measures triggering, coverage, and performance, but achieving a stable skill requires setting explicit metric targets. Iteration continues until those defined benchmarks are met, limiting fully autonomous deployment.

Related Skills

Explore More Software Engineering Skills→
s977043s977043
2

skill-creator

Design a Claude Code skill from a use case and produce a repo-ready package.

Community
Advanced
narcisolcfnarcisolcf

pca-skill-manager

Scaffold, validate, and package Claude Skills into .skill archives.

Community
Advanced
safzanpiranisafzanpirani
1

deslop

Remove redundant and suboptimal code sections from AI-generated source files.

Community
Basic
anxiety135790anxiety135790

dspy

Generate and optimize LLM programs using declarative signatures and metrics.

Community
Advanced