skills.rest
gelowzzz
gelowzzzCOMMUNITY
Explore all skills by this author →
GitHub

skill-creator

Create, validate, and package Claude Skills into .skill files.

Updated May 20, 2026
Search Tags:#automation#workflow#Claude#evaluation#iteration#benchmark#skill
One-click install
npx skills add https://github.com/gelowzzz/plushyai --skill skill-creator-gelowzzz
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/gelowzzz/plushyai/tree/main/.agents/skills/skill-creator
Command: npx skills add https://github.com/gelowzzz/plushyai --skill skill-creator-gelowzzz

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill enables teams to rapidly create, refine, and measure Claude Skills across the full lifecycle — from drafting SKILL.md and initial prompts to evaluating performance and benchmarking improvements.

Core Features & Use Cases

  • Author and iterate skills: write SKILL.md frontmatter, craft the workflow instructions, and extend with optional scripts, references, and assets.
  • Evaluate and benchmark: run trigger evaluation, gather quantitative metrics, and compare with baselines or prior iterations.
  • Automated packaging and validation: validate skills, package into deployable .skill files, and track iterations for continuous improvement.
  • Multiplier for teams: reuse and share skills across projects, and speed up agent automation workstreams.

Quick Start

Create a new skill folder with SKILL.md and run the built-in scripts to validate, test, and package the skill for deployment.

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 validate Claude Skills for automation workflows?▼

You create Claude Skills by scaffolding SKILL.md frontmatter, writing Markdown instructions, and running built-in validation scripts to verify structural integrity before deployment.

What is the best way to evaluate and benchmark Claude Skills across iterations?▼

Skill evaluation and benchmarking involves running scripted EVALs to gather quantitative metrics, allowing you to compare current performance against baselines or prior iterations and track improvements over time.

How does packaging skills into distributable files work for team deployment?▼

Packaging skills into distributable files works by validating the skill folder and bundling its components into a deployable .skill file, enabling teams to reuse and share automation workstreams across projects.

Do I need Python and pyyaml to scaffold and benchmark skill iterations?▼

Yes, you need Python and the pyyaml dependency installed, as the skill relies on these to parse configuration files and execute the scripted EVALs required for benchmarking performance.

Can I extend skill workflows with custom scripts and reference assets?▼

Yes, you can extend skill workflows by adding optional scripts, references, and assets into the skill folder, which are then packaged alongside the SKILL.md instructions for comprehensive automation.

Related Skills

Explore More Software Engineering Skills→
HeyvhuangHeyvhuang
339

skill-improver

Analyze run artifacts to propose concrete skill and workflow edits.

Community
Basic
ccstudentccccstudentcc

skill-creator

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

Community
Advanced
nanorepublicananorepublica
61

Global Tech Stack

Validate code against centralized global tech stack standards.

Community
Basic
devCharuzudevCharuzu

senior-prompt-engineer

Design prompts and evaluation frameworks for LLM workflows.

Community
Advanced