skills.rest
angrybeagles
angrybeaglesCOMMUNITY
Explore all skills by this author →
GitHub

skill-creator

Create and refine Claude Skills with SKILL.md and eval prompts.

Updated Apr 13, 2026
Search Tags:#workflow#evaluation#iteration#creation#benchmark#skill
One-click install
npx skills add https://github.com/angrybeagles/weather-dashboard --skill skill-creator-angrybeagles
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/angrybeagles/weather-dashboard/tree/main/.claude/plugins/marketplaces/claude-plugins-official/plugins/skill-creator/skills/skill-creator
Command: npx skills add https://github.com/angrybeagles/weather-dashboard --skill skill-creator-angrybeagles

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill enables teams to standardize and accelerate the end-to-end process of creating, validating, and refining Claude Skills, turning ideas into reusable, testable prompts and workflows.

Core Features & Use Cases

  • Capture intent, triggers, and evaluation criteria in a disciplined SKILL.md format.
  • Run iterative evals, benchmarks, and description optimization to improve triggering accuracy and skill quality.
  • Package completed skills into a distributable .skill file for deployment, sharing, or versioning.

Quick Start

Draft a new SKILL.md for your idea, then run the evaluation loop to test 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 Claude Skills?▼

To create Claude Skills, draft a SKILL.md file capturing intent, triggers, and evaluation criteria, then run iterative evals and benchmarks to optimize activation accuracy and quality before packaging.

What is the best way to standardize prompt creation and validation?▼

Standardize prompt creation by collecting intent and evaluation criteria in a SKILL.md format, enabling iterative evaluation and description tuning to refine triggering accuracy into a reusable workflow.

How does skill benchmarking and description tuning work?▼

Skill benchmarking works by running eval prompts to test performance iteratively, allowing you to tune descriptions and triggers to improve activation accuracy and overall skill quality.

Do I need PyYAML and Anthropic dependencies to package a skill?▼

You need PyYAML and Anthropic dependencies to support the Python scripts required for skill creation, evaluation loops, and packaging into a distributable .skill zip artifact.

Can I include scripts and references when building a Claude Skill?▼

You can include optional resources in scripts, references, and assets directories to support skill functionality, which are validated and packaged into the final .skill zip artifact.

Related Skills

Explore More Product & Management Skills→
PiaoxuemoliPiaoxuemoli

jupyter-live-kernel

Execute Python code incrementally with a stateful Jupyter kernel.

Community
Intermediate
ldilovldilov
3

release-readiness

Packages the canonical SKILL.md file for consistent deployment across environments.

Community
Basic
ManfronEnricoManfronEnrico

skill-creator

Automate creation, refinement, and benchmarking of Claude skills with iterative evaluations.

Community
Advanced
psd401psd401
2

skill-creator

Create, refine, and evaluate AI skills with automated testing.

Official
Advanced