skill-creator

Builds .skill packages with automated AST-based conflict detection.

Updated Mar 21, 2026

Search Tags:#automation #workflow #optimization #evaluation #skill #skill-creator

Ready to run

npx skills add https://github.com/SuperPauly/SkillCreatorSkill --skill skill-creator-superpauly

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/SuperPauly/SkillCreatorSkill/tree/main/.github/skills/skill-creator
Command: npx skills add https://github.com/SuperPauly/SkillCreatorSkill --skill skill-creator-superpauly

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Skill creation and iteration for Claude Copilot skills, enabling rapid drafting, evaluation, and improvement cycles with built-in tooling and frontmatter discipline.

Core Features & Use Cases

End-to-end skill creation workflow: draft SKILL.md, assemble tests/evals, and iterate using eval-viewer and agent tooling.
Metadata-driven discovery and packaging: enforce frontmatter validation, support optional bundles (scripts/references/assets), and produce a deployable .skill artifact.
Evaluation and optimization loop: run trigger evals, compare with baselines, and improve the skill description via the improve_description script.

Quick Start

Draft your skill objective and let this Skill Creator guide you through drafting, testing, evaluating, and iterating on SKILL.md, evals, and benchmarks.

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 Copilot skills from scratch?▼

To create Claude Copilot skills, draft a SKILL.md file, assemble test prompts, and run evaluation loops to measure trigger accuracy and quality. This workflow guides the end-to-end lifecycle from initial drafting to deployment packaging.

What is a SKILL.md file and how does frontmatter validation work?▼

A SKILL.md file defines a Claude skill using structured descriptions and frontmatter metadata. Frontmatter validation enforces required fields and formatting rules, ensuring the skill is discoverable and correctly packaged into a deployable artifact.

How do I evaluate and optimize skill trigger accuracy?▼

Evaluate skill trigger accuracy by running trigger evals against test prompts and comparing results with baselines. An optimization script then refines the skill description to improve performance across iterations.

Can I bundle scripts, references, and assets into a single skill package?▼

Yes, you can coordinate optional bundles including scripts, references, and assets within your skill. Once frontmatter is validated, these components are packaged together into a deployable .skill artifact.

Do I need PyYAML installed to validate skill frontmatter?▼

Yes, PyYAML is required because skill frontmatter relies on YAML format for metadata definition. You need the PyYAML dependency installed in your environment to parse and enforce frontmatter validation.

What's the best way to iterate on a skill description using eval results?▼

The best way to iterate on a skill description is to run eval loops comparing quality and performance metrics against baselines, then use the improve_description script to refine the text for better trigger accuracy.