skill-creator

Orchestrate the end-to-end workflow for creating, testing, and refining Claude-like skills.

32|7|Updated Nov 26, 2025
One-click install
npx skills add https://github.com/netlify/context-and-tools --skill skill-creator-netlify
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/netlify/context-and-tools/tree/main/.claude/skills/skill-creator
Command: npx skills add https://github.com/netlify/context-and-tools --skill skill-creator-netlify

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

The Skill Creator provides a structured, end-to-end workflow for building Claude-like skills: drafting SKILL.md, running automated trigger evaluations, analyzing results, and iterating until a skill reaches desired performance. This reduces guesswork and accelerates reliable skill deployment.

Core Features & Use Cases

  • Guided drafting of SKILL.md and embedding of context, references, and assets.
  • End-to-end trigger evaluation loop (train/test splits, multiple prompts) with result recording.
  • Automatic description improvement and iteration history to boost triggering accuracy.
  • Packaging and distribution support via a built-in Skill packaging flow.

Quick Start

Draft a new skill, run the eval loop to test it, iterate on the results, and package the final .skill file.

Frequently Asked Questions about skill-creator

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate skill creation and testing for Claude-like assistants?

Automate skill creation by drafting SKILL.md files, running end-to-end trigger evaluation loops with train/test splits, and iterating on results to refine performance. This structured workflow reduces guesswork and accelerates reliable skill deployment.

What is the best way to evaluate and improve description triggering accuracy?

Improve description triggering accuracy by running automated trigger evaluations across multiple prompts, analyzing the recorded results, and applying automatic description improvements to iteratively boost the skill's activation reliability.

How do I package a SKILL.md file with its context and references for distribution?

Package a SKILL.md file by embedding its context, references, and assets into a final .skill file using the built-in packaging flow, ensuring all necessary components are bundled for distribution.

Can I run multiple test prompts and record results when refining a skill?

Run multiple test prompts by utilizing the end-to-end trigger evaluation loop, which supports train/test splits and automatically records results to guide your iteration history and skill refinement process.

Do I need pyyaml to draft and iterate on Claude-like skills?

Yes, pyyaml is a required dependency to run the Skill Creator, which orchestrates the end-to-end workflow for drafting, testing, and refining skills through automated evaluation loops.