skill-creator

Create and refine Claude skills into tested SKILL.md workflows.

Updated May 6, 2026
One-click install
npx skills add https://github.com/Takfes/indie-scaffolder --skill skill-creator-takfes
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/Takfes/indie-scaffolder/tree/main/components/agent-skills-commands/.agents/skills/skill-creator
Command: npx skills add https://github.com/Takfes/indie-scaffolder --skill skill-creator-takfes

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Skill Creator helps you turn an idea into a usable Claude skill, then iterate on it with test cases, evals, and feedback so the final skill is actually triggered and useful.

Core Features & Use Cases

  • Draft a new skill from scratch or improve an existing one.
  • Create realistic eval prompts, run comparisons, grade results, and inspect benchmark patterns.
  • Optimize the SKILL.md description so the skill triggers for the right user intents.
  • Package the finished skill for distribution and reuse.

Quick Start

Ask this skill to help you design, test, and refine a Claude skill for your task, then share the intended behavior and any example prompts or files.

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 a Claude skill from a rough idea?

To create a Claude skill, draft a SKILL.md workflow from your idea, generate realistic eval prompts, run comparisons, grade outputs, and refine the description for proper triggering. This iterates your skill until it is tested and useful.

What is the best way to optimize a SKILL.md description for better triggering?

Optimize a SKILL.md description by tuning the text to match specific user intents, ensuring the skill triggers correctly. Use description optimization tooling to refine prompts and align the workflow with expected queries.

Can I run benchmark analysis and grade outputs for Claude skills?

Yes, you can run benchmark analysis for Claude skills by generating test cases, comparing outputs across iterations, and inspecting patterns. Grading tooling evaluates the results to guide refinement.

How do I package a Claude skill for distribution and reuse?

Package a Claude skill for distribution by finalizing the SKILL.md workflow and using reusable scripts to prepare the files. This ensures the finished skill is ready for reuse across environments.

Does the skill creator workflow require pyyaml to function?

Yes, pyyaml is required as a dependency to support the skill creator workflow. It processes configuration files and reusable scripts during skill generation, testing, and packaging.

Why is my Claude skill not triggering for the right user intents?

A Claude skill fails to trigger when its description does not align with user intents. You can fix this by applying description optimization tooling, generating test cases, and refining the SKILL.md text for better matching.