skill-creator

Translate user intent into SKILL.md files and run evaluation loops.

1.5k|180|Updated Feb 13, 2026
One-click install
npx skills add https://github.com/Memento-Teams/Memento-Skills --skill skill-creator-memento-teams
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/Memento-Teams/Memento-Skills/tree/main/builtin/skills/skill-creator
Command: npx skills add https://github.com/Memento-Teams/Memento-Skills --skill skill-creator-memento-teams

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill provides a structured workflow for building new Claude skills: capturing user intent, drafting clear SKILL.md documentation, generating and running evaluations, and iterating based on results to improve performance and triggering accuracy.

Core Features & Use Cases

  • Capture intent from user conversations and translate it into a kebab-case skill name and a descriptive SKILL.md frontmatter.
  • Write the SKILL.md body with progressive disclosure, including a concise workflow, recommended scripts, and references to reusable assets.
  • Run automated evaluation loops (trigger tests) against a diverse set of prompts to measure trigger accuracy, evaluation results, and iteration progress.
  • Iterate description and skill content automatically or semi-manually based on evaluation feedback, then re-run tests until performance stabilizes.
  • Use the packaging and reference tooling to bundle scripts/assets for distribution and reuse in other projects.

Quick Start

Interview the user to capture intent, draft the SKILL.md, design and run evals, and iterate based on results.

Frequently Asked Questions about skill-creator

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

FAQPage Schema
How do I automate Claude skill creation and testing workflows?

Automate Claude skill creation by translating user intent into a SKILL.md file, executing parallel evaluations, and guiding iterative improvements to stabilize trigger accuracy and description quality.

What is the best way to write a SKILL.md file for reusable skill components?

Write a SKILL.md file by capturing user intent, generating kebab-case naming, drafting frontmatter, and structuring the body with progressive disclosure, concise workflows, and references to reusable scripts.

How do I evaluate trigger accuracy for Claude skills?

Evaluate trigger accuracy by running automated evaluation loops against diverse prompts, measuring trigger test results, and iterating skill descriptions based on feedback until performance stabilizes.

Can I use Python scripts and YAML to package reusable skill assets?

Yes, you can use Python scripts and YAML dependencies to package reusable skill assets, bundling scripts and references for distribution and reuse across other projects.

Does iterative skill improvement require manual evaluation feedback?

Iterative skill improvement supports both automatic and semi-manual evaluation feedback, allowing you to re-run trigger tests and refine descriptions until performance stabilizes without requiring fully manual intervention.

Why are my Claude skills not triggering accurately in automated workflows?

Inaccurate triggering often stems from poorly drafted descriptions; run parallel evaluations against diverse prompts, iterate SKILL.md content based on results, and re-run tests to improve trigger accuracy.