skills.rest
Nathan3303
Nathan3303COMMUNITY
Explore all skills by this author →
GitHub

skill-creator

Create, evaluate, and refine Claude skills through an automated drafting and testing loop.

4|Updated Jun 12, 2024
Search Tags:#automation#cli#benchmarking#evaluation#packaging#iteration#skill-creation
One-click install
npx skills add https://github.com/Nathan3303/nao-todo --skill skill-creator-nathan3303
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/Nathan3303/nao-todo/tree/main/.agents/skills/skill-creator
Command: npx skills add https://github.com/Nathan3303/nao-todo --skill skill-creator-nathan3303

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Streamline the creation and refinement of Claude skills by providing a repeatable framework for drafting, evaluating, and iterating skills, reducing guesswork and accelerating improvement.

Core Features & Use Cases

  • End-to-end skill creation: define intent, draft prompts, build test prompts, run evaluations, and iteratively improve based on results.
  • Evaluation-driven iteration: run trigger evaluations, compare with baselines, and surface both qualitative and quantitative feedback.
  • Automated improvement loop: generate targeted skill description updates and manage historical progress across iterations.
  • Packaging and distribution: package skills into .skill files, generate reports, and view benchmarks to guide decision-making.

Quick Start

Create or load a skill, run the evaluation loop with your eval set, and iterate until results meet your triggering and performance goals.

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 evaluation?▼

You can automate Claude skill creation by running an end-to-end loop that drafts prompts, builds test sets, runs trigger evaluations, and iteratively refines the skill based on quantitative feedback.

What is evaluation-driven iteration for prompt refinement?▼

Evaluation-driven iteration is a process that runs trigger evaluations on drafted prompts, compares performance against baselines, and surfaces qualitative and quantitative feedback to systematically improve skill descriptions.

How do I package skills into distributable files for deployment?▼

To package skills for deployment, you bundle the skill definitions, frontmatter, and optional bundled resources like scripts and assets into .skill files, then generate benchmark reports to guide deployment decisions.

Do I need PyYAML to define skill frontmatter and compatibility?▼

Yes, PyYAML is required as a dependency to parse and expose the clear, discoverable frontmatter containing the skill name, description, and compatibility metadata needed for deterministic task execution.

Can I bundle scripts and assets within a Claude skill?▼

Yes, you can bundle optional resources such as scripts and reference assets directly within a skill to facilitate deterministic tasks and enable on-demand information access during execution.

Related Skills

Explore More Software Engineering Skills→
BaryoDevBaryoDev

skill-creator

Create and iteratively refine AI skills with SKILL.md and performance evaluations.

Official
Advanced
yangkun19921001yangkun19921001
37

skill-creator

Create and package modular agent skills into distributable .skill files.

Community
Advanced
micaelmaltamicaelmalta
1

skill-creator

Create and refine Claude skills with SKILL.md templates and bundled resources.

Community
Basic
rattamnoonrattamnoon

skill-creator

Build, evaluate, and refine Claude Skills with automated evaluations.

Community
Advanced