skills.rest
nablarch
nablarchOFFICIAL
Explore all skills by this author →
WebsiteGitHub

skill-creator

Orchestrates executor, grader, comparator, and analyzer to create and test AI skills.

2|Updated Feb 6, 2026
Search Tags:#skill development#prompt engineering#AI agent#evaluation#performance testing#iterative improvement
One-click install
npx skills add https://github.com/nablarch/nabledge-dev --skill skill-creator-nablarch
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/nablarch/nabledge-dev/tree/main/.claude/skills/skill-creator
Command: npx skills add https://github.com/nablarch/nabledge-dev --skill skill-creator-nablarch

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill streamlines the entire lifecycle of creating and improving AI skills, from initial concept to performance measurement, reducing the manual effort and complexity involved in skill development.

Core Features & Use Cases

  • Skill Creation: Guides users through drafting and initializing new skills.
  • Iterative Improvement: Facilitates a loop of testing, grading, comparing, and analyzing skill versions.
  • Performance Measurement: Runs evals and benchmarks to quantify skill effectiveness.
  • Use Case: A developer wants to create a new skill to summarize meeting transcripts. They use this Skill to draft the initial prompt, write test cases, run evaluations, and iterate on the skill's instructions based on performance metrics until it reliably produces accurate summaries.

Quick Start

Use the skill-creator to start building a new skill for summarizing meeting notes.

Frequently Asked Questions about skill-creator

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

FAQPage Schema
How do I build and iterate on AI skills through performance testing?▼

AI skills can be built and improved by orchestrating executor, grader, comparator, and analyzer agents to run iterative testing loops. This process drafts initial prompts, runs evaluations, and refines instructions based on performance metrics.

What is the best way to measure AI agent performance during skill development?▼

The best way to measure AI agent performance is by running automated evals and benchmarks to quantify effectiveness. Automated testing evaluates the skill against specific test cases to ensure reliable outputs across different scenarios.

How do I create an AI skill from scratch for a specific use case?▼

To create an AI skill from scratch, start by drafting and initializing the new skill according to your use case. You can then write test cases, run evaluations, and iterate on the instructions until the skill reliably performs the target task.

Can I manage multiple versions of an AI skill during prompt engineering?▼

Yes, you can manage multiple versions of an AI skill by using dedicated workspaces. This allows you to track iterative improvements, compare different prompt versions side-by-side, and analyze performance metrics across iterations.

Does this skill development process support automated testing for prompt refinement?▼

Yes, the skill development process supports automated testing via evals to facilitate prompt refinement. It orchestrates agents to grade, compare, and analyze skill versions, ensuring iterative improvement based on quantified performance data.

Related Skills

Explore More Software Engineering Skills→
s977043s977043
2

skill-creator

Design a Claude Code skill from a use case and produce a repo-ready package.

Community
Advanced
vnmoorthyvnmoorthy
2

canary

Monitor live apps for console errors and performance regressions post-deploy.

Community
Advanced
HelloWorldSunginHelloWorldSungin
2

your-skill-name

Create customizable AI skills with structured frontmatter and workflow sections.

Community
Basic
DhumitechDhumitech

agent-evaluation

Automate AI agent evaluation and benchmarking with repeatable test pipelines.

Community
Advanced