skill-creator

Draft SKILL.md content, generate eval prompts, and execute test prompts.

6|1|Updated Apr 7, 2026
One-click install
npx skills add https://github.com/kmshihab7878/claude-code-setup --skill skill-creator-kmshihab7878
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/kmshihab7878/claude-code-setup/tree/main/skills/skill-creator
Command: npx skills add https://github.com/kmshihab7878/claude-code-setup --skill skill-creator-kmshihab7878

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

The Skill Creator provides a repeatable, auditable workflow to design, test, and iteratively improve Claude Skills, replacing ad-hoc edits with a scalable process that tracks progress and outcomes.

Core Features & Use Cases

  • End-to-end skill lifecycle: draft, test, evaluate, and refine skills in a single, reusable pattern.
  • Automated testing & benchmarking: run trigger evaluations, collect metrics, and compare configurations with built-in visualization.
  • Structured skill writing: guidance and templates for composing SKILL.md, crafting evaluation prompts, and organizing references/scripts/assets.
  • Reportable iteration history: maintain a history of iterations, results, and decisions to inform future improvements.
  • Collaborative workflow support: standardized schemas (evals.json, benchmark.json, history) enable cross-team collaboration and governance.

Quick Start

Create a new skill from scratch, write its SKILL.md, run a baseline evaluation, 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 create and test Claude Skills systematically instead of making ad-hoc edits?

Use an automated workflow to draft SKILL.md content, generate evaluation prompts, execute tests, and aggregate results into actionable improvements for iterative Claude Skill creation.

What is the best way to benchmark Claude Skills during the iteration process?

Benchmark Claude Skills by running trigger evaluations, collecting metrics, and comparing configurations with built-in visualization to track iteration progress and outcomes.

How do I structure a SKILL.md file for a new automation workflow?

Structure SKILL.md using provided templates and guidance for composing skill content, crafting evaluation prompts, and organizing references, scripts, and assets.

Can I use YAML dependencies to manage skill evaluation and iteration history?

Yes, YAML dependencies support standardized schemas for evals.json, benchmark.json, and history files to enable cross-team collaboration and governance during skill iteration.

What's the process for end-to-end skill lifecycle management from scratch?

Start by drafting a new skill from scratch, write its SKILL.md, run a baseline evaluation, and iterate based on the aggregated test results to refine the skill.

When should I not use an automated skill evaluation workflow?

Avoid automated skill evaluation workflows when you need one-off skill edits without repeatable testing, as the process is designed for scalable, auditable lifecycle management.