skills.rest
jawwad-ali
jawwad-aliCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

skill-creator

Create and refine Claude skills with SKILL.md templates and evaluations.

4|2|Updated Jan 17, 2026
Search Tags:#evaluation#iteration#benchmark#skill-development#triggering#skill-creator
One-click install
npx skills add https://github.com/jawwad-ali/claude-code-skills --skill skill-creator-jawwad-ali
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/jawwad-ali/claude-code-skills/tree/main/.claude/skills/skill-creator
Command: npx skills add https://github.com/jawwad-ali/claude-code-skills --skill skill-creator-jawwad-ali

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

The skill-creator enables teams to rapidly conceive, draft, evaluate, and iterate Claude skills from concept to deployable artifacts, reducing cycle times and improving triggering reliability.

Core Features & Use Cases

  • Define intent and scope for new skills
  • Drive structured evaluation loops with benchmarks and feedback
  • Generate starter SKILL.md templates and guide the skill through refinement
  • Organize work with optional scripts, references, and assets to support deployment

Quick Start

Outline the skill's intent, draft the SKILL.md, run initial evaluations, and iterate based on user feedback to reach a polished skill.

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 iterate on Claude skills end-to-end?▼

To create and iterate on Claude skills, define the skill's intent, draft the SKILL.md file, run structured evaluations, and optimize the trigger description based on benchmark feedback. This lifecycle process ensures reliable triggering and deployable artifacts.

What is a structured evaluation loop for skill development?▼

A structured evaluation loop for skill development is an iterative process of testing prompts, running benchmarks, and applying feedback to refine the skill. It validates performance and improves discovery before final deployment.

Do I need scripts and references directories to build a skill?▼

You do not need scripts and references directories to build a skill, but they are supported as optional modular components. They help organize deployment assets alongside the core SKILL.md file for complex workflows.

What's the best way to optimize skill triggering for better discovery?▼

The best way to optimize skill triggering is to iteratively refine the trigger description using benchmark performance data and user feedback. This ensures the skill activates accurately for the intended queries.

How do I generate a starter SKILL.md template for a new prompt?▼

You can generate a starter SKILL.md template by outlining the new skill's intent and scope. The skill-creator guides this drafting process and structures the file for immediate evaluation and refinement.

Related Skills

Explore More Software Engineering Skills→
xurenluxurenlu
1

skill-creator

Creates and iteratively improves AI skills with SKILL.md and test cases.

Community
Advanced
uzumaki-incuzumaki-inc

canary

Monitor live apps for console errors, performance regressions, and page failures.

Official
Advanced
silvainfmsilvainfm
2

skill-developer

Create and manage Claude Code skills with triggers and enforcement levels.

Community
Advanced
zangjeicyzangjeicy

mcporter

Discover, authenticate, and execute MCP servers and tools via CLI.

Community
Intermediate