skills.rest
ccstudentcc
ccstudentccCOMMUNITY
Explore all skills by this author →
GitHub

skill-creator

Create, modify, and benchmark Claude skills with SKILL.md workflows.

Updated Apr 17, 2026
Search Tags:#automation#documentation#evaluation#iteration#skill-creation#prompt-design
One-click install
npx skills add https://github.com/ccstudentcc/agent-prompts --skill skill-creator-ccstudentcc
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/ccstudentcc/agent-prompts/tree/main/.codex/skills/skill-creator
Command: npx skills add https://github.com/ccstudentcc/agent-prompts --skill skill-creator-ccstudentcc

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill provides a structured, repeatable workflow to design, evaluate, and iteratively improve Claude skills from scratch, helping teams turn ideas into robust capabilities with measurable results.

Core Features & Use Cases

  • End-to-end skill development: capture intent, draft SKILL.md, assemble bundled resources (scripts/references/assets), and publish public-facing material.
  • Iterative evaluation loop: run trigger evaluations, collect feedback, and refine skill descriptions and instructions based on quantitative and qualitative results.
  • Benchmark-ready output: generate evaluation metadata, packaging-ready artifacts, and deployment-ready documentation to accelerate adoption.

Quick Start

Draft the SKILL.md frontmatter and body, then run the evaluation loop to iteratively test prompts, capture feedback, and refine the description until triggers stabilize.

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 from scratch?▼

To create Claude skills, draft the SKILL.md frontmatter and body, then run an iterative evaluation loop to test prompts, capture feedback, and refine descriptions until triggers stabilize.

What is the best way to benchmark Claude skills and evaluate trigger performance?▼

Benchmarking Claude skills involves running trigger evaluations to collect quantitative and qualitative feedback, allowing you to iteratively refine skill descriptions and generate benchmark-ready artifacts.

How does prompt design work when packaging SKILL.md with bundled resources?▼

Prompt design during skill packaging coordinates the SKILL.md instructions with bundled scripts, references, and assets to produce deployment-ready documentation and packaging-ready artifacts.

Do I need pyyaml to assemble scripts, references, and assets for skill creation?▼

Yes, pyyaml is required to parse configuration files and read SKILL.md frontmatter when assembling bundled resources like scripts, references, and assets into a packaged output.

When should I use an iterative evaluation loop for skill development?▼

Use an iterative evaluation loop during skill development when trigger evaluations are unstable, allowing you to capture feedback and refine prompt instructions until triggers perform reliably.

What are the limitations of automating skill creation without quantitative feedback?▼

Automating skill creation without quantitative feedback limits your ability to refine trigger conditions, preventing the generation of evaluation metadata needed for stable deployment.

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
surus-latsurus-lat
8

push-to-latamboard

Merge local benchmark results into the HuggingFace LatamBoard leaderboard dataset.

Official
Advanced
wx-chevalierwx-chevalier
10

skill-creator

Create, test, and optimize AI skills with SKILL.md and evaluation workflows.

Community
Advanced
oabdelmaksoudoabdelmaksoud
4

skill-creator

Draft, test, evaluate, and iterate on OpenClaw SKILL.md-based skills.

Community
Advanced