skills.rest
krzemienski
krzemienskiCOMMUNITY
Explore all skills by this author →
Website𝕏@nkrzemienskiGitHub

skill-creator

Orchestrate Claude Code skill development from SKILL.md drafting to trigger evaluation.

2|1|Updated May 21, 2025
Search Tags:#automation#iteration#benchmark#skill-creation#test-cases#eval#trigger-optimization
One-click install
npx skills add https://github.com/krzemienski/awesome-list-site --skill skill-creator-krzemienski
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/krzemienski/awesome-list-site/tree/main/.agents/skills/skill-creator
Command: npx skills add https://github.com/krzemienski/awesome-list-site --skill skill-creator-krzemienski

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires anthropic, pyyaml.

What problem does it solve?

This skill enables rapid creation, testing, and iterative improvement of Claude Code skills by coordinating the end-to-end workflow: drafting SKILL.md, running trigger-eval prompts, analyzing results, and refining descriptions for better activation.

Core Features & Use Cases

  • Draft and refine SKILL.md with structured frontmatter and clear instructions.
  • Design and run eval prompts to test trigger accuracy, including train/test splits and baseline comparisons.
  • Analyze results and iterate on descriptions, tests, and benchmarks.
  • Manage optional benchmarking and result visualization to compare iterations.

Quick Start

Run an initial evaluation cycle on the skill, review results in the eval viewer, and iteratively refine SKILL.md and trigger phrases.

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 Code skill creation and testing?▼

Automate Claude Code skill creation by orchestrating an end-to-end workflow that drafts SKILL.md files, runs trigger-eval prompts, analyzes results, and iterates to optimize trigger descriptions and benchmarks.

How do trigger-eval prompts improve skill activation accuracy?▼

Trigger-eval prompts improve skill activation by running test cases against draft triggers, analyzing the eval viewer results, and iterating on the descriptions to refine baseline comparisons and train/test splits.

Can I run benchmark comparisons when iterating on SKILL.md files?▼

Yes, you can manage optional benchmarking and result visualization to compare iterations of SKILL.md files, allowing you to track improvements in trigger optimization across different test cases.

What is the best way to structure a SKILL.md file for trigger optimization?▼

The best way to structure a SKILL.md file for trigger optimization is using structured frontmatter and clear instructions, which are then tested and refined through automated eval loops.

Do I need Anthropic and PyYAML dependencies to run skill creation eval loops?▼

Yes, the skill creation eval loops require the Anthropic and PyYAML dependencies to orchestrate the workflow, parse structured frontmatter, and execute trigger-eval prompts.

Why are my Claude Code skill triggers not activating correctly?▼

Skill triggers may not activate correctly due to vague descriptions; running trigger-eval prompts and reviewing the eval viewer results helps identify and refine weak trigger phrases through iterative testing.

Related Skills

Explore More Education & Research Skills→
mamd69mamd69
4

skill-creator

Automates drafting, testing, benchmarking, and iterating Claude skill SKILL.md workflows with Python and anthropic/pyyaml libraries.

Community
Advanced
artusjsartusjs
11

skill-creator

Automate drafting, evaluating, and optimizing Claude Code skills with SKILL.md validation.

Official
Advanced
qiushibangqiushibang

skill-creator

Create, modify, and improve AI agent skills through eval-driven workflows.

Community
Advanced
DFly7DFly7

skill-creator

Create, evaluate, and iteratively improve AI skill definitions and workflows.

Community
Advanced