skill-creator

Draft SKILL.md content and run trigger-focused evaluations for Claude Code skills.

Updated Aug 27, 2026

Search Tags:#prompt engineering #skill creation #benchmarking #evaluation #Claude Code #trigger optimization

Ready to run

npx skills add https://github.com/soygabimoreno/Los-ANDROIDES --skill skill-creator-soygabimoreno

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/soygabimoreno/Los-ANDROIDES/tree/main/.agents/skills/skill-creator
Command: npx skills add https://github.com/soygabimoreno/Los-ANDROIDES --skill skill-creator-soygabimoreno

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill helps you design a new Claude Code skill—or improve an existing one—by converting your intent into a high-quality SKILL.md, then validating whether Claude triggers the skill correctly using an eval loop.

Core Features & Use Cases

Skill drafting and iteration: Turn a rough idea into a working skill and refine it based on structured feedback.
Trigger accuracy evaluation: Generate a test set of prompts and run trigger evaluations to measure when the skill is (and isn’t) invoked.
Benchmarking and analysis: Produce quantitative summaries and identify patterns that metrics alone can’t explain.
Description optimization: Optimize the skill description field to improve triggering accuracy so Claude uses the skill at the right times.

Quick Start

Tell the skill what kind of skill you want to create (its purpose), when it should trigger, and what output format you expect, then ask it to draft SKILL.md and set up evaluations to test triggering behavior.

Frequently Asked Questions about skill-creator

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

FAQPage Schema

How do I create a Claude Code skill and test its trigger accuracy?▼

To create a Claude Code skill, you draft a SKILL.md file with YAML frontmatter defining the name and description, then run automated evaluations to test trigger accuracy across generated prompts.

How do I optimize Claude skill descriptions for better invocation accuracy?▼

Optimizing Claude skill descriptions involves iterating on the YAML frontmatter text and running benchmark-style comparison loops. This process measures invocation accuracy to ensure the skill triggers only at the appropriate times.

What is trigger-focused evaluation in prompt engineering?▼

Trigger-focused evaluation in prompt engineering is the process of generating a test set of queries and running automated eval loops to measure when a skill is or isn't invoked. It validates that description metadata correctly targets user intent.

Do I need pyyaml to benchmark and evaluate Claude Code skills?▼

Yes, you need the pyyaml dependency installed to parse and encode the YAML frontmatter required for skill creation. This metadata defines the trigger conditions evaluated during the benchmarking process.

Can I improve an existing skill without rewriting the entire SKILL.md?▼

Yes, you can perform a description-optimization pass on an existing skill to improve its triggering behavior. This involves analyzing quantitative summaries from eval runs and refining the trigger conditions without a full rewrite.

Why does my Claude Code skill trigger at the wrong times?▼

A Claude Code skill triggers incorrectly when its YAML frontmatter description lacks accuracy or scope. Running trigger-focused evaluations and analyzing post-run patterns helps identify and fix these invocation mismatches.