skill-creator

Draft, evaluate, iterate, and package Claude skills with structured metadata.

1|Updated Mar 19, 2026

Search Tags:#skill creation #benchmarking #evaluation #packaging #iterative improvement #trigger optimization

Ready to run

npx skills add https://github.com/ian-pascoe/dotfiles-chezmoi --skill skill-creator-ian-pascoe

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/ian-pascoe/dotfiles-chezmoi/tree/main/dot_agents/skills/skill-creator
Command: npx skills add https://github.com/ian-pascoe/dotfiles-chezmoi --skill skill-creator-ian-pascoe

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 helps you design new skills, improve existing ones, and measure whether they actually work, instead of guessing from a single draft.

Core Features & Use Cases

Skill Drafting: Turn a rough idea into a structured SKILL.md with clear triggering guidance and usable instructions.
Evaluation and Iteration: Create test prompts, run comparisons, grade outputs, and revise the skill based on real feedback.
Description Optimization: Tune the frontmatter description so the skill triggers on the right requests more reliably.
Packaging and Review: Organize helper scripts, references, and assets, then package the finished skill for distribution.

Quick Start

Use the skill-creator skill to help me draft, test, and improve a new skill for my workflow.

Frequently Asked Questions about skill-creator

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

FAQPage Schema

How do I build and test a Claude skill from scratch?▼

To build a Claude skill from scratch, draft a structured SKILL.md with triggering guidance, generate test prompts, grade outputs, and iterate based on feedback. This skill creation process ensures reliable triggering and usable instructions.

What is skill benchmarking and when do I need it?▼

Skill benchmarking evaluates trigger behavior by running test prompts and grading outputs. You need benchmarking when refining an existing skill or optimizing frontmatter descriptions to ensure the skill triggers reliably on the right requests.

How do I optimize a skill description for better discovery?▼

Optimizing a skill description for better discovery involves tuning the frontmatter metadata so the skill triggers on the right requests. You generate test prompts, evaluate trigger behavior, and iterate on the description for reliable discovery.

Can I use pyyaml to package Claude skills with helper scripts?▼

Yes, you can package Claude skills with helper scripts, references, and assets for distribution. The skill requires the pyyaml dependency to support structured skill metadata and organize components into a finished, distributable package.

What is the best way to improve an existing skill's trigger behavior?▼

The best way to improve trigger behavior is through iterative evaluation: create test prompts, run comparisons, grade outputs, and revise the skill based on real feedback. Benchmarking trigger behavior ensures reliable activation on target requests.

Why does my Claude skill fail to trigger on the right requests?▼

A Claude skill fails to trigger when the frontmatter description is misaligned with user requests. You fix this by tuning the description, generating test sets to benchmark trigger behavior, and iterating through grading and review loops.