skills.rest
datorresb
datorresbCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

skill-creator

Automate skill development from SKILL.md drafting through evaluation loops and packaging.

Updated Mar 24, 2026
Search Tags:#automation#optimization#packaging#skill#prompt-engineering#creator#evals
One-click install
npx skills add https://github.com/datorresb/niwashi-studio --skill skill-creator-datorresb
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/datorresb/niwashi-studio/tree/main/skills/external/skill-creator
Command: npx skills add https://github.com/datorresb/niwashi-studio --skill skill-creator-datorresb

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires yaml.

What problem does it solve?

Automates the end-to-end lifecycle of skill development, from drafting SKILL.md to automated evaluation loops and iterative improvements.

Core Features & Use Cases

  • Draft, test, and iterate skills quickly with a structured workflow that includes evals, scoring, and optimization.
  • Run automated trainer/evaluation loops to measure triggering accuracy, optimization potential, and packaging readiness.
  • Package final skills for deployment and distribution, including lightweight validation steps.

Quick Start

Draft a new skill, connect it to a set of eval prompts, run the evaluation loop, and iterate until the triggering and performance meets your criteria.

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 skill development and evaluation loops?▼

Automating Claude skill development involves orchestrating the end-to-end lifecycle from drafting SKILL.md files to running automated evaluation loops, collecting eval prompts, and managing train/test splits for iterative improvements.

What is prompt engineering for skill triggering accuracy and how does benchmarking work?▼

Prompt engineering for skill triggering accuracy refines skill descriptions to ensure correct activation. Benchmarking measures this performance by scoring eval prompt responses across iterative optimization loops.

How do I package ready-to-use skill artifacts for deployment?▼

Packaging ready-to-use skill artifacts involves finalizing the optimized SKILL.md, running lightweight validation steps, and outputting structured files for benchmarking and deployment distribution.

Do I need YAML to create and optimize Claude skills?▼

Yes, YAML is a required dependency to create and optimize Claude skills, supporting the structured formatting needed for SKILL.md generation and automated evaluation loop configurations.

What's the best way to refine skill descriptions for better triggering accuracy?▼

The best way to refine skill descriptions is through automated trainer loops that iterate through description optimization, measure triggering accuracy against test splits, and score performance for iterative improvements.

Related Skills

Explore More Software Engineering Skills→
rajivhasija79-bitrajivhasija79-bit
3

skill-creator

Draft, test, and evaluate Claude skills through iterative refinement.

Community
Intermediate
victorjoshi9victorjoshi9
1

skill-creator

Draft Claude skill instructions, generate evals, and run comparisons.

Community
Advanced
codeboltaicodeboltai

skill-creator

Create and refine Claude skills with structured SKILL.md templates and packaging workflows.

Official
Intermediate
dduquennedduquenne
1

skill-creator

Create and iterate Claude skills with SKILL.md files and evaluation loops.

Community
Advanced