skills.rest
firstsun-dev
firstsun-devOFFICIAL
Explore all skills by this author →
WebsiteGitHub

skill-creator

Define, test, and iteratively refine AI skills with structured evaluation loops.

1|Updated Apr 29, 2026
Search Tags:#automation#workflow#evaluation#AI#iteration#skill-creation
One-click install
npx skills add https://github.com/firstsun-dev/yao-agent-skills --skill skill-creator-firstsun-dev
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/firstsun-dev/yao-agent-skills/tree/main/external/basic/skill-creator
Command: npx skills add https://github.com/firstsun-dev/yao-agent-skills --skill skill-creator-firstsun-dev

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides a structured workflow and tooling to create, test, and iteratively improve AI skills, reducing time to reliable triggering and consistent behavior.

Core Features & Use Cases

  • Workflow orchestration: draft, evaluate, review, and refine skills with built-in evals and analyzer support.
  • Iterative improvement: automatically propose description updates and re-run tests to converge on a robust skill.
  • Benchmark-ready: supports analytics, timing, and qualitative review to compare skill variants.
  • Collaboration and auditing: keeps history of iterations and artifacts in git-like trees.

Quick Start

Draft a new skill by outlining its purpose, create clear evaluation prompts, and loop through evaluation, feedback, and refinement until the skill triggers reliably.

Frequently Asked Questions about skill-creator

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

FAQPage Schema
How do I iteratively test and refine AI skills for reliable triggering?▼

Iteratively test and refine AI skills by drafting a purpose, creating evaluation prompts, and looping through evaluation, feedback, and refinement until reliable triggering and consistent behavior are achieved.

What is the best way to automate evaluation loops for AI skill creation?▼

Automate evaluation loops for AI skill creation by orchestrating a workflow that automatically proposes description updates and re-runs tests to converge on a robust, reliably triggering skill.

How do I benchmark and compare AI skill variants with analytics?▼

Benchmark and compare AI skill variants using built-in analytics, timing metrics, and qualitative review to evaluate performance differences and ensure consistent behavior across iterations.

Can I keep an audit history of AI skill iterations and artifacts?▼

Keep an audit history of AI skill iterations and artifacts using git-like trees that track collaboration, preserve previous versions, and maintain a record of all refinement stages.

Do I need structured prompts to define consistent AI skill behavior?▼

Structured prompts are required to define consistent AI skill behavior, providing the baseline logic that evaluation loops and analyzer support test against to ensure reliable execution.

Related Skills

Explore More Software Engineering Skills→
NAKKA-KNAKKA-K

eval-driven-development

Define rubrics, run baseline evaluations, and compare before-and-after outcomes.

Community
Advanced
itsmarsssitsmarsss
4

skill-creator

Creates and optimizes trigger-aware AI skill definitions with reusable workflows.

Community
Advanced
Steffen025Steffen025
186

Apify

Search Apify actors, launch runs, and read datasets in code.

Community
Intermediate
mizchimizchi
320

waxa-eval

Coordinate empirical evaluation loops for skill prompts using the waxa CLI.

Community
Advanced