skills.rest
JuantoC
JuantoCCOMMUNITY
Explore all skills by this author →
GitHub

skill-creator

Create and iterate Claude skills through drafting and evaluation workflows.

Updated Aug 27, 2026
Search Tags:#claude#evaluation#iteration#skill-creation#prompt-engineering#BlueStack
One-click install
npx skills add https://github.com/JuantoC/BlueStack-Test-Automation-Framework --skill skill-creator-juantoc
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/JuantoC/BlueStack-Test-Automation-Framework/tree/main/.claude/skills/skill-creator
Command: npx skills add https://github.com/JuantoC/BlueStack-Test-Automation-Framework --skill skill-creator-juantoc

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Este Skill facilita la creación de nuevos skills y su mejora iterativa en BlueStack, coordinando drafting, evaluación y optimización para incrementar el rate de triggering y la calidad de los outputs.

Core Features & Use Cases

  • Creación de nuevos skills desde cero, con plantilla frontmatter y contenido.
  • Evaluación con runs/graders/viewer para medir triggering y calidad.
  • Optimización de la descripción para mejorar triggering.
  • Soporte de auditoría y orquestación a través de agentes y wikis.

Quick Start

Write a first draft of a new skill, run the standard evaluation loop (train/test), review results, and iterate until the 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 create and iterate Claude skills from a basic draft?▼

To create and iterate Claude skills, draft your initial prompt, run standard train and test evaluations, and optimize the description based on results to improve triggering rates and output quality.

What is the best way to evaluate Claude prompt engineering performance?▼

Evaluating Claude prompt engineering performance involves running a standard evaluation loop with runs, graders, and a viewer to measure both triggering accuracy and output quality before iterating.

How do I optimize a Claude skill description for vector-search discovery?▼

Optimize a Claude skill description for vector-search discovery by aligning it with BlueStack conventions, ensuring the metadata is structured for vector-search friendly discovery to increase trigger rates.

Does skill creation with BlueStack require specific environment setup?▼

Skill creation with BlueStack requires a Python environment with the pyyaml dependency installed to parse frontmatter templates and structure the skill workflow correctly.

Can I audit and orchestrate Claude skills using external agents?▼

Auditing and orchestrating Claude skills is supported through agents and wikis, allowing you to coordinate drafting, evaluation, and optimization workflows across different components.

Why is my Claude skill not triggering in BlueStack?▼

A Claude skill fails to trigger in BlueStack when its description lacks vector-search friendly alignment; optimize the description and run evaluation loops to increase the triggering rate.

Related Skills

Explore More Software Engineering Skills→
samjhechtsamjhecht
4

initialize-governance

Generate Constitution, Roadmap, and process documentation templates for project governance.

Community
Advanced
shhubbhshhubbh
1

canary

Monitor a live URL for console errors, performance regressions, and page failures after deploy.

Community
Advanced
Nuwanda04Nuwanda04

senior-prompt-engineer

Analyze prompts, evaluate RAG systems, and design agentic workflows.

Community
Advanced
gesmith0606gesmith0606

skill-creator

Create, evaluate, and iteratively improve SKILL.md descriptions with Python scripts.

Community
Advanced