Why use progressive disclosure in skill design?

It keeps the context window lean by only loading detailed information when the AI determines it is necessary for the current task, saving tokens and improving accuracy.

What is the difference between references and assets?

References are documentation files intended for Claude to read to inform its process, while assets are files like logos or templates intended for use in the final output.

Can I include executable code in a skill?

Yes, skills can include a 'scripts/' directory for Python, Bash, or other code to perform deterministic tasks that would be inefficient or error-prone if written from scratch every time.

What is a Claude Code Skill?

A skill is a modular package that extends Claude's capabilities with specialized knowledge, tools, and workflows, transforming it into a domain-specific agent.

Skill Architect

Name: Skill Architect
Author: Microck

byMicrock

•

开发者工具

Standardizes the creation and optimization of custom Claude Code skills through structured workflows and modular resource management.

关于

The Skill Architect skill empowers developers to extend Claude's native capabilities by providing a rigorous framework for building specialized, domain-specific skills. It guides the development of modular packages that include executable scripts, reference documentation, and static assets while prioritizing context window efficiency through a progressive disclosure design. Whether you are automating complex DevOps pipelines or documenting company-specific business logic, this skill ensures your custom extensions are concise, reliable, and perfectly integrated into the Claude Code ecosystem.

主要功能

Strategies for balancing instruction specificity and degrees of freedom
Progressive disclosure patterns to optimize context window usage
81 GitHub stars
Guidelines for bundling executable scripts and reference materials
Framework for modular skill architecture and file structure
Step-by-step workflow for initializing and iterating on custom skills

使用场景

Creating new specialized skills for unique company workflows or internal APIs
Refactoring existing long-form prompts into modular, reusable skill packages
Optimizing AI agent performance by managing large documentation sets via reference files

关于

主要功能

Strategies for balancing instruction specificity and degrees of freedom
Progressive disclosure patterns to optimize context window usage
81 GitHub stars
Guidelines for bundling executable scripts and reference materials
Framework for modular skill architecture and file structure
Step-by-step workflow for initializing and iterating on custom skills

使用场景

Creating new specialized skills for unique company workflows or internal APIs
Refactoring existing long-form prompts into modular, reusable skill packages
Optimizing AI agent performance by managing large documentation sets via reference files