What are 'Degrees of Freedom' in skill creation?

It refers to matching the specificity of instructions to the task's fragility: high freedom for creative text tasks, and low freedom (specific scripts) for error-prone technical operations.

How does this skill help with context window management?

It teaches the 'Progressive Disclosure' principle, using a three-level loading system (Metadata, SKILL.md, and Bundled Resources) to ensure Claude only uses tokens for information relevant to the current task.

What is the mandatory structure of a skill?

Every skill must have a SKILL.md file containing YAML frontmatter metadata and Markdown body instructions. Optional folders include scripts, references, and assets.

Can I include executable code in a skill?

Yes, skills can include a 'scripts' directory containing Python or Bash scripts for tasks requiring deterministic reliability, which Claude can execute as needed.

What is a Claude Code Skill?

A Claude Code Skill is a specialized, modular package that extends Claude's capabilities by providing domain-specific knowledge, tool integrations, and procedural workflows.

Claude Skill Creator

Name: Claude Skill Creator
Author: lawvable

bylawvable

•

228

•

Aprendizaje y Documentación

Guides the development of modular, high-performance AI agent capabilities using standardized patterns and context-efficient design.

The Claude Skill Creator provides a structured framework for building and optimizing specialized extensions within the Claude Code ecosystem. By implementing core principles like token conservation and progressive disclosure, it enables developers to transform Claude from a general-purpose assistant into a domain-specific expert. This skill ensures your custom extensions—whether they are for legal automation, API integration, or complex workflows—remain efficient, discoverable, and reliably executed by managing the balance between procedural instructions and bundled resources.

Características Principales

01Framework for defining agent degrees of freedom

02Context-efficient Progressive Disclosure design patterns

03Resource management guidance for scripts, assets, and references

04Standardized SKILL.md template and metadata structure

05Step-by-step skill planning and packaging workflow

06228 GitHub stars

Casos de Uso

01Optimizing context window usage for complex, multi-step AI workflows

02Building custom agent capabilities for specialized technical or business domains

03Standardizing internal team tools and procedural documentation for AI agents

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add lawvable/awesome-legal-skills skill-creator-anthropic

For use in Claude.ai and ChatGPT

Características Principales

01Framework for defining agent degrees of freedom

02Context-efficient Progressive Disclosure design patterns

03Resource management guidance for scripts, assets, and references

04Standardized SKILL.md template and metadata structure

05Step-by-step skill planning and packaging workflow

06228 GitHub stars

Casos de Uso

01Optimizing context window usage for complex, multi-step AI workflows

02Building custom agent capabilities for specialized technical or business domains

03Standardizing internal team tools and procedural documentation for AI agents

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add lawvable/awesome-legal-skills skill-creator-anthropic

For use in Claude.ai and ChatGPT