meta-skill

Create reusable Claude Code Skills with structured SKILL.md metadata.

Updated Apr 24, 2026
One-click install
npx skills add https://github.com/papeete-consulting-lab/banking-reliever --skill meta-skill-papeete-consulting-lab
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: meta-skill
Source: https://github.com/papeete-consulting-lab/banking-reliever/tree/main/.claude/skills/meta-skill
Command: npx skills add https://github.com/papeete-consulting-lab/banking-reliever --skill meta-skill-papeete-consulting-lab

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps users package domain expertise and repeatable workflows into discoverable Claude Code Skills instead of relying on repeated manual prompting.

Core Features & Use Cases

  • Skill Design Guidance: Provides a structured workflow for defining, organizing, and documenting new Agent Skills with valid SKILL.md metadata.
  • Progressive Disclosure Patterns: Explains how to separate core instructions, references, templates, and scripts for efficient AI context usage.
  • Use Case: A developer building a team-specific Claude Code capability can use this Skill to create a properly structured skill directory with examples, supporting resources, and testing steps.

Quick Start

Use the meta-skill to create a new Claude Code Skill for reviewing Python code quality.

Frequently Asked Questions about meta-skill

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

FAQPage Schema
How do I create reusable Claude Code Skills for specialized agent workflows?

Claude Code Skill creation involves packaging domain expertise into structured instructions within a SKILL.md file. This requires valid frontmatter with name and description fields, plus optional supporting resources following Agent Skills conventions.

What is the best way to package domain expertise into discoverable agent skills?

Packaging domain expertise into agent skills is best done by defining structured instructions and metadata in a SKILL.md file. This approach replaces repeated manual prompting with discoverable, reusable Claude Code workflows.

How does progressive disclosure work when designing agent skills?

Progressive disclosure in agent skills works by separating core instructions, references, templates, and scripts. This structure optimizes AI context usage by loading only the necessary supporting resources for the active task.

Do I need specific dependencies to build Claude Code Skills?

Building Claude Code Skills requires no external dependencies. You only need a properly structured skill directory containing a SKILL.md file with valid frontmatter and optional supporting resources like examples or scripts.

Can I use this approach to create a skill directory with examples and testing steps?

Yes, you can use this skill design guidance to create a properly structured skill directory. It supports organizing examples, supporting resources, and testing steps to validate new agent capabilities before deployment.