skills

Load and activate markdown-defined agent skills from project directories.

Updated May 6, 2026
One-click install
npx skills add https://github.com/dbowm91/codegg --skill skills-dbowm91
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skills
Source: https://github.com/dbowm91/codegg/tree/main/.opencode/skills/skills
Command: npx skills add https://github.com/dbowm91/codegg --skill skills-dbowm91

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The skills module solves the challenge of maintaining a modular, extensible agent architecture by providing a standardized way to load, discover, and activate specialized capabilities on demand.

Core Features & Use Cases

  • Dynamic Loading: Automatically discovers and registers skills from global and project-specific directories.
  • Context Augmentation: Injects specialized instructions into the system prompt only when a skill is activated, keeping the active context clean and relevant.
  • Use Case: A developer can define a custom git-workflow skill in the project directory, which the agent then loads and makes available via a simple command to assist with complex repository operations.

Quick Start

Activate the git skill to load its specialized instructions into the current session context.

Frequently Asked Questions about skills

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

FAQPage Schema
How do I load specialized agent capabilities into a system prompt dynamically?

To load specialized agent capabilities dynamically, you define them as markdown files with YAML frontmatter in a structured directory. This module discovers those definitions and injects their operational instructions into the system prompt only when activated at runtime.

What is modular skill activation for AI agents?

Modular skill activation is the process of loading specialized instructions into an agent's context on demand. It uses markdown-based definitions to keep the active context clean by injecting capabilities only when a specific skill is triggered.

How do I create a custom agent skill for project-specific workflows?

You create a custom agent skill by writing a markdown file containing YAML frontmatter to define metadata and operational instructions. Placing this file in the project-specific directory allows the system to automatically discover and register it for runtime use.

Can I use markdown files to configure extensible agent architectures?

Yes, you can use markdown files to configure extensible agent architectures. The system requires structured markdown files with YAML frontmatter to define skill metadata, enabling dynamic loading and tool-based discovery within the environment.

Does context augmentation keep the system prompt clean when multiple skills are available?

Context augmentation keeps the system prompt clean by only injecting specialized instructions when a skill is explicitly activated. This prevents the active context from being overloaded with irrelevant capabilities during a session.

What are the limitations of using markdown-based skill definitions for agent configuration?

A limitation of markdown-based skill definitions is the strict requirement for YAML frontmatter formatting within a structured directory. Without this specific metadata structure, the automatic discovery and runtime activation mechanisms cannot register the skills.