Agent Skills Hub

Create New Skills

A framework for creating reusable Claude Code agent skills, following best practices for directory structure, progressive disclosure, and multi-file patterns.

make-skill-template

Scaffold and generate new GitHub Copilot Agent Skills. Provides templates, directory structures, and instructions to build specialized AI capabilities with bundled resources.

connections

Lightweight MCP (Model Context Protocol) connection handler supporting stdio, SSE, and streamable HTTP transports for seamless server integration.

skill-installer

Install and manage Codex agent skills from curated lists or GitHub repositories.

ui

Generates UI components, hero sections, and feedback forms with integrated accessibility checks, leveraging specialized design references and quality gates.

saving-codeacts

Preserve successful Python code executions as reusable tools within the gentools package structure, utilizing Pydantic models for structured output and type-safe interfaces.

github-pr-creation

Automated GitHub Pull Request creation with task validation, test execution, Conventional Commits formatting, and project-aware label suggestions.

agent-system

Implementation patterns for MERIDIAN autonomous AI agents using Claude API, including BaseAgent lifecycle, structured tool use, token budget enforcement, and cron scheduling.

glyphbox

A framework for an LLM-based NetHack agent that dynamically synthesizes Python code in a secure sandbox to perform complex dungeon exploration and gameplay actions via a high-level API.

backend-development

Build, optimize, and maintain production-ready backend systems using Node.js, Python, Go, and Rust. Includes API design, database management, security, and DevOps best practices.

agent-sdk

Expert skill for building and maintaining AI agents using the Claude Agent SDK, covering architecture, tool integration, MCP servers, and agentic workflows.

evaluation

Build systematic evaluation frameworks for AI agents using multi-dimensional rubrics, LLM-as-a-judge, and regression testing to measure performance, quality, and context engineering effectiveness.