Agent Skills Hub

long-running-agent

Framework for building AI agents that persist state across multiple context windows, enabling them to complete complex, multi-day coding tasks without losing progress or context.

mcp-server-creator

Generate production-ready Stigmer McpServer YAML configurations for integrating external tools into your AI agents.

convex-self-hosting

Automate Convex static site hosting integration, managing upload APIs, HTTP routing, and deployment scripts for React, Vite, and Next.js applications.

template-structure

Standardize project scaffolding with pre-configured Claude Code directories, commands, and agents to ensure consistency across all your development templates.

railway-database

Provision and manage Railway database services (Postgres, Redis, MySQL, MongoDB) with automated configuration and environment wiring.

skill-architect

Expert consultant for designing and building high-quality, consistent AI agent skills. Guides you through discovery, architecture, and creation phases to ensure reliable, composable, and efficient skill delivery.

testing

Run, debug, and manage DBHub tests including unit, integration with Testcontainers, and database-specific suites. Perfect for verifying code changes and troubleshooting database connector issues.

repository-setup

Standardize git remote configuration and issue tracking for contributors working with forked repositories in the libuipc project.

skillsdotmd_web

A scaffolding tool for generating production-ready Model Context Protocol (MCP) servers, including boilerplate, typed handlers, schema definitions, and test stubs for AI agent integrations.

claude-code

Standardized skill for Claude Code agents to dynamically query OpenRouter model recommendations and metadata via the Claudish CLI.

typescript

TypeScript development standards for LobeHub, covering type safety, async patterns, import organization, UI component integration, and performance optimization.

Vercel Deploying

Automated Vercel production deployment agent that fetches logs via MCP, identifies build errors, applies fixes, and retries until success.