Browsing:

summarybotng

An agentically constructed replacement for my previously vibe-coded version

oimiragieo

agent-evaluation is a LLM-as-judge evaluation framework that assesses AI-generated content quality using a weighted composite score and structured verdict with evidence citations.

futuresearch

deploy-mcp is a GitHub Actions-based AI agent skill for automating MCP server deployment and scaling, designed for seamless integration with Claude Code and AI coding workflows.

futuresearch

deploy-mcp is a skill that automates the deployment and scaling of MCP servers, providing a robust foundation for AI research teams to work efficiently.

Ilenburg1993

🤖 Autonomous AI agent for browser automation with Puppeteer - Domain-driven task processing with adaptive validation and real-time monitoring

mshafei721

Multi-agent AI coding platform powered by Vercel Sandbox and AI Gateway - Phase 3: Skills & MCP Integration Complete

ksmuvva

Code-generation is the process of creating production-quality code that adheres to clean code principles, security best practices, and maintainability standards.

ismailytics

Ralph Advanced with Claude Code, Linear and Playwright - Autonomous AI agent loop with Linear MCP integration, Playwright browser testing, and optional TDD workflow.

Tiendil

donna-do is a skill that provides deterministic behavior, state machines, artifact management, and meta programming for coding agents, ensuring predictable and reliable execution.

smadgerano

intern is a Claude Code skill that automates task delegation using Opencode through ACP.

janekbaraniewski

The one dashboard you’ve been looking for — track spend and usage across Claude, Cursor, OpenRouter, Copilot, Gemini, Codex, and more.

stacklok

ToolHive is an application that allows you to install, manage and run MCP servers and connect them to AI agents