OpenLoomi is an open-source AI coworker. It connects your work tools, understands what you’re working on, and tells you what needs your attention, why it matters, and what to do next. It’s your open-source Attention Agent.

A curated collection of high-quality prompt templates designed for Claude, focused on coding, problem-solving, productivity, and advanced reasoning workflows.

AI-промпты, агенты и анти-паттерны для QA — от аудита спецификаций до генерации API-тестов

庖丁 — dissect any AI skill into an anatomy handbook: why it works, how it's built, what's worth stealing. 把 skill 解成一本解剖手册的 Claude Code skill

AI Context Engineering for QA

Real-time Claude.ai/Codex subscription awareness for AI coding assistants. Surfaces your live Session 5hr and Weekly 7day utilization, forecasts when you'll hit the limit, gates expensive operations before they run, and measures real per-task cost — all without leaving your machine.

The definitive open-source guide for mastering AI Prompt Engineering techniques.

jailbreak_google_gemini_3.1_lite_ai

Step-by-step LangChain tutorials covering models, prompts, chains, retrievers, tools, and agents — theory to full implementation.

GitHub Raw URL Explorer is a small web UI that scans a public GitHub repository and lists raw.githubusercontent.com URLs for all files in the selected branch.

A curated collection of design patterns, reference architectures, and practical examples for building AI/ML-driven applications. Covers agent engineering, prompt design, foundational models, generative AI, context engineering, vector databases, and integration with modern cloud & tech stacks.

A scalable prompt engineering and optimization framework for building, testing, and documenting high-quality prompts across GPT, Gemini, Claude, and other LLMs.

Natural language to SQL analytics tool powered by AI - ask questions about banking data in plain English and get instant insights with visualizations. Built with Python, Streamlit, and Groq API. Demonstrates AI integration, prompt engineering, and full-stack data application development.

Sistema de Gestión de Monitores de Salas de Cómputo (SGMSC) evolucionado a Agente Inteligente. Integra arquitectura RAG, Model Context Protocol (MCP) y memoria contextual para administrar la base de datos, generar reportes y auditar la seguridad mediante lenguaje natural.

Claude Code plugin for spartan brevity — measured 66% output token savings

Agentic workflow in Claude Code: slash command orchestrates a subagent to research, then formats output with a skill. All in Markdown—no compilation needed.

AI task assigner works using github issues. Assigns tasks to developers based on their experince and knowledge.

Generates structured test cases (unit, integration, and e2e) from a plain-text feature description, using the OpenAI API (GPT-4o).

Claude Code skills purpose-built for Solidity security auditing and protocol research.

AI Context Engineering for Frontend — Patterns, prompts, and tools for UI development.