Awesome GitHub RepositoriesAgent Skill Definitions

ECC est un framework d'orchestration d'agents LLM et une suite d'outils IA multiplateforme conçue pour coordonner les flux de travail multi-modèles. Il fournit un système pour gérer les rôles d'agents spécialisés, les compétences réutilisables et la planification structurée pour exécuter des tâches de développement logiciel complexes à travers différents éditeurs de code alimentés par l'IA. Le projet se distingue en tant que gestionnaire de protocole de contexte de modèle, fournissant une couche de configuration pour intégrer des serveurs externes et auditer l'exécution des outils. Il implémente en outre un bac à sable de sécurité agentique qui restreint l'accès aux fichiers sensibles et recherche les fuites de secrets pour sécuriser les flux de travail autonomes. Le framework couvre de larges domaines de capacités, notamment l'automatisation du flux de travail de codage IA avec des garde-fous de développement piloté par les tests, l'optimisation des coûts des modèles par routage intelligent et la gestion de la mémoire isolée par état. Il inclut également des outils pour appliquer des normes de codage spécifiques au langage et gérer les comportements des agents à travers divers environnements de développement intégrés. Le système est géré via une interface en ligne de commande qui gère l'installation des outils, la réparation de la configuration et le déploiement des préréglages d'outils.

Mem0 is an agent-agnostic memory layer designed to provide intelligent agents with long-term persistence and cross-session state management. By acting as a centralized service, it allows diverse AI agents to recall user preferences, past interactions, and historical context, ensuring continuity across multiple workflows and independent agent systems. The platform distinguishes itself through a multi-signal retrieval engine that combines semantic vectors, keyword matching, and entity-linked metadata to surface the most relevant information. It employs an adaptive memory engine that automatical

Impeccable is a design system framework for large language models and an AI coding assistant plugin. It functions as an AI-driven UI generator and a rule-based design linter, providing a structured set of instructions and configuration files to standardize the production of professional user interfaces. The project features a design token orchestrator that maps standards across different AI provider environments and a config-driven factory for managing skills across multiple providers. It employs a deterministic rule engine to audit interfaces for accessibility violations, typography errors,

This project is a library of prompt-based skill definitions and functional extensions for AI assistants. It provides a system for automating product management tasks and strategic workflows by integrating specialized capabilities into coding agents and command line interfaces. The toolset utilizes a collection of standardized templates and guided processes to execute product management frameworks. These include tools for product discovery, market analysis, and business viability modeling, allowing users to chain analytical skills into end-to-end automated processes. The capability surface co

Openwork is an AI agent for desktop automation that uses large language models to execute browser tasks, manage local files, and automate desktop workflows. It operates on a local-first execution model, translating natural language prompts into sequences of tool calls to perform digital chores. The system functions as a framework for defining and saving repeatable sequences of actions as reusable skills. It integrates large language models with third-party services and local APIs to synchronize data and share files. The agent includes capabilities for headless browser automation to conduct r

This project is a collection of patterns and configurations for deploying AI agents with specialized technical skills and personas. It provides a framework for agentic software engineering, defining standards for AI-driven development workflows and the management of modular technical capabilities. The system features a skill framework that activates technical guidelines based on prompt intent and a context management system that preserves project state using persistent plans and checklists across session resets. It employs a modular organization of guidelines to prevent context window overflo

vibe-vibe is an LLM agent engineering framework and toolchain optimizer designed for orchestrating multi-agent systems. It serves as a comprehensive guide and methodology for transforming conceptual ideas into deployed applications through agentic software engineering. The project focuses on the orchestration of specialized AI agent roles with defined collaboration boundaries and iterative feedback loops. It provides frameworks for toolchain optimization, including the selection and evaluation of protocols that extend model capabilities and the design of standardized tool interfaces. The sys

OpenViking is a multi-tenant context server and knowledge base administration system designed to provide AI agents with persistent long-term memory. It enables the indexing of diverse documents and codebases to support retrieval-augmented generation, allowing agents to recall past interactions, user preferences, and learned experiences across sessions. The project is distinguished by its use of a URI-based virtual filesystem to organize memories, resources, and skills. It implements a tiered context loading system that balances retrieval precision with token budgets by structuring data into a