150 boosters for "framework" — open source, verified from GitHub, ready to install
A template-based framework for generating domain-specific AI agents on Copilot, emphasizing quality control, workflow automation, and zero hallucination through structured skill execution and multi-step verification loops.
"name": "publishing-astro-websites-agentic-skill", "name": "Richard Hightower", "email": "rhightower@spillwave.com"
AI coding assistant instructions for contributing to the FlightPHP documentation site, helping developers understand project structure, contribution guidelines, and best practices for maintaining high-quality framework documentation.
"name": "codesession-marketplace", "name": "Brian Mwirigi", "email": "brianmwirigi@users.noreply.github.com"
PocketFlow-PHP is a set of Cursor rules that guide AI agents to build modular, agentic PHP applications using a minimalist LLM framework with strict architectural constraints. Developers using Cursor for PHP projects with AI assistance benefit from clear architectural guardrails.
"name": "maker-framework", "description": "Massively Decomposed Agentic Processes (MAD) - Break complex tasks into atomic steps with near-zero errors", "name": "MAKER Framework Team",
A Cursor IDE rule that implements state management within the CursorRIPER Framework, designed to help developers maintain consistent project state across AI-assisted development sessions.
ArmBench-LLM is a system prompt for benchmarking large language models using Armenian character-to-numeric matching tasks. It's designed for developers evaluating LLM performance across multiple coding platforms.
ArmBench-LLM is a system prompt framework for evaluating large language models on Armenian language tasks through structured multiple-choice questions. It's designed for developers and AI researchers who need standardized benchmarking tools across popular coding assistants and chat platforms.
Tool-evaluator is an agent that rapidly assesses development tools, frameworks, and services through structured benchmarking and comparative analysis to support informed technology adoption decisions. It benefits engineering teams and tech leads evaluating new solutions aligned with studio goals.
"name": "python-developer-plugin", "description": "Production-grade Python development plugin: web frameworks (Django, FastAPI), data science (Pandas, NumPy), testing (pytest), async programming, packaging, DevOps automation, and performance optimization", "name": "Dr. Umit Kacar & Muhsin Elcicek",
Expert guide for building AI-powered applications with the Glove TypeScript framework, helping developers create agent-based systems with tools and custom renderers. Ideal for developers working with Glove projects, React integrations, and AI model adapters.
A voice-controlled multi-agent framework for spawning and orchestrating AI workers across machines via CLI, SDK, and Telegram. Useful for developers building complex distributed AI workflows.
Copilot instructions for the OSAFW ASP.NET Core business application framework that guides developers through a structured task workflow with documentation, decision tracking, and post-processing optimization. Developers working with OSAFW on C# and ASP.NET Core projects benefit from standardized task management and knowledge capture.
Guidelines for contributing to the Astro framework monorepo, covering build systems, testing, coding conventions, and workflows. Essential for developers working on the Astro project itself.
PrismBench enables developers to create specialized LLM agents through YAML configuration for systematic evaluation of model capabilities using Monte Carlo Tree Search. Useful for ML engineers, researchers, and teams building production LLM systems who need comprehensive benchmarking and evaluation frameworks.
SpecLoom is a system prompt that enforces spec-driven development using a V-Model framework, ensuring AI-assisted design and code generation maintain traceability from requirements through implementation. It benefits teams adopting structured, specification-first development practices with Claude, Cursor, or Windsurf.
A self-generating MCP server framework that enables developers to create and deploy Model Context Protocol servers with built-in service management and development tooling. Useful for developers building AI integrations and Claude extensions.
PrismBench enables developers to create specialized LLM agents through YAML configuration for comprehensive benchmarking and evaluation of language model capabilities. Teams building AI evaluation systems and ML testing pipelines benefit from its systematic Monte Carlo Tree Search approach and containerized deployment.
GovRider MCP Server connects tech products and consulting services to thousands of live government tenders, RFPs, and grants from 25+ worldwide sources, updated nightly. It's ideal for founders, consultants, and businesses seeking government procurement opportunities.
A Cursor IDE configuration framework that establishes structured collaboration rules between humans and AI assistants, defining roles, communication styles, and contribution areas. Developers using Cursor will benefit from explicit guidelines on how to work with AI collaborators and onboard new ones.
FORGE Framework DevOps specialist agent that handles infrastructure, deployment, monitoring, and operational concerns with awareness of Claude model capabilities and MCP server integrations. Ideal for teams managing cloud infrastructure, CI/CD pipelines, and DevOps automation workflows.
MRF is a security-hardened metaprompting framework designed to protect AI agents from prompt injection attacks while enabling structured decision-making. It benefits developers building production agents on Claude platforms who need robust input sanitization and instruction clarity.
A QA-focused agent that provides comprehensive code review, testing strategy design, and quality assurance guidance for development teams. Ideal for developers and teams seeking to improve code quality, establish testing frameworks, and ensure professional coding standards.
