470 boosters for "lit" — AI-graded, open source, ready to install
AGENTS.md Version 2 enables AI agents to autonomously interact with websites using browser automation, allowing developers to automate complex web tasks programmatically. It's ideal for developers building AI-powered automation tools and agents that need reliable web interaction capabilities.
A system prompt that enables AI agents to automate browser tasks, navigate websites, and extract information by operating in an iterative loop. Developers and AI automation engineers use this to enhance AI capabilities for web automation across multiple platforms.
Heuristic scoring (no AI key configured).
A comprehensive guide to creating and managing autonomous agents within the CrewAI framework, enabling developers to build specialized AI agents with defined roles, capabilities, and collaboration features. Ideal for AI engineers and developers building multi-agent systems.
Get Shit Done (GSD) is a meta-prompting and context engineering system that helps developers coordinate AI-assisted workflows across multiple platforms while preventing quality degradation from context window bloat. Developers building with Claude, OpenCode, Gemini, and Codex benefit from its structured Plan→Execute→Verify→Complete pipeline.
This MCP server enables users to search and discover Agent Skills from the skills.sh registry, helping developers find and integrate pre-built automation capabilities into their AI agents.
A comprehensive tutorial for creating, registering, and deploying custom third-party agents that extend UFO² automation capabilities beyond Windows GUI automation. Developers building domain-specific automation agents (hardware control, Linux CLI, web automation, IoT) will find this invaluable for understanding the complete agent architecture and implementation workflow.
This MCP server enables browser automation capabilities within Claude and Cursor by providing programmatic control over web browsers. It's valuable for developers building AI agents that need to interact with web applications, perform testing, or gather web-based data.
TinyClaw enables developers to run multiple specialized AI agents simultaneously with isolated workspaces and independent configurations, allowing for task-specific agent teams that can be routed via simple @agent_id syntax. This is valuable for projects requiring diverse AI capabilities (coding, writing, analysis) working in parallel without state interference.
Ultracite is a Cursor rules booster that enforces strict code quality standards for TypeScript/JavaScript projects through automated formatting and linting via Biome. It's designed for developers who want zero-config, opinionated code standards focused on type safety, performance, and maintainability.
A Cursor IDE rules file providing comprehensive UI/styling guidelines for building responsive React components with HeroUI, Tailwind CSS, and accessibility best practices. Developers building social media automation tools in Cursor will benefit from these standardized component patterns and design specifications.
A MCP proxy that bridges Claude with JetBrains IDEs (IntelliJ, PyCharm, etc.), enabling developers to leverage IDE capabilities directly within Claude conversations. This benefits IDE users who want to integrate their development environment with AI assistance.
Tangle is a skill-based booster that guides multi-AI implementation for the development phase using Double Diamond methodology, with built-in quality gates for code validation and security checks. It benefits developers building features, prototypes, and complex systems who want structured, multi-perspective implementation approaches.
A GitHub Copilot instruction set that standardizes CHANGELOG maintenance and Dart/Flutter API documentation for the shadcn/ui Flutter ecosystem. Developers benefit from deterministic, high-quality contribution guidelines that ensure consistency across the project.
Natural language workflows that enable AI agents to perform complex, multi-step tasks with consistency and reliability.
