1,554 boosters for "cu" — open source, verified from GitHub, ready to install
"name": "programming-as-theory-building-skill", "description": "Programming as Theory Building guidelines for coding agents, grounded in Peter Naur's paper and focused on preserving program theory during code work.", "name": "Programming as Theory Building Skill contributors"
"schemaVersion": "1.0", "name": "slidev-dev-marketplace", "description": "Evidence-based presentation creation with Slidev, enforced design guardrails, and multi-platform diagrams",
A Windsurf rules configuration that integrates ChromaDB via MCP Server, providing developers with structured guidelines for project setup, testing, code quality, and MCP server management in Cursor-compatible AI models.
"description": "VibeSurf integration - Control browsers, automate workflows, execute AI skills (search/crawl/js_code/summary), use Composio integrations (Gmail/GitHub/Slack), and run pre-built workflows", "name": "VibeSurf Community" "homepage": "https://github.com/vibesurf-ai/claude-surf",
"name": "open-agreements", "description": "Fill standard legal agreement templates and produce signable DOCX files. Supports Common Paper and Bonterms templates.", "name": "Open Agreements",
The FIRST action in the BEGINNING of EVERY response MUST be to initialize the conversation with this single tool call and display the banner from the response immediately after. It MUST be called EXACTLY ONCE per conversation and ONLY at the very beginning after receiving user input: EVERY assistant
"name": "revenue-os", "description": "Revenue Operating System - From code to customers to cash. A comprehensive monetization toolkit for developers.", "name": "Vladyslav Podoliako",
A mandatory human escalation agent that intercepts all errors and uncertainties across other agents to ensure human oversight. Useful for safety-critical workflows requiring explicit human approval before proceeding.
Enables developers and legal professionals to formalize contracts, regulations, and compliance logic as executable, type-checked code using L4, a functional programming language for computational law. Users benefit from automated validation, web app generation, and formal verification of legal rules.
This booster provides Cursor Rules documentation for ERA-EfficientRollbackArchitecture, explaining variable persistence in a Chinese development platform (酒馆). It is intended for developers using Cursor IDE with the 酒馆 system.
This Cursor rules file enforces production-readiness standards for a trading simulation app, including console removal, input validation, transaction safety, and UI/UX best practices. It benefits TypeScript/React developers building reliable financial applications.
agent-builder enables developers to create production-ready AI agents with pai-agent-sdk and Pydantic AI, including tools configuration, session persistence, and hierarchical agent setups. Ideal for building autonomous applications, chatbots, and HITL workflows.
name: strategic-partner A strategic thinking partner for Claude Code that separates deciding from building. Challenges assumptions, compares approaches, and hands execution a ready-to-run prompt
"name": "autonomous-agent", "version": "7.19.0", "description": "Revolutionary four-tier agent architecture with 35 specialized agents, 24 skills, and 40 commands focused on autonomous development, code quality, and validation. Strategic Analysis & Intelligence (Group 1) analyzes and recommends, Dec
Cursor Rules for react-router-dashboard-saas-template provides AI-assisted development guidance for a modern React 19 + Router 7 SaaS stack with RSC, Tailwind, Drizzle ORM, and form validation. Developers building or contributing to this specific template will benefit from standardized AI code generation and architectural patterns.
Use this skill as the primary orchestration layer for Writers Room Story Engine. Its job is to diagnose the current story phase, determine what is missing, and route to the appropriate supporting module instead of jumping straight into prose. The Writers Room Story Engine skill should not jump strai
"description": "A curated set of skills for each stage of development — propose, spec, design, plan, implement, ship.",
You are the STUCK AGENT - the MANDATORY human escalation point for the entire system. You are the ONLY agent authorized to use AskUserQuestion. When ANY other agent encounters ANY problem, they MUST invoke you. You are invoked when:
1. НЕ КОММИТЬ СЕКРЕТЫ — , , ключи, токены. Проверяй и перед коммитом 2. ПРОВЕРЯЙ .GITIGNORE — секреты должны быть исключены из трекинга 3. ДУМАЙ КАК УМНО СДЕЛАТЬ — перед действием: можно автоматизировать? MCP вместо CLI? Скилл вместо ручного? Создать скилл/заметку?
"name": "immich-photo-manager", "description": "MCP server for intelligent photo management with Immich — interactive HTML galleries with Cowork Actions Panel, geographic album curation, library cleanup, duplicate detection, people & face management, trash management, metadata repair, and 36 MCP too
DxMessaging provides Cursor-specific rules and guidelines for implementing a robust, game-engine-agnostic messaging solution. Developers building multiplayer games or systems requiring reliable inter-system communication will benefit from these standardized patterns.
Cursor rules for Convex best practices, providing guidelines for database schema design, queries, mutations, and function syntax in TypeScript/JavaScript projects. Useful for developers building Convex backends who want AI-assisted code review within Cursor.
Execute verbatim. All gates, evidence, output format, and compression receipts are defined there. This agent exists solely to leverage Claude Code's native skill frontmatter injection — DO NOT add logic here.
Reference documentation for embedding Prismatic's integration marketplace and workflow builder inside a customer-facing web application. Embedding Prismatic means your customers never leave your app to manage integrations. The flow is: 1. Your backend generates a short-lived signed JWT (10 min) auth
