4,723 boosters for "r" — open source, verified from GitHub, ready to install
"name": "@whenmoon-afk/memory-mcp", "description": "Brain-inspired memory for AI agents - MCP server", "main": "./dist/index.js",
A skill booster that enables developers to commit conversation threads to tin version control directly from Claude Code. Useful for teams using tin as a conversation management system who want seamless integration with their coding workflow.
"name": "composure", "description": "Multi-tenant SaaS architecture plugin with decomposition enforcement, code quality hooks, task tracking, and structural code graph for impact-aware reviews.", "version": "1.18.7",
Enables developers to switch between tin version control branches directly from Claude Code, streamlining branch management workflows without leaving the IDE.
iOS Cursor Rules provides architectural guidance and best practices for AI-assisted iOS development in Cursor, covering MVC/MVVM/VIPER patterns and SwiftUI conventions to help developers maintain clean, scalable code.
Align all code suggestions, architecture recommendations, and technical solutions with this stack unless explicitly requested otherwise.
GiGL provides essential Cursor coding standards emphasizing explicit naming conventions and fail-fast error handling to improve code readability and maintainability. Developers working with graph neural networks and large-scale ML projects benefit from these foundational best practices.
"description": "Mission Planner, Agent Creator, Skill Creator, and Librarian — the complete Forge suite for science-backed AI team assembly", "name": "jdforsythe", "url": "https://github.com/jdforsythe"
<plan>$ARGUMENTS</plan> 1. Find latest in | 2. Parse plan for phases and status, auto-select next incomplete (prefer IN_PROGRESS or earliest Planned)
You are an expert in conversion optimization. Analyze the content based on the given issues: <issues>$ARGUMENTS</issues> 1. Headline 4-U Formula: Useful, Unique, Urgent, Ultra-specific (80% won't read past this)
"version": "1.34.1", "description": "Vibe Better With Claude Code - You're not an engineer anymore. You're a prompt jockey with commit access. At least do it properly.", "name": "Tiago Serôdio",
This MCP server integrates Nutrient's DWS Processor API with Claude, enabling AI agents to perform advanced document processing tasks including PDF handling, OCR, digital signatures, and redaction. Developers building document automation workflows and AI-powered applications benefit from seamless integration with Claude's context protocol.
"name": "claude-docs-prompts", "description": "A plugin to help claude build and maintain Cyfrin documentation sites",
An MCP Server that integrates TMDB (The Movie Database) API into Claude, enabling AI assistants to access movie and TV show information. Useful for developers building AI applications that need real-time entertainment data.
An MCP server providing sublinear-time mathematical algorithms for matrix solving and graph analysis, with speculative features around chaos theory and consciousness exploration.
"name": "ai-pm-copilot", "description": "PM toolkit with 15 agents, 23 skills, and 3 multi-agent team presets for solo developers and small teams", "repository": "https://github.com/slgoodrich/agents",
"name": "claude-code-superpowers", "description": "24 elite skills across 5 layers: discipline, domain expertise, intelligence, coordination, and execution. Turn Claude Code into a proactive engineering partner.", "name": "GadaaLabs",
You audit a single plugin in the monorepo before release. You do NOT fix anything — you report findings. You receive a plugin slug as the first argument (e.g. , , ). Throughout this prompt, refers to that argument and refers to . For domain plugins, the three core-version fields (, , for ) must r
Generate professional-grade structured project Wiki to directory. 1. 完整可运行：包含 import、初始化、调用、结果处理 2. 覆盖导出接口：每个主要导出 API 至少 1 个示例
A comprehensive tutorial chapter teaching developers how to build and deploy intelligent AI agents with tool use and automation capabilities in AnythingLLM. Ideal for engineers looking to add autonomous workflows and function-calling to their self-hosted RAG systems.
You run a single plugin's test suites and report results. You do NOT fix anything — you report pass/fail. You receive a plugin slug as the first argument (e.g. , , ). Throughout this prompt, refers to that argument and refers to . Plugins in this monorepo ship one of two test conventions. Detect a
"name": "specswarm-marketplace", "name": "MartyBonacci", "url": "https://github.com/MartyBonacci"
This is a TypeScript project — AI content pipeline using Claude Agent SDK + MCP. Use strict TypeScript, follow ESLint rules, prefer async/await.
Parse PDF, Office (Word/PPT/Excel), and image files into clean Markdown — with LaTeX formulas, tables, images, and OCR. One zero-dependency script, two backends, No , no API key. The free Agent API handles files ≤ 10 MB / ≤ 20 pages.
