109 boosters for "language" — open source, verified from GitHub, ready to install
Named in homage to Tagore, whose prose carried what frontier models reach for and miss: a point of view, specificity over abstraction, and restraint over puffery. The skill exists to bring those qualities back to AI-drafted text. You are a writing editor whose job is to make prose sound like a human
"description": "Production-ready Claude Code configuration with role-based workflows (PM→Lead→Designer→Dev→QA), safety hooks, 44 commands, 19 skills, 8 agents, 43 rules, 23 hook scripts, auto-learning pipeline, hook profiles, and multi-language coding standards", "name": "xiaobei930", "url": "https:
A Windsurf rules collection that guides AI coding assistants in implementing data-driven UI testing patterns, helping developers separate test logic from test data for improved maintainability and scalability.
A .windsurfrules collection that guides AI coding assistants in implementing rigorous backtesting techniques for trading strategies, helping developers avoid common pitfalls like lookahead bias and overfitting. Useful for quants and trading engineers building reliable strategy validation systems.
A curated collection of Windsurf rules files that guide AI coding assistants in generating Helm charts following industry best practices, architecture patterns, and Kubernetes conventions. Developers using Codeium's Cascade or similar AI tools benefit by getting standardized, production-ready Helm chart scaffolding and configurations.
A Windsurf rules collection that guides AI coding assistants to implement Gitflow branching workflows and best practices. Useful for teams adopting structured version control and release management processes.
A curated collection of .windsurfrules files that guide AI coding assistants in generating performant, well-architected code by establishing best practices for optimization, database tuning, caching, and concurrency. Developers using Windsurf/Cascade benefit from standardized coding patterns that reduce manual code review overhead.
The user provides a sentence or paragraph that needs verification. The AI must NOT "run a quick search, glance at a few web snippets, and improvise a conclusion." It must dig down to original trustworthy sources, or honestly admit it cannot. Five scenarios are covered: 1. Basic truthfulness check: w
<!-- Bilingual skill: this SKILL.md is the English primary; the Chinese mirror is SKILL.zh.md. Each references/.md has a Chinese mirror references/.zh.md (same content, two languages). The .md files are authoritative for the agent; the .zh.md files are for human readers. -->
"description": "Skills for developing with Lean 4 and Mathlib — proof methodology, toolchain setup, bisection, and more", "name": "Lean FRO, LLC" "homepage": "https://github.com/leanprover/skills",
This MCP server enables developers to manage Home Assistant directly from Cursor, VS Code, or Claude Code using natural language—creating automations, dashboards, and configurations without leaving their IDE. It's essential for smart home enthusiasts and developers who want AI-assisted Home Assistant development.
"name": "apple-mail", "description": "Manage Apple Mail through natural language - read, search, send, and organize emails (macOS only)", "name": "Rob Sweet",
You are an expert App Store Optimization (ASO) strategist with full App Store Connect integration via direct API calls. Generate optimized App Store metadata with competitor analysis and localization. Setup credentials, check status, and sync metadata.
"name": "ralph-dev", "version": "0.4.10", "description": "Autonomous end-to-end development system - from requirement to production-ready code with zero manual intervention",
This skill transforms annual goals or detailed plans into an actionable, trackable execution system. It provides daily guidance, task management, progress tracking, and regular reviews to ensure users achieve their objectives. This skill uses Claude's memory system to persist user data across conver
"name": "semantic-search", "description": "Search your local documents with natural language. Index folders of PDFs, Word docs, markdown, and more — then ask questions in English or German and get answers with source citations.", "name": "Omar Drljevic"
Heuristic scoring (no AI key configured).
NexA4A is a meta-agent system prompt that creates specialized AI agents from natural language requirements, enabling product managers and developers to automate task creation and management across multiple coding platforms.
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.
RagCode MCP is a semantic code navigation tool that integrates RAG-powered code search into Windsurf and other IDEs, enabling developers to intelligently query and understand multi-language codebases using local LLMs. It's ideal for developers working with Laravel, Go, Python, and PHP who need fast, context-aware code exploration without leaving their IDE.
Cortex is a local-first knowledge graph that automatically watches your project files, extracts entities and relationships using LLMs, and enables natural language queries across multiple projects. It's ideal for developers who need intelligent cross-project search and knowledge management without relying on external services.
DynamicEndpoints Autogen_mcp enables creation and management of collaborative AI agents that solve problems through natural language interaction. Developers and AI teams benefit from orchestrating multi-agent workflows across Claude Desktop, Claude Code, and Cursor.
"$schema": "https://anthropic.com/claude-code/marketplace.schema.json", "name": "XiaoConstantine", "email": "constantine124@gmail.com"
"name": "@dpantani/tdmcp", "mcpName": "io.github.Pantani/tdmcp", "description": "tdmcp — the TouchDesigner MCP server. Build real TouchDesigner visual systems from plain language with Claude, Cursor, or Codex (Model Context Protocol).",
