5,123 boosters — open source, verified from GitHub, ready to install
"$schema": "https://anthropic.com/claude-code/marketplace.schema.json", "name": "eze-skills", "url": "https://github.com/eze-is"
Launch background tasks for parallel execution. Enables concurrent work on independent tasks with result aggregation. Launch a background task or manage running tasks. Start a new background task:
A skill booster that automates the execution of work items across different operational modes (autopilot, confirm, validate) with support for batch processing, designed for AI-native development workflows on Claude Code.
A unified initialization booster that streamlines project setup by routing to specialized commands for documentation, preferences, and design tokens—ideal for developers standardizing new projects and maintaining consistent configurations.
"name": "seo-skills", "description": "Claude SEO Skills for the SE Ranking MCP server. Turns raw API data into finished deliverables across keyword research, content briefing, page intelligence, technical and content audits, structured data, drift monitoring, SXO diagnostics, competitive analysis, p
"name": "director-mode-lite", "description": "Use Claude Code like a Director, not a Programmer. Complete toolkit with 26 commands, 14 agents, 31 skills, and TDD-based Auto-Loop.", "name": "Lucas Wang",
This is a Shell/Markdown toolkit for Claude Code Director Mode. Keep shell scripts POSIX-compatible where possible. Markdown files are the primary deliverable.
A Cursor IDE rule set that enforces consistent Rust coding standards, project structure, and architectural patterns for the LLML library. Developers working on LLML in Cursor will benefit from automated guidance on module organization, naming conventions, and API design.
"description": "Review markdown documents with an interactive TUI. Leave inline comments, then let Claude address the feedback automatically.", "name": "Kevin Dutra" "homepage": "https://github.com/kevindutra/crit",
This file provides guidance to AI Agent when working with code in this repository. Pre-commit hooks: husky + lint-staged runs on and on . Full server-side rendering ( in astro.config.mjs). All pages are server-rendered by default. API routes must export .
A comprehensive guide for creating and managing autonomous agents within the CrewAI framework, enabling developers to build specialized AI team members with defined roles, goals, and collaborative capabilities. Ideal for developers building multi-agent AI systems who need clear patterns for agent design and configuration.
<!-- Real instructions live in config/config.md and meta/instructions/general.md. This file only bootstraps Windsurf into those. --> Check whether exists. If it does, you are in framework mode — this repo is being used to develop or maintain the llm-context-base framework itself, not as a personal
"name": "akii-seo-ai-search-optimizer", "description": "Free SEO + AEO + GEO toolkit by Akii. All skills run on your Claude Code session model (Claude Sonnet / Opus / etc). Aligned with Google's AI Optimization Guide for Google AI Overviews + AI Mode. Audit sites, plan content, optimize pages, gener
你是 Relic 引擎，一个能把万物锻造成可交互数字灵魂的系统。 如果用户说"让我跟奶奶聊天""让我跟咪咪互动""模拟星火工作室群聊"或类似的体验请求： 2. 根据蒸馏对象类型，从 选择合适的模板
"description": "Harness Engineering plugin exposing executable fitness functions for architecture quality, change-aware validation, and MCP-powered review context.", "version": "0.1.14", "homepage": "https://github.com/phodal/entrix",
You are a QA validation agent. Execute user stories against web apps using the skill. Walk through each step, screenshot every step, and report a structured pass/fail result. 1. Parse the user story into discrete, sequential steps (support all formats below) 2. Setup — derive a named session from t
Litmus spawns multiple OpenClaw subagents that experiment on your GPU overnight. Each runs on its own git branch in a shared lab repository — every experiment is a commit, agents can read each other's code, cherry-pick breakthroughs, and build on the global best at any time.
Superargs is an MCP server that enables dynamic runtime updates to MCP server arguments and environment variables without restarts. It's useful for developers building flexible AI agent systems that need to adapt configuration on-the-fly.
This file provides guidance to AI coding assistants working with code in this repository. photo-cli is a .NET 10 CLI tool that reads EXIF metadata from photos, reverse-geocodes GPS coordinates via Google Maps / OpenStreetMap / BigDataCloud, and organizes photos into structured folders with SQLite st
"name": "ai-software-architect", "description": "AI-powered architecture documentation framework with ADRs, reviews, and pragmatic mode", "name": "AI Software Architect Project"
Provides quick-start guidance and code examples for integrating Upstash Vector, a high-performance vector database, into TypeScript applications. Developers building RAG systems, semantic search, or embedding-based features will benefit from this unified entry point.
A GEO (search engine optimization) pipeline booster that analyzes, ranks, rewrites, and generates schema markup for URLs and content to improve search visibility. Useful for developers, content creators, and SEO professionals optimizing web content.
Rijksmuseum MCP Server provides Claude with integrated access to the Rijksmuseum's artwork collection for exploration and analysis. It enables developers and researchers to build AI-powered applications that leverage museum data.
A Cursor rules configuration that provides structured task analysis and execution framework for AI-assisted development, helping developers break down complex problems systematically while avoiding duplicate implementations.
