1,753 boosters for "AI" — open source, verified from GitHub, ready to install
当用户对已有老板 Skill 说以下内容时，进入进化模式： 当用户说 时，展示预置老板列表供选择： 当用户在任何模式下说 草、卧槽、我靠、怎么怼、教我反击 时，进入反击模式。
"description": "Nemp Memory — Cognitive memory layer for AI agents across every platform. Local-first, zero cloud, works with Claude, Codex, Cursor, and Windsurf.", "name": "Sukin Shetty", "email": "contact@nemp.dev",
This skill generates reusable Relay-based Nodes components that: Activate this skill when users ask to: The skill automatically determines:
"name": "@context-sync/server", "description": "Universal Context layer McP server", "main": "dist/index.js",
"name": "@cyanheads/mcp-ts-core", "version": "0.2.11", "mcpName": "io.github.cyanheads/mcp-ts-core",
An MCP Server that integrates Alibaba Cloud DevOps API capabilities into AI assistants, enabling automated participation in development workflows and team collaboration optimization. Useful for teams using Alibaba Cloud infrastructure who want AI-assisted DevOps processes.
你是一位精通台灣各類正式文件撰寫的專家。你的任務是根據使用者的需求，判斷文件類別，並依照對應的規範產出格式正確、用語合規的文件。 收到使用者請求後，先判斷文件屬於哪一類。如果無法從使用者描述中確定，主動詢問： 使用者不一定會明確指出類別，以下線索幫助你判斷：
Memelord is a persistent memory system for AI coding agents that uses vector search and reinforcement learning to help agents learn from past interactions. It's useful for developers building sophisticated coding assistants that need to retain and leverage historical context.
You are "TunaCode", a Staff-level software developer agent inside the user's terminal. You are not a chatbot. You are an operational agent: you search, read, write, and execute code. Think step by step. Be direct, neutral, and concise.
Spawn N parallel API workers for any long-running or multi-turn batch task. Auto-calculates optimal worker count and stagger delay. Supports tiered model delegation: orchestrator plans with a frontier model (V4 Pro), workers execute with a cheaper model (V4 Flash). DeepSwarm 2.0 generalizes the prov
This MCP server bridges n8n workflow automation with Claude by providing programmatic access to workflows, executions, and credentials through the Model Context Protocol. It's valuable for developers and automation engineers who want to integrate n8n capabilities into AI-powered applications and Claude instances.
The Outline API is not purely RESTful. All endpoints use POST and never GET, PUT, or any other HTTP method.
Resource Scout helps developers quickly find existing Claude Code skills and MCP servers from marketplaces and repositories before building custom solutions. It's essential for anyone looking to avoid reinventing the wheel and discover pre-built integrations.
你是一位专业的股票分析师，通过 Python 脚本获取真实市场数据，结合技术分析和消息面，为用户生成决策看板。 脚本支持分级降级策略，零配置即可运行，配置 API Key 后数据更精准： 3. 执行（先尝试直接运行，加 --news 可同时搜索新闻）：
A life management AI assistant that proactively handles daily planning, evening reviews, health tracking, and investment monitoring through event-driven workflows triggered by natural language keywords in both English and Chinese.
ZAI CLI is a command-line tool that brings AI-powered capabilities—including vision analysis, web search, page reading, and GitHub exploration—directly to developers and AI coding assistants. It's useful for developers who need programmatic access to vision, search, and code discovery features.
DyNote 是面向 Codex 这类 Agent 的抖音学习工具，不是一次性摘要器。核心原则是“数据资产先行，学习笔记后置”：先把字幕/转写、评论、元数据和 AI 快读沉淀为可复用资产，再按用户需求生成可追溯的学习笔记、总结和写作材料。默认目标不是字幕工程文件，而是先落一份原始数据包：、、、、、、，并用 归档可复用资产。默认把独立字幕轨或本地自动语音识别转写当作事实主干；当转写密度低、任务需要画面理解或用户只要快速筛选时，再用已登录抖音网页版的“问AI / 识别画面”补充，豆包只作为抖音 AI 不可用时的备用快读或待核验假设。 联网或登录态操作必须先使用 。不要读取、复制或打印 Cooki
A local SQLite-based command-line task board for AI agents and developers to manage multi-step coding tasks, track progress, and coordinate work across sessions without external dependencies. Ideal for breaking down complex implementations into trackable subtasks with comments and checklists.
A plaintext-first docstring formatting specification for Python code that standardizes documentation style across projects. Developers writing or maintaining Python codebases benefit from consistent, readable documentation practices.
Anti-Slop Toolkit provides automated detection and cleanup for AI-generated code patterns across Python, R, and text files, helping developers enforce quality standards in CI/CD pipelines and codebases.
A Google Calendar CLI tool that enables AI assistants to view, create, manage, and check availability across multiple calendar accounts. Useful for developers and AI applications that need programmatic calendar integration.
Manage tasks and dependencies with Tracer CLI. Use for issue tracking, dependency management, finding ready work, and AI agent workflows.
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, and model persistence. Should be invoked for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.
Ray is an expert booster for Apache Ray distributed computing that helps developers convert Python code to Ray workloads, debug applications, and optimize performance across Ray's ecosystem (Core, Data, Train, Serve, Tune). Ideal for ML engineers and Python developers scaling computations from single machines to clusters.
