趋势榜

为 Claude Code 提供 471 个插件、3,069 个 Skill、347 个 Agent。开源市场位于 tonsofskills.com，配备 ccpi CLI 包管理器。471 plugins, 3,069 skills, 347 agents for Claude Code. Open-source marketplace at tonsofskills.com with the ccpi CLI package manager.

多 Agent 编排 AI 编码 CLI —— Claude Code、Kiro、Codex 等，在隔离的 tmux 会话中协同调度Multi-agent orchestration for AI coding CLIs — Claude Code, Kiro, Codex, and more, coordinated in isolated tmux sessions

一份共享记忆，被 Claude Code、Codex、Cursor、Copilot CLI、OpenClaw 以及另外 29 个 coding agent 共同使用，基于磁盘上已有的会话历史构建。在任一 agent 中发现的修复会自动同步到其他所有 agent，包括安装前数月的会话。无需 LLM，无需 embeddings，单个本地 Go 二进制。One memory shared by Claude Code, Codex, Cursor, Copilot CLI, OpenClaw and 29 more coding agents, built from the session history already on disk. A fix found in one agent comes back in any of them, including months of sessions from before you installed it. No LLM, no embeddings, one local Go binary.

SAM Sovereign Agent MeshSAM Sovereign Agent Mesh

一个 Model Context Protocol (MCP) 服务器，使 AI 助手能够与 AKS 集群交互，作为 AI 工具（如 Claude、Cursor 和 GitHub Copilot）与 AKS 之间的桥梁A Model Context Protocol (MCP) server that enables AI assistants to interact with AKS clusters. It serves as a bridge between AI tools (like Claude, Cursor, and GitHub Copilot) and AKS.

Mario Kart Wii，原生运行于 iOS、iPadOS 和 MacOSMario Kart Wii, native for iOS, iPadOS, and MacOS.

类似 unix du 的命令行工具，用于统计每个文件和目录的 token 使用量a unix-like du command line tool to count token usage per files and directories

通过 MCP 为 Claude Code 提供持久化长期记忆 — 跨会话捕获编码决策、Bug 修复和上下文。采用 FTS5 + TF-IDF 混合搜索与 episode 批处理。单一 SQLite 数据库，无需外部服务。作为 claude-mem 的替代方案，成本降低 600 倍。Persistent long-term memory for Claude Code via MCP — captures coding decisions, bugfixes, and context across sessions. Hybrid FTS5 + TF-IDF search with episode batching. Single SQLite DB, no external services. Alternative to claude-mem with 600x lower cost.

一个 Model Context Protocol (MCP) 服务器，使 AI 助手能够与 Kubernetes 集群交互，作为 AI 工具（如 Claude、Cursor 和 GitHub Copilot）与 Kubernetes 之间的桥梁A Model Context Protocol (MCP) server that enables AI assistants to interact with Kubernetes clusters. It serves as a bridge between AI tools (like Claude, Cursor, and GitHub Copilot) and Kubernetes

2026 年最佳 Dead Island 2 训练工具：高级作弊引擎。Best Dead Island 2 Trainer Tool 2026: Advanced Cheat Engine

2026 年面向现代音乐人的交互式钢琴乐谱训练工具。Interactive Piano Sheet Music Trainer for Modern Musicians 2026

MonoTrainer 2026：创建自定义健身与游戏训练计划的最佳工具。MonoTrainer 2026: Best Tool for Creating Custom Fitness and Game Training Programs

Best Mafia Old Country Trainer & Mod Menu 2026（Windows 版）Best Mafia Old Country Trainer & Mod Menu 2026 for Windows

Ultimate Flux1-LoRA Training Toolkit 2026：面向 AI 创作者的智能极简训练工具Ultimate Flux1-LoRA Training Toolkit 2026: Smart Simplicity for AI Creators

2026 年终极 Big Walk 伴侣工具：高级策略叠加与 Mod 中心。Ultimate Big Walk Companion Tool 2026: Advanced Strategy Overlay & Mod Hub

阿里云 2026 自动化 LoRA 训练 Docker 构建Automated LoRA Training Docker Builds for Alibaba Cloud 2026

ModeAtlas 2026：面向开发者的 AI 驱动代码仓库情报工具。ModeAtlas 2026: AI-Powered Repository Intelligence for Developers

Ultimate Hysteria Modding Framework 2026：UE3 运行时反射 API 与资源工作室Ultimate Hysteria Modding Framework 2026: Runtime Reflection API & Asset Studio for UE3

2026 年最佳 OpenGL FPS 练枪工具。Best OpenGL Aim Trainer for FPS Mastery 2026

Alan Wake 2 Ultimate Trainer 2026：专业游戏增强与 PC 优化器Alan Wake 2 Ultimate Trainer 2026: Pro Gameplay Enhancer & PC Optimizer

2026 年顶级 EFT ESP 与透视叠加层：玩家、战利品与撤离点追踪器。Top EFT ESP & Wallhack Overlay 2026: Player, Loot & Extract Tracker

2026 年最佳硬核专注计时应用：NoMoreBS 生产力工具。Best Brutal Focus Timer App 2026: NoMoreBS Productivity Tool

PokePlus 2026：PokeMMO 冒险智能自动捕捉与对战机器人PokePlus 2026: Smart Auto-Catch & Battle Bot for PokeMMO Adventures

Kingdom Come 2 Trainer 2026 Windows 11 终极指南与安装。Kingdom Come 2 Trainer 2026 Ultimate Guide & Setup for Windows 11

"通过可复用代码实现可复现研究" 研讨会课程材料Lesson material for Reproducible research through reusable code workshop

GAP 的引文管理器支持。助力报告、论文、数据和演示的引用！Citation manager support for GAP. This helps with citations for reports, papers, data, and presentations!

CPersona — 持久化 AI 记忆服务器，具备 3 层混合搜索、置信度评分和 30 个工具，MIT 许可。CPersona — Persistent AI memory server with 3-layer hybrid search, confidence scoring, and 30 tools. MIT licensed.

AI辅助的系统文献综述，附带可追溯证据。AI-assisted systematic literature reviews with traceable evidence.

使用此 XeLaTeX 模板为 Xiamen University Malaysia 格式化作业，包含标准页眉与 APA 引文。Use this XeLaTeX template to format assignments for Xiamen University Malaysia with standard headers and APA citations.

为 LLM Agent 自动化学术文献搜索、检索和管理工作流，使用面向主流数据库的集成研究 Skill。Automate academic literature search, retrieval, and management workflows for LLM agents using integrated research skills for major databases.

基于关键词反馈的每日 arXiv 论文推荐Daily arXiv paper recommendations with keyword feedback

一个基于源材料的 Codex Skill，用于严谨的数学和统计写作、分析与验证A source-grounded Codex skill for rigorous mathematical and statistical writing, analysis, and verification.

课程共享工作文件夹。Shared Work folder for the course

严格忠于数据和解读的双语科学写作 SkillBilingual scientific writing skill with strict data and interpretation fidelity

综述：总结涵盖主要 NLP 任务的 10 篇深度学习研究论文Survey summarizing 10 deep learning research papers across major NLP tasks.

文献综述论文筛选器 —— 本地 Agent Skill（搜索、证据打包、验证、Excel 渲染）。云端模板为专有。Literature Review Paper Screener - local agent skill (search, evidence packaging, validation, Excel rendering). Cloud template is proprietary.

Python 包，作为可复现的科学刺激生成视觉、听觉和视听错觉 —— 17 个已编目错觉导出为 PNG、WAV、GIF、MP4 和 NPZ，附带 SHA-256 清单与确定性随机种子，含 15 个附带源数据边车的发表级图表，测试覆盖率 90% 以上Python package that generates optical, auditory and audio-visual illusions as reproducible scientific stimuli — 17 catalogued illusions exported to PNG, WAV, GIF, MP4 and NPZ with SHA-256 manifests, deterministic seeds, 15 publication figures with source-data sidecars, and 90%+ test coverage.

语言 case 的范畴论处理，集成 Active Inference 与 CEREBRUM 架构：DisCoPy 弦图横跨类型学、范畴语法、拓扑斯理论及量子扩展，生成 30 个发表级图表与一篇 24 节的手稿。1,207 个测试，覆盖率 95.96%，零 mockCategory-theoretic treatment of linguistic case integrated with Active Inference and the CEREBRUM architecture: DisCoPy string diagrams spanning typology, categorial grammar, topos theory, and quantum extensions, generating 30 publication figures and a 24-section manuscript. 1,207 tests, 95.96% coverage, zero mocks.

面向 arXiv 与 Semantic Scholar 的 Scrapy Spider，聚焦非洲 AI 生态 — 导出包含引用次数的丰富 CSV。Spiders Scrapy pour arXiv et Semantic Scholar, centrés sur l'écosystème IA africain — export CSV enrichi du nombre de citations.

AI 工程作品集，聚焦可控 Agent、可复现研究与本地生成式 AI 基础设施AI engineering portfolio focused on controllable agents, reproducible research, and local generative AI infrastructure.