Today's brief

Paperclip 是开源 Node.js + React 应用，可将 Claude Code、Cursor、Codex 等 AI Agent 像员工一样纳入组织架构。它通过仪表盘统一分配目标、审批策略并监控成本，把多 Agent 协调从终端命令升级为带预算与治理的企业级工作流。

anthropics/claude-plugins-official

Official, Anthropic-managed directory of high quality Claude Code Plugins. Claude Code Plugins Directory A curated directory of high-quality plugins for Claude Code. ⚠️ Important: Make sure you trust a plugin before installing, updating, or using it. Anthropic does not control what MCP servers, files, or other software are included in plugins and cannot verify that they will work as intended or that they won't change. See each plugin's homepage for more information. Structure /plugins - Internal plugins developed and maintained by Anthropic /external_plugins - Third-party plugins from partners and the community Installation Plugins can be installed directly from this marketplace via Claude Code's plugin system. To install, run /plugin install {plugin-name}@claude-plugins-official or browse for the plugin in /plugin > Discover Contributing Internal Plugins Internal plugins are developed by Anthropic team members. See /plugins/example-plugin for a reference implementation. External Plugins Third-party partners can submit plugins for inclusion in the marketplace. External plugins must meet quality and security standards for approval. To submit a new plugin, use the plugin directory submission form. Plugin Structure Each plugin follows a standard structure: plugin-name/ ├── .claude-plugin/ │ └── plugin.json # Plugin metadata (required) ├── .mcp.json # MCP server configuration (optional) ├── commands/ # Slash commands (optional) ├── agents/ # Agent definitions (optional) ├── skills/ # Skill definitions (optional) └── README.md # Documentation License Please see each linked plugin for the relevant LICENSE file. Documentation For more information on developing Claude Code plugins, see the official documentation.

Hindsight 是一个专为 AI Agent 设计的开源记忆系统，强调通过「学习」而非简单检索来积累长期记忆，在 LongMemEval 基准测试中获得领先表现。它支持 MCP 集成和多种嵌入式客户端，对需要构建持续学习 AI 体验的设计工程师而言，提供了可直接接入工作流的记忆基础设施。

obra/superpowers

An agentic skills framework & software development methodology that works. Superpowers Superpowers is a complete software development methodology for your coding agents, built on top of a set of composable skills and some initial instructions that make sure your agent uses them. Quickstart Give your agent Superpowers: Claude Code, Codex CLI, Codex App, Factory Droid, Gemini CLI, OpenCode, Cursor, GitHub Copilot CLI. How it works It starts from the moment you fire up your coding agent. As soon as it sees that you're building something, it doesn't just jump into trying to write code. Instead, it steps back and asks you what you're really trying to do. Once it's teased a spec out of the conversation, it shows it to you in chunks short enough to actually read and digest. After you've signed off on the design, your agent puts together an implementation plan that's clear enough for an enthusiastic junior engineer with poor taste, no judgement, no project context, and an aversion to testing to follow. It emphasizes true red/green TDD, YAGNI (You Aren't Gonna Need It), and DRY. Next up, once you say "go", it launches a subagent-driven-development process, having agents work through each engineering task, inspecting and reviewing their work, and continuing forward. It's not uncommon for Claude to be able to work autonomously for a couple hours at a time without deviating from the plan you put together. There's a bunch more to it, but that's the core of the system. And because the skills trigger automatically, you don't need to do anything special. Your coding agent just has Superpowers. Sponsorship If Superpowers has helped you do stuff that makes money and you are so inclined, I'd greatly appreciate it if you'd consider sponsoring my opensource work. Thanks! Jesse Installation Installation differs by harness. If you use more than one, install Superpowers separately for each one. Claude Code Superpowers is available via the official C…[truncated]

TypeScript 教育家 Matt Pocock 开源了他自用的 Claude agent skills 仓库，提供一套小型、可组合、模型无关的工程化技能集合，附带一键安装脚本。不同于完全放任的 vibe coding，这套技能旨在修复 Claude Code 与 Codex 等工具的常见失效模式，让开发者保持对真实工程流程的掌控。

Univer 是一个开源 Office SDK，支持在浏览器和 Node.js 中嵌入电子表格、文档、幻灯片等办公组件。其 Canvas 渲染、公式引擎和插件架构，使其成为构建 AI Agent 办公能力的底层运行时。项目近期登上 GitHub Trending，适合需要在产品中集成生产力工具的设计工程师。

Anthropic 在 GitHub 公开 Claude Skills 官方仓库，涵盖文档处理、MCP 生成与企业工作流示例。每个技能通过 SKILL.md 定义指令与资源，让 Claude 动态加载并执行品牌规范等定制任务。设计师与工程师可直接复用这些模式，将通用助手改造为懂内部规范的专业代理。

StarNet 是一款本地优先的桌面 AI agent 框架，将操作界面做成像素艺术空间站。用户摆放房间、走廊和物品，分别对应 agent 团队、交接通道和能力授权，让抽象的协作变成可拖拽的空间布局。支持多 agent 并发、自带密钥和外部消息接入，把可视化直接变成了运行时的真实工作流。

wifit3 是一款基于纯 Python 开发的跨平台 USB Wi-Fi 审计工具，支持 Linux、macOS 和 Windows。它内置无线协议栈，无需依赖 aircrack-ng，可实现多网卡聚合抓包、WPA/WPA2 握手捕获、PMKID 收集、EvilTwin 攻击及 WPS 破解等功能，目前登上 GitHub Trending 日榜。

Kelsey Hightower 的经典项目再登 Trending，从零开始手把手搭建 K8s 集群，不依赖自动化脚本，涵盖 etcd、TLS、containerd 等核心组件配置。但对产品设计师与设计工程师而言，这属于底层基础设施/DevOps 领域，与日常设计工具链、AI 创作工作流或前端交付毫无交集。

GitHub Trending 新晋全开源AI工程课程，共435节课、20个阶段约320小时，覆盖Python/TypeScript/Rust/Julia。课程要求从线性代数和反向传播开始手写代码，逐步构建Tokenizer、Attention机制直至MCP服务器和自主智能体集群，每节课均产出可复用工程产物。

一个面向A股投资者的自托管量化工作台，集成选股、回测、异动监控与LLM策略分析，支持插件化数据源与Docker一键部署。虽然技术栈完整，但其核心场景是金融量化交易，与设计师日常工具链完全无交集。

AX 是 Google 开源的声明式智能体编排框架，用类似 Kubernetes 的 YAML 语法定义任务与沙箱环境，解决 AI Agent 在隔离、状态管理和规模化运行中的痛点。设计工程师可将其用于部署自动化设计 Agent 或模型工作流。

NVIDIA 开源模型优化库 ModelOpt 整合量化、剪枝、蒸馏与推测解码等 SOTA 技术，支持将 Hugging Face 与 PyTorch 模型压缩后导出至 TensorRT-LLM、vLLM 等推理框架。其 Hugging Face Export API 最新覆盖 transformers 与 diffusers 模型，对生成式 AI 模型的端侧部署有一定意义。

Impeccable 是一套面向 Claude 的开源前端设计技能库，在 Anthropic 官方 frontend-design 基础上扩展了 7 大领域参考、23 条命令与 27 条反模式规则，并配有 CLI 和浏览器扩展。它通过共享设计词汇与自动审计，帮助设计工程师让 AI 输出摆脱千篇一律的 SaaS 模板感。

OpenBao 是 HashiCorp Vault 的开源替代品，专注于密钥、证书等敏感数据的存储与分发。虽然登上 GitHub Trending，但它属于纯后端基础设施工具，与产品界面设计、AI 创作或设计工程完全无关，目标读者没有直接实操价值。