$ loading_
35295 Skills & MCP tools — copy a prompt, zero pre-install, into Claude Code / Codex / Cursor.
🎓 Skill = teach the AI how to do a task, copy & use; 🔌 MCP = connect the AI to an external tool/data source, usually needs a key.
Read Figma designs and quickly help turn interface structures into code.
Search, download, and extract frames or sheets from GIF sources via CLI.
Manage Feishu document and file sharing, access permissions, and collaborators.
Generate concept, architecture, flow, and whiteboard diagrams in multiple formats.
Extract key frames or short clips from videos for analysis and editing.
Find meme templates, suggest formats, and generate shareable meme images.
Clarify intent, requirements, and solution direction before any creative implementation work.
Build a motion foundation for React/Next.js with safe, accessible performance rules.
Forge complete OpenClaw lobster personas with lore, rules, names, and avatar prompts.
Convert UI screenshots or mockups into Vue 3 components in batch.
Build advanced motion, gestures, and animation sequences in React and Next.js.
Turn PRD intent into an implementation-ready capability plan with clear constraints.
Create reusable Manim animated explainers for technical concepts, graphs, and system flows.
Create animation-rich web presentations or convert PowerPoint decks for talks and pitches.
Learn SwiftUI architecture, state management, navigation, and performance best practices.
Generate images, videos, and audio with one unified AI media workflow.
Build reusable UI animations and transitions for React and Next.js products.
Build accessible React and Next.js interfaces with robust UI accessibility patterns.
Build polished React and Next.js animations with reusable production-ready patterns.
Learn frontend patterns for React, Next.js, state, performance, and UI best practices.
Edit footage, structure videos, add AI enhancements, and polish final cuts.
Search icons and generate Xcode-ready PNG asset sets for iOS apps.
Design safer EMR/EHR workflows, prescribing modules, and accessible clinical data-entry interfaces.
Create iOS liquid glass interfaces with dynamic visuals and interactive morphing.
从访谈内容留存、转写回看，到主题归纳与产品建议，一套串起用户研究整理流程。
从流量采集、营销归因到数仓查询与看板输出，一套串起自动取数和分析闭环。
从读取设计稿、提取上下文到映射组件库与同步评审，这套组合很适合设计到前端落地的协作链路。
In-depth guides on Skill / MCP setup and security — beyond the directory listings
普通聊天 AI 很难真正读懂大型仓库，因为它缺少结构、上下文和可验证的检索路径。本文从 0 到 1 搭一个只面向本地代码库的 Cursor 助手：能查结构、追调用链、看 diff、给重构建议，还能尽量压住幻觉。
Agent-hop 是一个基于 Rust 的 TUI，支持在进行中的 Claude Code 聊天里切换到其他编程代理，尽量不丢失上下文。项目作者提到，它最早源自一个简历与搜索工具，后来因为使用过程中的阻碍，单独做成了现在的界面。
Harden.run 表示，针对能够生成任意代码的 Coding Agent，单靠传统红队测试并不够。他们通过后训练网络安全小模型、调整推理方式，并结合 inline reference monitoring 等程序分析手段，在 LinuxArena 和 SleightBench 上取得了超过 GPT5.5-xhigh 的成绩。