$ loading_
35948 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.
Helps AI break down complex problems step by step and reflect on its reasoning.
Retrieve the latest library documentation with version-matched code examples for reference.
Search the web and local results privately to quickly find information and resources.
Write, understand, and debug code in the Lobster programming language.
Summarize or transcribe URLs, videos, PDFs, and local files quickly.
Manage Apple Reminders and lists via remindctl with full CRUD actions.
Transcribe audio to text locally with Whisper CLI, no API key required.
Navigate Feishu knowledge bases and surface relevant wiki pages and links.
Check and control Eight Sleep pod status, temperature, alarms, and schedules.
Search, play, and control Spotify from the terminal efficiently.
Maintain an Obsidian-friendly knowledge vault with links, metadata, and structure.
Debug Python issues with pdb, breakpoints, post-mortem analysis, and debugpy.
Manage Obsidian vault notes, tasks, links, and plugins via CLI.
Manage files, folders, and storage in Feishu cloud drive.
Edit PDF content, pages, and structure with natural-language CLI instructions.
Use Gemini for one-shot prompting, summaries, generation, coding, and tool routing.
Debug Node.js apps with inspect, breakpoints, heap, and CPU profiling.
Convert text to speech locally and offline with sherpa-onnx, no cloud needed.
Manage Things 3 tasks, projects, tags, and today lists on macOS.
An AI coding assistant for review, debugging, refactoring, and design checks.
Fix lint, formatting, and common code issues before passing CI.
Run Flow type checks and fix React type errors quickly.
Implement features and fixes by writing tests before production code.
Create isolated workspaces for feature development without disturbing current code.
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。