$ loading_
60320 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.
Securely read and write local files, manage directories, and quickly search needed content.
Retrieve the latest library documentation with version-matched code examples for reference.
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.
Maintain an Obsidian-friendly knowledge vault with links, metadata, and structure.
Create, refine, validate, and restructure AgentSkills and SKILL.md files.
Regenerate OpenClaw release changelog sections from Git history before releases.
Prepare and verify OpenClaw stable or beta releases and release notes.
Draft OpenClaw release announcements and testing guidance from release evidence.
Search and manage Granola archives, sync status, notes, transcripts, and counts.
Create and review technical docs and agent instruction files in repositories.
Create, organize, search, and export Apple Notes from the macOS command line.
Refactor OpenClaw docs pages with source-checked preservation, clearer structure, and verification.
Search, export, sync, and analyze archived Notion content and related repo data.
Manage Feishu document and file sharing, access permissions, and collaborators.
Manage files, folders, and storage in Feishu cloud drive.
Manage Google Workspace apps from the command line in one workflow.
Create, search, and manage Bear notes on macOS via grizzly CLI.
Manage Things 3 tasks, projects, tags, and today lists on macOS.
Maintain an OpenClaw memory wiki with deterministic, source-backed page updates.
Summarize or transcribe URLs, videos, PDFs, and local files quickly.
Triage security advisories, drafts, and GHSA reports with trusted evidence.
Manage Obsidian vault notes, tasks, links, and plugins via CLI.
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。