$ loading_
36505 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.
Send and receive Slack messages, manage channels, and handle workspace collaboration tasks.
Manage Trello boards, lists, and cards to streamline team task tracking.
Triage inbox messages, route intents, track replies, and generate follow-up summaries.
Generate concept, architecture, flow, and whiteboard diagrams in multiple formats.
Manage files, folders, and storage in Feishu cloud drive.
Manage issues, PRs, logs, releases, and repos with GitHub CLI.
Read, edit, and write Feishu documents for faster cloud collaboration.
Generate shareable code or text diffs for review and collaboration.
Manage, search, and send IMAP/SMTP email efficiently from the command line.
Find meme templates, suggest formats, and generate shareable meme images.
Chat directly with the Discord-backed OpenClaw agent in real time.
Access X from the CLI for posting, search, DMs, and API calls.
Convert text into high-quality speech with a macOS say-like workflow.
Search and analyze Slack archives, count threads, and support repo workflows.
Archive, search, and summarize Discord messages and direct messages.
Draft OpenClaw release announcements and testing guidance from release evidence.
Manage Feishu document and file sharing, access permissions, and collaborators.
Review, triage, and manage OpenClaw issues and pull requests faster.
Preview local channel message flow fixtures to inspect conversation flow behavior.
Clarify intent, requirements, and solution direction before any creative implementation work.
Coordinate GitHub and Linear workflows for triage, tracking, and execution alignment.
Plan and execute multi-channel marketing campaigns from research to launch.
Unify multi-channel notifications for routing, deduplication, escalation, and inbox consolidation.
Turn PRD intent into an implementation-ready capability plan with clear constraints.
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。