$ loading_
35753 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.
Monitor blogs and RSS/Atom feeds to catch new updates quickly.
Access X from the CLI for posting, search, DMs, and API calls.
Find meme templates, suggest formats, and generate shareable meme images.
Extract key frames or short clips from videos for analysis and editing.
Search, download, and extract frames or sheets from GIF sources via CLI.
Convert text into high-quality speech with a macOS say-like workflow.
Generate images, videos, and audio with one unified AI media workflow.
Create animation-rich web presentations or convert PowerPoint decks for talks and pitches.
Edit footage, structure videos, add AI enhancements, and polish final cuts.
Audit, plan, and implement SEO improvements for better search visibility.
Plan and execute multi-channel marketing campaigns from research to launch.
Find, qualify, and reach high-value leads with AI-driven outreach workflows.
Rank social graphs to find warm intros, bridges, and network gaps.
Conduct market research and competitive analysis with sourced, decision-ready summaries.
Schedule, publish, and track social posts across multiple platforms.
Post, read, search, and analyze X data through the Twitter API.
Draft concise, personalized investor outreach messages for fundraising conversations.
Ingest, analyze, search, edit, and monitor video and audio streams.
Organize inboxes, draft emails, verify sending, and follow up safely.
Post, search, read timelines, and analyze data via the X API.
Check live messages, recover recent codes, and verify the exact source inspected.
Create Slack-ready animated GIFs with optimized specs, validation, and animation guidance.
Enhance image quality, sharpness, and resolution for docs, presentations, and social posts.
Analyze your business and find quality leads with actionable outreach strategies.
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。