Browse skills

Edit PDFs with natural-language instructions using the nano-pdf CLI.

Work with Obsidian vaults (plain Markdown notes) and automate via obsidian-cli.

Local speech-to-text with the Whisper CLI (no API key).

Control Philips Hue lights and scenes via the OpenHue CLI.

Capture and automate macOS UI with the Peekaboo CLI.

Control Sonos speakers (discover/status/play/volume/group).

CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).

Three-layer progressive MCP client with Socket daemon. Query available tools, call MCP servers efficiently, and manage daemon processes. Reduces token overhead with lazy loading.

Extract frames or short clips from videos using ffmpeg.

制作哲学、心理、历史、经济、金融与科技等主题的 AI 动画解说视频。适用于 Agent 研究和组织选题、编写旁白、将 1–5 分钟视频拆成均衡的 Seedance 片段、按关键人物数量生成人物参考图、逐片段设计具体场景与多镜头视频提示词、保持旁白音色一致、制作带字封面，或规划基于 CLI 的多模态生成与拼接流程。当前正式维护的执行路径使用 LibTV CLI；查阅最新官方文档后，也可将该生产方法适配到 Higgsfield、即梦及其他同类多模态 CLI。

Create or receive human-first AI task handoffs across chats, models, devices, and languages. Use when the user asks to hand off, export context, resume from a handoff, switch sessions while preserving work, says "交接一下", "接收交接", or supplies handoff.md, handoff.zip, handoff-audit.zip, an LCH Bundle/T0 package, OCH Snapshot, or LTM Packet. Default to one readable handoff.md; upgrade to handoff.zip only when required files must travel, and to handoff-audit.zip only for formal audit, cross-organization delivery, or proof. Preserve current intent, stop point, next action, decisions, constraints, rejected and failed paths, answered questions, materials, omissions, and revalidation needs. Do not use for generic summaries, memory lookup, hidden reasoning, completed trivial chats, or after the user declines.

Make short product / skill motion videos (10–30 s, narrated feature demos up to ~60 s) the way high-end launch clips are made — kinetic type, real UI as the material, a hand that causes every reaction, beats that carry into each other instead of replacing each other, hard cuts only where they mean something — without HyperFrames or Remotion. A single HTML composition where every value is a pure function of time, built from a library of measured moves (springs, entrances, carries, contact, camera), rendered frame by frame with real shutter motion blur (1080p30 drafts, 4K60 final), with synthesised sound effects that share one room and an oracle that fails a slideshow before a human has to watch it. Use for 做个动效短片 / 产品宣传片 / 介绍视频 / 发布视频 / 15 秒 launch video / 给 skill 或 app 做个视频 / promo / teaser, for turning real pages or screen recordings into a cut, for product feature demos (产品功能演示 / 功能展示动效) where the UI is rebuilt in HTML from screenshots instead of screen-recorded (不录屏 / 复刻界面 / 截图还原 UI), for narrated cuts with voice-over and subtitles (配音 / 字幕 / 换配音) and for the same film in other languages (日语版 / 多语言 / 本地化), for adding motion vocabulary (动效库 / 转场 / 衔接), and for auditing why a motion video reads as a slideshow (像 PPT / 没节奏 / 一个一个展示 / 转场生硬).

Rewrites AI-generated content to sound natural, human, and conversational. Removes AI clichés, varies sentence structure, adds personality and real-world grounding.

AI desktop agent — control any app on Windows/macOS from your OpenClaw agent. Send natural language tasks and it handles opening apps, clicking buttons, typing text, and navigating browsers.

Convert YouTube videos to vertical short-form clips using yt-dlp, FFmpeg, and Whisper. Auto-detects highlights, crops to 9:16, and overlays subtitles.

X Intelligence CLI — search, analyze, monitor, and engage on X/Twitter. Real-time search, AI-powered analysis, sentiment reports, bookmarks, trending topics, and following management.

AI-friendly CLI for Jira designed for token efficiency and security. Manage issues, sprints, and projects with significantly fewer tokens than Jira MCP. Restricts AI actions to permitted operations.

Teach your AI agent to work natively with Obsidian. Covers Markdown formatting rules, Bases (Obsidian's native database layer), JSON Canvas diagrams, and the Obsidian CLI for full vault automation. Works with any agent platform.

Connect Google Analytics 4 to Claude, Cursor, and other MCP clients. Query GA4 traffic, user behavior, and conversion data using natural language. Supports 200+ dimensions and metrics via the GA Data API.

Connect Google Search Console to Claude, Cursor, and other AI clients. Query search analytics, inspect URLs, manage sitemaps, and find indexing issues through natural language. 460+ stars, 19 tools.

Telegram CLI for reading/searching messages, syncing archives, and sending or downloading files. Use when the user asks about Telegram chats, messages, contacts, groups, or files.

Generate raster images (PNG/JPEG/WebP) using the user's ChatGPT subscription via a local one-file Python CLI — no OPENAI_API_KEY, no gateway, no daemon. Two backends: web (default) drives the user's logged-in ChatGPT browser so generation runs on the conversation surface and does NOT consume Codex-usage limits; codex is a headless fallback that bills the Codex-usage bucket. Use when an agent needs to create a brand-new bitmap asset for the current project (photos, illustrations, icons, hero banners, mockups, sprites, concept art) and the output should be a bitmap file saved into the workspace. Do not use when the task is better solved by editing existing SVG/vector assets, writing code-native graphics (HTML/CSS/canvas), or extending an established repo icon system.

Converts books and documents (PDF, EPUB, DOCX, HTML, Markdown, plain text, RTF, MOBI/AZW with Calibre) into structured agent skills, extracting frameworks, mental models, principles, techniques, and anti-patterns. Use when the user wants to study a document through GitHub Copilot CLI, Amp, or Claude Code, apply an author's frameworks while working, or build a reusable knowledge base from a file.

>-