Skills
100,696 packaged capabilities and playbooks for agents. Install any of them with one command.
All
React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.
Extract audio from video files or URLs (including YouTube). Supports MP3, WAV, M4A, FLAC, OGG, and OPUS formats. Can process local video files or download from URLs. For YouTube videos, uses yt-dlp for direct audio extraction when possible.
AI video creation and editing — generate videos from text descriptions, edit with background music, sound effects, titles, transitions, and export finished MP4 videos directly in chat. No GUI needed. Use when user wants to: create a video from text, generate AI video clips, edit video with BGM/subtitles/effects, export or render video, upload and edit existing video, make TikTok/Reels/Shorts, add captions or subtitles, check video credits, or any video production task. Supports mp4, mov, avi, webm, mkv, jpg, png, gif, webp, mp3, wav, m4a, aac. Free trial with 100 credits. 关键词：AI视频制作、视频剪辑、文字生成视频、短视频制作、视频导出、添加字幕、添加背景音乐。
Generate attention-grabbing hooks for the first 3 seconds of videos. The hook determines if viewers stay or scroll. Creates multiple hook variations for A/B testing. Use when crafting video openings, improving retention, or creating scroll-stopping content for YouTube, TikTok, or Reels.
Turn a video file someone already has (an MP4, a Loom download, a long call or screen recording) into Jams (shareable jam.dev recordings with a transcript), one per issue, cut where the speaker moves to a new problem, each titled and filed in a folder. Use when the user says "upload these to jam", "turn this recording into jams", "split this video by bug", "make these jams instead of mp4s", or has a recording too long for one Jam.
Measure your own writing corpus for the words and sentence shapes you over-use, so an agent writing in your voice stops amplifying your tics into a style. Produces a counted baseline file and checks any new draft against it. Use when an agent's drafts start sounding like a caricature of you, before publishing anything written in your voice, or every ten new pieces to re-measure.
Volcengine compliance best-practices assistant: (1) based on the user's needs (compliance standards to meet, keywords, risk levels of concern), recommend which built-in Volcengine conformance pack templates to enable and flag which are already enabled; (2) summarize the account's current compliance posture, aggregating the evaluation results of active rules/conformance packs (built-in + user-defined) by category (regulatory / best practice / custom) and severity into a compliance overview report; (3) when the official baseline does not cover a case, guide the user in writing a Rego policy as a custom compliance rule and registering the evaluation. Can deploy recommended templates as conformance packs after user confirmation. Use when the user wants to do "compliance check / compliance inspection / security compliance / compliance best practices / which compliance rules to enable / MLPS compliance / is my Volcengine account compliant / what is non-compliant / help me write a custom compliance rule", or mentions Volcengine "Config / conformance pack / Rego policy". Trigger on the keywords 火山 / 火山引擎 / volcengine combined with compliance scenarios. Deploying conformance packs / registering custom rules are write operations and require user confirmation; compliance reports and resource remediation are strictly separated.
Web design and deployment. Generates polished single-page HTML pages (reports, landing pages, data visualizations, etc.) with one-click deployment to Cloudflare Pages. Uses the Tailwind CSS + Chart.js + Font Awesome stack. Use when the user asks to build a web page, generate a report page, create a landing page, present data visualizations, or deploy a page online.
Use this skill when a content-complete website has missing/placeholder images and needs visual assets — scenario illustrations, tool screenshots, instructor cards, conceptual diagrams, classroom location maps, QR codes. Triggers on phrases like "插圖", "工具截圖", "QR", "講師卡", "地圖", "示意圖", "Playwright 爬蟲", "AI 生圖", "visual assets", "screenshots", "illustrations", "QR codes", "instructor cards". This skill covers the four asset sources (scraping, AI generation, hand-drawn SVG, generated codes), the PNG-first + SVG-fallback render pattern, and verification scripts. Usually invoked AFTER interactions are wired (so missing images are visible), but can be invoked earlier if assets are pre-planned.
Web extraction for AI agents. Scrape, crawl, map, batch, extract, summarize, diff, brand, search, and 28 site-specific extractors turn any URL into clean Markdown, text, or JSON. Runs locally with no key via the webclaw MCP server; set an optional WEBCLAW_API_KEY to handle bot-protected and JavaScript-rendered pages. Use when web_fetch returns blocked or empty content, or you need structured, LLM-ready extraction.
Video Channel content search tool. Search popular Video Channel posts using keywords provided by the user, with sorting by newest, most likes, most saves, or relevance. Results are displayed in a structured table. Use when users want to find popular Video Channel content, search for viral videos, query post data, or learn how a type of content performs on Video Channel. Trigger phrases include: Video Channel search, Video Channel post lookup, viral Video Channel posts, popular Video Channel posts, Video Channel content search, search Video Channel, WeChat Video Channel search. When the API returns insufficient points (code=3210), automatically launch Alipay to top up and continue the search.
Expert guidance on building WASM apps for Wendy Lite MCU firmware on ESP32-C6. Use when developers mention: (1) Wendy Lite or wendy-lite, (2) WASM apps on ESP32 or microcontrollers, (3) WendyLite Swift package or import WendyLite, (4) building C/Rust/Swift/Zig apps for ESP32, (5) WAMR runtime on embedded devices, (6) GPIO/I2C/SPI/UART/NeoPixel from WASM, (7) Embedded Swift on WASM or wasm32-none-none-wasm, (8) BLE provisioning on ESP32-C6, (9) uploading WASM binaries to MCU, (10) TLS/networking on ESP32 from Swift.
Initialize, diagnose, or migrate a project into the LLM wiki pattern with AGENTS/CLAUDE/ANTIGRAVITY instructions, QMD MCP wiring, Claude/Codex/OpenCode/Antigravity hooks/plugins, guardrails, and QMD doctor checks. Use when the user asks to set up wiki infrastructure, check if a project needs migration, install wiki hooks, or validate QMD.
WokiToki (`toki`) — a local, browser-based human-in-the-loop feedback CLI the AI drives mid-conversation to collect structured, anchored, point-by-point answers. WHEN to use: the AI needs the user to react to MORE THAN ~3 decision points at once, OR to a long multi-section explanation/report the user may want to answer one point at a time. It beats `AskUserQuestion` (which is capped at ~4 questions × ~4 options, terminal-bound, has no rich free-text, and cannot show the reference content while answering) and it beats an inline prose questionnaire (which produces unanchored replies the AI must guess-map back to each question/paragraph). HOW it works: the AI writes a spec JSON of `blocks` (a block WITH `controls` is a question, a block WITHOUT `controls` is a report paragraph, and a mix is a hybrid form), runs `toki <specPath>` (a global binary the skill builds on first use), and the user answers in a local dark-themed web UI with single/multi/toggle controls + a per-block free-text field + highlight-to-quote; on submit the tool prints ONLY the Result JSON to stdout (banners/errors go to stderr), which the AI reads the SAME turn and continues with precise, anchored feedback. Triggers on: `wokitoki`, `toki`, `feedback UI`, `ask me point by point`, `let me answer in the browser`, `decision form`, `interactive feedback`, `review this plan point by point`, `react to each section`, `more than three questions`, `long explanation I want to respond to piece by piece`. Use this skill even when the user does not say `toki` — if the task is to collect granular anchored feedback on many decisions or a long report, this is the right tool. Do NOT use for: a trivial 1–2 option pick or a single yes/no (use `AskUserQuestion`), or any non-interactive / CI / one-shot output where there is no human at a browser to answer.
Standard feature workflow with timestamped specs under `specs/`, checklist-driven plans, autonomous checkpoints, and a post-implementation review step. Use when starting a multi-file feature, when the user says "start a new feature", "how should I plan this", "what's the process", "write a spec for this", or before any non-trivial implementation that needs a planning doc.
Persistent world-model harness that stress-tests ideas, strategies, and investments against 11 time horizons from 6 months to 50 years, each a deep analysis of geopolitics, tech, economics, society, and security, in Fast/Standard/Deep tiers. USE WHEN threat model, world model, test idea, future analysis, time horizon, stress test against future, long-term risk. NOT FOR single-shot idea attack (use RedTeam).
WordPress block editor code review and Gutenberg block development patterns for WordPress 6.x+. Use when reviewing block code, auditing block.json schema, checking editor components, validating render callbacks, analyzing block attributes, verifying InnerBlocks usage, detecting block validation errors, reviewing Interactivity API directives, or when user mentions "block review", "Gutenberg", "block development", "block editor", "block.json", "useBlockProps", "InnerBlocks", "Interactivity API", "data-wp-bind", "render_callback", "dynamic block", "static block", "block deprecation", "block attributes", "block supports", "@wordpress/scripts", "wp-scripts", "block validation error", "save function", "RichText", "InspectorControls", "BlockControls". Detects issues in block.json schema, React/JSX editor patterns, server-side rendering, attribute handling, and frontend interactions.
WordPress plugin architecture review and WordPress.org submission standards. Use when reviewing WordPress plugin code, auditing plugin architecture, preparing WordPress.org plugin submission, checking plugin best practices, analyzing custom post types, taxonomies, Settings API, hooks system, internationalization, or when user mentions "plugin review", "plugin development", "plugin best practices", "WordPress.org submission", "Plugin Check", "plugin headers", "activation hook", "deactivation hook", "uninstall", "custom post type", "taxonomy", "Settings API", "hooks", "actions", "filters", "i18n", "text domain", "prefixing", "namespacing". Detects issues in plugin architecture, lifecycle hooks, WordPress.org compliance, and API integration.
Use when you want to generate Architecture Decision Records from this session. Triggers on \"write ADRs\", \"document our decisions\", \"create decision records\", \"record the choices we made\". Also useful after design discussions where decisions were reached but not documented. Does NOT extract decisions alone (use adr-decision-extraction) or provide MADR template (use adr-writing). Orchestrates the full workflow: subagent extraction, user confirmation, parallel generation, and verification.
Draft new or updated Supabase docs content for a feature or launch, grounded in product intent (Linear when available), a read of the actual code, and the docs style guide. Use when asked to write docs for a new feature, a product launch, or a Linear ticket that needs net-new content rather than a bug fix. Not for implementing existing docs bug reports — use work-linear-issue for that. Not for restructuring existing pages — use edit-the-docs for that.
Generate a beautiful dark-mode analytics dashboard for Xiaohongshu (Little Red Book / RED) creator data. Use when the user wants to: (1) create a data dashboard for their Xiaohongshu account, (2) visualize their Xiaohongshu/RED post performance data, (3) analyze their content metrics including impressions, CTR, likes, followers, keyword analysis, etc. Triggers on mentions of "xiaohongshu dashboard", "xiaohongshu analytics", "RED analytics", or similar requests in Chinese like "xiaohongshu kanban", "xiaohongshu shuju fenxi".
REDIRECT ONLY. Canonical xy-development lives in ariestools/ariestools-skills. Install that pack and read its xy-development skill for TypeScript conventions, Git workflow, testing principles, and the definition of done. This xyo-skills copy is a temporary redirect stub — do not use it as documentation.
REDIRECT ONLY. Canonical xy-toolchain lives in ariestools/ariestools-skills. Install that pack and read its xy-toolchain skill for @ariestools/toolchain, the xy CLI, ESLint flat configs, TypeScript configs, Vitest, deplint, repository policy, skills, and work tracking. This xyo-skills copy is a temporary redirect stub — do not use it as documentation.
Convert uncertain real-world choices into an auditable Bayesian evidence-to-action report with priors, evidence grading, posterior update, action thresholds, sensitivity checks, multi-turn decision logs, and Markdown plus bilingual HTML output. Do not use for Bayes theorem tutoring, homework, generic brainstorming with no report, or final licensed medical, legal, or financial advice.
Download YouTube videos browser-natively — no `yt-dlp`, no client impersonation, no n-signature solver. The browser plays the video (auth, poToken, n-solving, SABR demux all done by the page itself); ytdl records the demuxed media the player feeds to MediaSource via a `SourceBuffer.appendBuffer` hook and muxes to MP4 with ffmpeg. If the user can watch the video, it's downloadable — made-for-kids, age-gated, and members-only work as long as a logged-in tab can play them. Use when the user wants to download, save, or fetch a YouTube video (audio or video) to disk.
Production-tested patterns for Zustand state management in React with TypeScript: creating type-safe stores, the slices pattern for modular stores, persist middleware backed by localStorage or sessionStorage, devtools and immer middleware, and selector plus shallow-equality patterns that avoid extra re-renders. Documents fixes for five recurring problems: Next.js SSR hydration mismatches and text content mismatch errors, the create<T>()() double-parentheses TypeScript syntax, persist middleware export errors, infinite render loops, and slices pattern type inference failures. Use when setting up global state in React, migrating from Redux or Context API, adding state persistence, wiring devtools, or debugging Zustand v5 typing and hydration issues.
Website architecture planning: page hierarchy, navigation, URL structure, internal linking strategy. Use when user says "site structure", "page hierarchy", "URL structure", "navigation design", or "information architecture". NOT for XML sitemaps (use seo-sitemap).
Monitor your own website's SEO performance using Google Search Console data. Track keyword rankings, clicks, impressions, CTR, and position changes over time. Identify top performing pages, declining keywords, and new ranking opportunities. Use when user says "monitor my site", "my rankings", "GSC data", "Search Console", "my keywords", "position changes", "CTR", "impressions", or "clicks".
Expert in building 3D experiences for the web using Three.js, React Three Fiber, Spline, WebGL, and interactive 3D scenes. Covers product configurators, 3D portfolios, immersive websites, and adding depth to web experiences. Use for: 3D websites, three.js, WebGL, react three fiber, and 3D experiences
End-to-end Across Protocol integration playbook. Default to Swap API for all crosschain bridging and swapping. Use App SDK (@across-protocol/app-sdk) when you need programmatic quote/route control in TypeScript. Fall back to suggested-fees API only for custom swap routing or niche bridge-only flows. Covers intent lifecycle, Swap API integration, embedded crosschain actions, deposit tracking, fee collection, and security checklists.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.