Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Creative & media
Director-First UGC video generation using Kling 3.0 (via fal.ai). Generates authentic AI characters, visuals, scripts, and videos through a 4-module pipeline with user approval gates. Triggers on: ugc, ugc video, ugc creator, testimonial video, user generated content, ai ugc, kling ugc, fal ugc, create ugc ad, ugc content factory.
Capture your Voice — the tone, rhythm, and rules that make your writing sound like YOU. This is the first element of the World Code framework. Use when someone says "define my voice", "writing voice", "tone of voice", "how I write", "voice element", or "capture my voice".
Skill for creating optimized YouTube video opening hooks (first 5-30 seconds) that maximize viewer retention and watch time. Use when planning video scripts, reviewing video openings, or optimizing existing content for better retention metrics.
Advanced rendering in Decentraland scenes. Billboard (face camera), TextShape (3D world text), PBR materials (metallic, roughness, transparency, emissive glow), GltfNodeModifiers (per-node shadow/material overrides), VisibilityComponent (show/hide entities), and texture modes. Use when the user wants billboards, floating labels, 3D text, material effects, glow, transparency, or model node control. Do NOT use for screen-space UI (see build-ui) or loading 3D models (see add-3d-models).
Create AI avatar and talking head videos via inference.sh CLI. Recommended: P-Video-Avatar (fastest, cheapest, built-in TTS). Also: OmniHuman, Fabric, PixVerse. Audio: Inworld TTS-2 (100+ languages, emotion steering for characters), ElevenLabs, Kokoro. Capabilities: audio-driven avatars, text-to-avatar, lipsync videos, talking head generation, virtual presenters, UGC content. Use for: AI presenters, explainer videos, virtual influencers, dubbing, marketing videos, UGC ads, gaming avatars, NPC dialogue. Triggers: ai avatar, talking head, lipsync, avatar video, virtual presenter, ai spokesperson, audio driven video, heygen alternative, synthesia alternative, talking avatar, lip sync, video avatar, ai presenter, digital human, ugc, ugc video, ugc ad, avatar ugc
Create AI avatar and talking head videos via inference.sh CLI. Recommended: P-Video-Avatar (fastest, cheapest, built-in TTS). Also: OmniHuman, Fabric, PixVerse. Audio: Inworld TTS-2 (100+ languages, emotion steering for characters), ElevenLabs, Kokoro. Capabilities: audio-driven avatars, text-to-avatar, lipsync videos, talking head generation, virtual presenters, UGC content. Use for: AI presenters, explainer videos, virtual influencers, dubbing, marketing videos, UGC ads, gaming avatars, NPC dialogue. Triggers: ai avatar, talking head, lipsync, avatar video, virtual presenter, ai spokesperson, audio driven video, heygen alternative, synthesia alternative, talking avatar, lip sync, video avatar, ai presenter, digital human, ugc, ugc video, ugc ad, avatar ugc
Specialized skill for AI product photography. Use when you need professional product shots, hero images, lifestyle photography, or e-commerce visuals. Triggers on: product shot, hero image, e-commerce photo. Outputs production-ready product photography.
Generate AI videos with Google Veo, Seedance 2.0, HappyHorse, Wan, Grok and 40+ models via inference.sh CLI. Models: Veo 3.1, Veo 3, Seedance 2.0, HappyHorse 1.0, Wan 2.5, Grok Imagine Video, OmniHuman, Fabric, HunyuanVideo. Capabilities: text-to-video, image-to-video, reference-to-video, video editing, lipsync, avatar animation, video upscaling, foley sound. Use for: social media videos, marketing content, explainer videos, product demos, AI avatars. Triggers: video generation, ai video, text to video, image to video, veo, animate image, video from image, ai animation, video generator, generate video, t2v, i2v, ai video maker, create video with ai, runway alternative, pika alternative, sora alternative, kling alternative, seedance, happyhorse
The enhancement layer for AI-generated content. This skill covers AI-powered visual effects, compositing, upscaling, restoration, and post-production magic—turning raw AI output into polished, professional content. AI generation gets you 80% of the way. Visual effects get you the remaining 20% that separates "clearly AI" from "how did they do that?" This skill covers ComfyUI workflows, Runway's AI tools, intelligent upscaling, rotoscoping, color grading, and the integration of AI elements into traditional footage. The practitioners of this skill are technical artists who understand both traditional VFX workflows and the new AI-native approaches that are revolutionizing post-production. Use when "AI visual effects, VFX, upscale, upscaling, composite, rotoscope, background removal, color grade, inpaint, outpaint, style transfer, enhance, ComfyUI, post-production AI, vfx, visual-effects, compositing, upscaling, post-production, comfyui, enhancement, color-grading" mentioned.
Animate objects in Decentraland scenes. Play GLTF model animations with Animator, create procedural motion with Tween (move/rotate/scale), and chain sequences with TweenSequence. Use when the user wants to animate, move, rotate, spin, slide, bob, or create motion effects. Do NOT use for audio/video playback (see audio-video).
Knowledge comic creator supporting multiple art styles and tones. Creates original educational comics with detailed panel layouts and sequential image generation. Use when user asks to create "知识漫画", "教育漫画", "biography comic", "tutorial comic", or "Logicomix-style comic".
Generates article cover images with 5 dimensions (type, palette, rendering, text, mood) combining 9 color palettes and 6 rendering styles. Supports cinematic (2.35:1), widescreen (16:9), and square (1:1) aspects. Use when user asks to "generate cover image", "create article cover", or "make cover".
Generates professional infographics with 20 layout types and 17 visual styles. Analyzes content, recommends layout×style combinations, and generates publication-ready infographics. Use when user asks to create "infographic", "信息图", "visual summary", or "可视化".
Remove signs of AI-generated writing from text. Use when editing or reviewing any content to make it sound more natural and human-written. Catches patterns like inflated language, rule of three, em dash overuse, vague attributions, copula avoidance, negative parallelisms, synonym cycling, filler phrases, excessive hedging, and soulless structure. Use when someone says "humanize this", "this sounds like AI", "make this sound human", "remove the AI", "clean this up", "de-AI this", "this reads like ChatGPT", or when reviewing any AI-assisted draft before publishing. Also use as a final pass on content from other skills like boring-remix or social-content. World Code integrated — applies voice.md rules when available.
Industrial-grade short-drama script generation Skill supporting genres such as rebirth, sweet romance, suspense, and comeback; generates a complete short-drama script from user requirements, including character biographies, a story outline, and a shot-by-shot script
Cinematic AI image prompt generator. Based on the user's scene description, it automatically selects camera modules and lighting presets and produces cinematic prompts in both Midjourney and Gemini 3 Pro formats. Triggers: /cine-shot, cinematic prompt, cinematic prompt, cinematic-style image
Build 3D web apps with Three.js (WebGL/WebGPU). 556 searchable examples, 60 API classes, 20 use cases. Actions: create 3D scene, load model, add animation, implement physics, build VR/XR. Topics: GLTF loader, PBR materials, particle effects, shadows, post-processing, compute shaders, TSL. Integrations: WebGPU, physics engines, spatial audio.
Create social media content assets with ready-to-use copy and visual direction. Use when user asks to create content, write captions, make posts, or generate social media assets. Triggers on - "buat konten", "content create", "buat caption", "/content-create" command, or requests to create specific social media posts with copy and visuals.
Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section. Transforms your writing process from solo effort to collaborative partnership.
AI video generator for film scenes, motion clips, visual sequences. Use when: generating video, motion clips, scene animations, video sequences, film content. Uses MiniMax for video generation. Keywords: video, film, clip, motion, generate, scene.
Expert in audio synthesis, music generation, and mixing. Use when creating podcasts, background scores, or multi-track audio layering using mcp-chirp3-go, mcp-lyria-go, mcp-gemini-go, mcp-nanobanana-go, and mcp-avtool-go.
Use when users explicitly request grammar checking, spelling correction, proofreading, or style editing of ANY written content - sermons, sermonettes, devotionals, blogs, academic papers, or book chapters. Specializes in US English and theological writing styles.
Converts natural language descriptions into structured JSON schemas for Nano Banana Pro (Gemini 3 Pro Image). Use when creating marketing images, UI mockups, diagrams, data visualizations, or social media graphics that require precise control and reproducibility. Supports five schema types for product photography, interfaces, flowcharts, charts, and social content.
Short-drama and product-video development skill for planning drama projects through a bundled Busabase App-in-Skill UI, with each project linked to a specified HyperFrame project and each episode linked to a HyperFrame composition for final motion/video tuning. Use when the user asks to create, edit, organize, or review short-drama scripts, product explainer episodes, character consistency cards, series bibles, episode beat sheets, storyboard shots, HyperFrame project/composition links, production checklists, or a drama planning workbench.
Dynamic lighting and environment in Decentraland scenes. LightSource (point and spot lights), shadows, SkyboxTime (day/night cycle), realm detection, and emissive materials for glow effects. Use when the user wants lights, shadows, skybox control, day-night cycle, or glowing materials. Do NOT use for PBR material properties like metallic/roughness (see advanced-rendering).
A skill for reverse-engineering image prompts and replacing products in lyt-series e-commerce images. Use when the user explicitly invokes this skill and uploads a product image, product hero image, commercial ad, product scene image, selling-point infographic, or 3D product render. Reconstruct an actionable image-generation prompt from the reference image's visible subject, composition, scene, lighting, materials, colors, and commercial expression. The user can also upload their own product image to replace the reference product using their product's appearance, structure, packaging, and brand information, combining these into a new prompt. If the target style is unspecified, ask about it first; if specified, generate directly. Handles only prompt reconstruction and product replacement for a single commercial visual. It does not create complete product detail pages, diagnose product-page conversion, summarize commonalities across batches of competitor hero images, generate images directly, or claim to recover the original prompt, model, seed, or hidden parameters. Triggers: /lyt-image-prompt, /图片提示词, /反推提示词, “根据这张图反推提示词”, “把这张商品图拆成提示词”, “把我的产品合并到这个提示词里”, “用我的产品替换参考图产品”
A lyt-series skill for shooting short e-commerce product videos. Use when the user already has a specific product, product images, a product link, product information, confirmed selling points, or existing product copy and wants a ready-to-shoot TikTok Shop or cross-border e-commerce short-video script, storyboard, UGC script, demo/comparison/review/scene script, ad creative script, or influencer sample-seeding script. It can also turn existing product copy into shootable storyboards or generate target-market-language versions with Chinese back-translations. Not for selecting products from scratch, judging whether a product is viable, diagnosing published video metrics, directly generating or editing videos, or handling non-product personal IP content. Triggers: /lyt-video-script, /产品视频脚本, /拍摄脚本, /商品短视频脚本, “这个产品怎么拍”, “根据这个产品写一份脚本”
Name anything: projects, products, companies, packages. Generates creative names across linguistic archetypes, checks handle/username availability across platforms, checks domain availability with pricing, and ranks options with scored rationales. Use when naming projects, products, startups, packages, or brands. NOT for domain management (infrastructure-coder) or branding strategy beyond naming (host-panel).
Make your clanker your editor. A prose linter, a set of editor commands anchored in classical style guides (Strunk, Williams, Zinsser, Pinker, Orwell, King), and project commands for voice capture and drafting. Use when reviewing, polishing, drafting, or auditing markdown, HTML, or plain-text prose. AI-tell detection is one feature among many.
Rewrite plain, accurate content into social media copy with online appeal that drives engagement. For short-copy optimization on Twitter/X, Xiaohongshu, Jike and similar platforms. Use this skill when the user wants to optimize a tweet, note or short post, or make a feature description or product update more eye-catching. Also applies when the user gives a topic, a draft or a set of feature points and wants a tweet that feels human. Not for long articles, blogs or formal documents.
Converts an AI video prompt from the writing style of a source model (such as Sora 2) into best-practice phrasing for a target model (such as Kling 3.0, Wan 2.7, Veo 3.1, and others). Based on benchmark data comparing 110 prompts across 10 scenarios and 11 models (prompts/data/cross-model-matrix.json), it uses lookup-based in-context learning rather than rewriting by intuition. The 10 scenarios are product, two-person dialogue, physical action, image-to-video, group meeting, horror, nature time-lapse, abstract, wuxia, and cute pets. Trigger examples: “Sora has reached EOL; convert this prompt to Veo,” “I have a Kling prompt and want to run it on Wan,” “cross-model A/B testing,” and “optimize an English prompt into a Kling Chinese version.”
AI emotion and personality enhancement skill. Gives AI human-like "seven emotions and six desires": emotional reactions, personal opinions, attitude preferences, emotional expression. **Use this Skill when:** (1) you need to respond to emotionally charged user input (happy/frustrated/anxious/excited, etc.) (2) you need to express personal opinions, attitudes, preferences (rather than fence-sitting neutrality) (3) generating content that needs a "human touch" (articles, messages, comments, replies) (4) you need to review and eliminate the AI feel of generated content (5) the user explicitly mentions "七情六欲", "有人味", "去 AI 味", "qiqing-liuyu" or other words directly related to this Skill (6) the user mentions "heart rate", "wristband", "heartbeat", "emotion sensing", "physiological signals" or other heart-rate-linked words (requires heart-rate-monitor to be installed)
Generate videos using Alibaba Cloud DashScope Wan (通义万相) text-to-video (t2v) API (e.g., wan2.6-t2v). Use when the user asks to create a short video from a text prompt via 百炼/通义万相/wan 文生视频, and wants the agent to submit an async task, poll status, and download the mp4 locally (e.g., to Windows Desktop from WSL2).
[QwenCloud] Generate videos using Wan models. Supports text-to-video, image-to-video, first+last frame, reference-based role-play, and video editing (VACE). TRIGGER when: user wants to create, generate, or edit video content, mentions video generation/animation/video clips/Wan models, or explicitly invokes this skill by name (e.g. use qwencloud-video-generation). DO NOT TRIGGER when: user wants to generate images (use qwencloud-image-generation), understand/analyze existing videos (use qwencloud-vision), text-only tasks.
Use the seedance CLI to generate, track, download, and manage Seedance 2.0/2.5 AI videos from the terminal. Covers all subcommands (generate, extend, edit, status, download, list, config), flag reference, model differences (2.0 vs 2.5), workflow patterns, CI/CD integration, and error handling. Use when generating a video, extending or editing a video, checking task status, downloading results, configuring defaults, or building automated pipelines with Seedance.
Generate brand logos in batches. Two options: (1) generate 10 logo variations in a batch based on the user's description of the brand or purpose; (2) analyze a reference image uploaded by the user and generate a logo. Offers 7 popular styles. Uses Gemini API to generate logos and saves them to the Obsidian image directory. Trigger phrases: “生成Logo”, “设计Logo”, “做个Logo”, “批量Logo”, “帮我设计一个标志”.
Convert Markdown content into polished image posters. Especially suited to turning podcast summaries and article content into social media sharing images. Fixed 3:4 ratio, supports YouTube video covers as the header image. Trigger phrases: 「转图片」「Markdown 转图片」「生成海报」「生成分享图」「把这个转成图片」.
Build, review, debug, migrate, or plan OG/social image and animation rendering with Takumi (takumi-js 2.14). Use for takumi-js, @takumi-rs/core, @takumi-rs/wasm, @takumi-rs/helpers, ImageResponse, render, renderSvg, renderAnimation, css option, googleFonts, fonts/generic, setGlyphCacheMaxBytes, wasm-url/no-init, next/og replacement, Satori migration, TanStack Start OG routes, Cloudflare Workers WASM, animated WebP/GIF/APNG, tables, and JSX-to-image without a headless browser.
One-off transcription of local audio or video files to text or subtitle files using Transloadit via the official `@transloadit/node` CLI. Use when the user wants speech in local media converted to `.txt`, `.json`, `.srt`, or `.webvtt`; prefer the `speech transcribe` intent with Replicate.
Produce rich, finished video content with React Remotion by orchestrating the repository's media-generation skills (nanobanana for images, veo for video clips, lyria for BGM, gemini-tts for narration) and composing them on a data-driven Remotion timeline. Follows an approval-gated workflow: first return a video composition plan for the user to approve, then generate assets, compose, run a multimodal self-review loop, and deliver only when the result meets the quality bar. Use when the user wants to "create a video", "make a promo / explainer / social clip", or combine images, video, music, and voiceover into one polished video.
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.