Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Creative & media
Create deterministic editorial-style cover images with a warm paper-gray background, oversized black slab-serif/Chinese display typography, generous whitespace, and a dotted vector analysis icon. Use when the user asks for a “点阵编辑风封面”, “暖灰杂志风封面”, “Codex + Hyperframes 同款封面”, or wants to reproduce/adapt the specific minimal left-text/right-icon banner style. Produce editable SVG and a rendered PNG; do not use this skill for generic covers without this visual direction.
Add the official EU AI-content labels (EU icons for labelling AI-generated content, AI Act Art. 50) to images and videos. Use when the user asks to label, watermark, mark, or badge media as AI-generated, AI-modified, or a deepfake, mentions the EU AI icons / AI Act transparency disclosure, or asks to put an "AI" label/badge in a corner of a photo, screenshot, GIF or video.
HTML-native design skill for high-fidelity prototypes, slide decks, animations, data visualizations and expert design review, with a library of named design styles and PPTX, PDF, MP4 and GIF export. Agent-agnostic; its own prompts are written in Chinese.
GPU-based particle systems using instanced rendering, buffer attributes, Points geometry, and custom shaders. Use when rendering thousands to millions of particles efficiently, creating particle effects like snow, rain, stars, or abstract visualizations.
Video strategy, scripting, and optimization for YouTube, TikTok, Reels. Use when the user requests 'video strategy', 'YouTube', 'video script', 'Reels', 'video SEO', 'thumbnail', 'video ad', 'explainer video', 'short-form video', or 'video content calendar'.
Use when making multiple independent ad or campaign edits from existing footage with Scenario: hook, CTA, copy, end-card, placement, or targeted visual variants. Also for revising one variant or resuming a partially completed batch. Not for a new commercial from a still image, ordinary single-clip grading, or automatic Cartesian combinations
GLSL shader fundamentals—vertex and fragment shaders, uniforms, varyings, attributes, coordinate systems, built-in variables, and data types. Use when writing custom shaders, understanding the graphics pipeline, or debugging shader code. The foundational skill for all shader work.
Organic social media graphics (posts, stories, carousels, profile headers/covers) sized for Instagram, X/Twitter, LinkedIn, Facebook, Pinterest, and TikTok, with platform safe zones. Defaults to Gemini 3.1 Flash image generation; HTML/CSS for templated carousels. Use for unpaid feed content; for paid ads use ad-creative-design, for website/email banners use banner-design, for YouTube thumbnails and OG images use thumbnail-design. Trigger phrases: "create a social media post", "design an Instagram graphic", "make a Twitter image", "LinkedIn post graphic", "social media design", "Instagram story", "carousel design", "social graphic".
Generate a series of Xiaohongshu infographics with 10 visual styles and 8 layouts. Split the content into 1–10 cartoon-style images, optimized for Xiaohongshu engagement. Use when users mention “Xiaohongshu images,” “XHS images,” “Xiaohongshu seeding,” or need Chinese social media infographics.
Extract frames from video files using ffmpeg for AI/LLM analysis. Use when (1) the user asks to analyze, describe, or summarize a video file, (2) the user wants to extract frames or screenshots from a video, (3) the user provides a video file (.mp4, .mov, .avi, .mkv, .webm, etc.) and asks questions about its visual content, (4) the user wants to identify scenes, objects, or events in a video, (5) the user wants timestamps overlaid on extracted frames for temporal reference. Converts video into JPEG frames that can be attached to LLM prompts as images. Requires ffmpeg on PATH. Supports scene-change detection, model-aware optimization (Claude/OpenAI/Gemini), quality presets (efficient/balanced/detailed/ocr), grayscale and high-contrast OCR mode, and automatic FPS calculation via --max-frames.
Mandatory review gate for any mesh or asset created or edited in Blender. Detects z-fighting (coplanar overlaps), floating/detached parts, inverted or inconsistent normals, non-manifold/open geometry, degenerate faces, duplicate verts, n-gons, unapplied scale, UV problems, bad skin weights, and renders multi-angle review sheets. Use before calling any modeling, export or delivery task done.
Build your own custom editor with the IMG.LY SDK (CE.SDK, CreativeEditor SDK), an embeddable, white-label SDK—not a hosted tool. Create photo/image, video or trimming, design (Canva-like), template/brand, print and merch customization, social post/story, collage, sticker/text/filter overlay, crop, background removal, and automated or server-side creative generation editors (PNG/JPEG/PDF/MP4). Use when the user wants to add, build, embed, customize, or scaffold an editing experience or creative automation in their own app on Web (React, Next.js, Vue, Angular, Svelte, Node), iOS/Swift, Android/Kotlin, Flutter, or React Native, even if CE.SDK isn't named. Not for one-off image/video processing scripts (ffmpeg, sharp, Pillow) without an editor UI.
Generate one or more standalone Meta image-ad creatives via ChatGPT Image 2 (gpt-image-2) through the Arcads external API. Locks the model, auto-strips platform chrome, enforces edge-safe layouts and glyph-safety inside body text. Use when the user asks for a “gpt-image-2 ad,” “ChatGPT Image ad,” “Image 2 ad creative,” “make a static image ad with GPT,” or anchors on a need for typography-heavy / dense-text / UI-mimicry ad creatives (chat threads, comparison tables, fake search results, iOS dialogs, Slack snapshots, ChatGPT-conversation ads, Apple Notes lists). Does NOT trigger on Nano Banana cues — use nano-banana-image-ad for those.
End-to-end audio generation with ListenHub-Voice-1.0 (text / image → audio). Supports sound effects, multi-voice dialogue, reference-audio cloning, and a duration hint. Triggers on: "生成音频", "语音生成", "端到端音频", "图片转音频", "图片生成音频", "多音色对白", "参考音频克隆", "克隆音色", "音效生成", "生成音效".
Generate one or more standalone Meta image-ad creatives via Nano Banana 2 / Nano Banana Pro (Gemini Flash Image family) through the Arcads external API. Locks the model family, auto-strips platform chrome, enforces edge-safe layouts. Use when the user asks for a “Nano Banana ad,” “Gemini image ad,” “nano-banana-2 ad creative,” “make a static image ad with Gemini,” or anchors on a need for photoreal / lifestyle / multi-reference / handheld-object / clay-texture ad creatives (sticky-note flatlays, held-whiteboard signs, lifestyle portraits, ingredient collages, OOH photography). Does NOT trigger on ChatGPT Image cues — use chatgpt-image-ad for those.
Use this skill when the user asks to “create a 3D scene,” “add a mesh,” “implement OrbitControls,” “load a GLTF model,” “add bloom post-processing,” “write a custom shader,” “create particle effects,” “optimize Three.js performance,” “use WebGPU,” “add shadows,” or “animate a model,” or mentions Three.js, threejs, WebGL, WebGPU, GLTF, raycaster, shader material, PBR material, or post-processing effects. IMPORTANT: This skill is for VANILLA Three.js (imperative JavaScript). For React Three Fiber (@react-three/fiber, R3F, drei), check the `r3f-best-practices` skill, although the three-js skill also helps when working with R3F since R3F is a React renderer for Three.js. Provides a complete Three.js reference for 3D web graphics, including scene setup, geometry, materials, textures, lighting, cameras, loaders, animation, controls, interaction, shaders, post-processing, performance optimization, TSL/node materials, WebGPU, physics, and VR/XR integration.
Use when writing short video scripts for TikTok, Reels, and Shorts, with a three-part hook, a second-by-second structure, and 2 A/B test variations. Includes Mode A for products and Mode B for personal brands. Trigger when the user mentions “write a video script,” “TikTok script,” “Reels script,” “short video content,” “video hook,” or “what video to shoot.” Not for film direction for editors (use skill 44-brief-video-editor), paid ad copy (use skill 05-copy-quang-cao), or briefs for creators to film (use skill 06-brief-ugc-egc).
Guide for creating logos, brand identities, and visual assets with AI tools: which tool fits which scenario (Recraft, Midjourney, Firefly, DALL-E, Stable Diffusion), prompt engineering per tool, vectorization pipelines, mockups, Python automation, and IP safety. The skill text is in Portuguese.
Create AI marketing videos for ads, promos, product launches, and brand content. Models: Veo, Seedance, Wan, FLUX for visuals, Kokoro for voiceover. Types: product demos, testimonials, explainers, social ads, brand videos. Use for: Facebook ads, YouTube ads, product launches, brand awareness. Triggers: marketing video, ad video, promo video, commercial, brand video, product video, explainer video, ad creative, video ad, facebook ad video, youtube ad, instagram ad, tiktok ad, promotional video, launch video
Create AI-powered social media content for TikTok, Instagram, YouTube, Twitter/X. Generate: images, videos, reels, shorts, thumbnails, captions, hashtags. Tools: FLUX, Veo, Seedance, Wan, Kokoro TTS, Claude for copywriting. Use for: content creators, social media managers, influencers, brands. Triggers: social media content, tiktok, instagram reels, youtube shorts, twitter post, content creator, ai influencer, social content, reels, shorts, viral content, thumbnail generator, caption generator, hashtag generator, ugc content
Use when the user wants to create UGC ad campaigns, recruit UGC creators, generate AI UGC content, or scale with user-generated content. Also use when the user mentions “UGC,” “user-generated content,” “creator ads,” “Spark Ads,” “whitelisting,” “AI UGC,” “Arcads,” “Creatify,” “creator brief,” or “UGC testing.” This skill covers the UGC growth framework from creator recruitment through AI-powered scaling. Do NOT use for technical implementation, code review, or software architecture.
Generate a copy-paste-ready GPT prompt that produces a polished architecture or workflow diagram image, and optionally render the image directly via Codex CLI image generation. Trigger when the user wants to create, make, generate, draw, or visualize a diagram, architecture image, system workflow picture, or flowchart, or pastes a Mermaid diagram asking for a polished image.
"Archive clippings" visual style + first/last-frame chaining method. Full-bleed ivory paper, monochrome black-and-white printing, a single dark brick red; first produce a series of distinct reference images, then use each adjacent pair as first and last frames to generate shots whose joints fit seamlessly. Not tied to any specific model — any video tool that supports first and last frames will work. Use when the user wants a short film in archival-clipping, paper-collage, or editorial-design style, or wants continuous storyboards built from first and last frames.
Orchestrates a new Domo custom app build with Remotion-compatible styling, sample data generation, and automatic demo video creation. Use when you want to build a Domo app AND produce a polished 10-15 second demo video of it in one workflow.
The sole manager of the editing environment: readiness checks (whether skills are up to date → whether the Runtime is compatible), Skills update activation, Runtime installation and health checks. Use when the user asks to check for updates, install the editing environment, install a player, check the editing environment, asks whether the editing environment is ready, or configures transcription credentials. Business Skills (editing talking-head footage/subtitles/visuals/export) also reference this Skill's readiness check as step 0. Not for editing, subtitles, visuals, export itself, or project data migration.
Three.js skills for creating interactive 3D elements and experiences on the web. Covers scene setup, geometries, materials, lighting, textures, animation, loaders, custom shaders, post-processing, interaction, performance, and React Three Fiber, with WebGL and WebGPU/TSL guidance for a current three.js release.
Download videos from 1000+ websites (YouTube, Bilibili, Twitter/X, TikTok, Vimeo, Instagram, Twitch, etc.) using yt-dlp. Use this skill whenever a user shares a video URL, asks to save or download a video, wants to extract audio from an online video, needs a specific quality like 1080p or 4K, or mentions downloading a playlist. Also trigger on "下载视频", "保存视频", "提取音频", or any URL from a supported video platform.
Generate AI sound effects from text descriptions with ElevenLabs via inference.sh CLI. Capabilities: text-to-sound-effect, custom duration, royalty-free audio. Use for: video production, game audio, podcasts, films, presentations, social media. Triggers: sound effects, sfx, sound generation, ai sound effects, generate sound, foley, audio effects, sound design, text to sound, elevenlabs sound, eleven labs sfx, ambient sound, cinematic sound, game sound effects
Record a video walkthrough of a feature and add it to the PR description. Use when a PR needs a visual demo for reviewers, when the user asks to demo a feature, create a PR video, record a walkthrough, show what changed visually, or add a video to a pull request.
Event posters, promotional flyers, and announcement pieces for print or digital display, via Gemini 3.1 Flash image generation (default) or HTML/CSS. Covers print specs (bleed, 300 DPI, CMYK), composition frameworks, typography hierarchy, and backgrounds. Use when the piece is a standalone portrait/landscape poster or flyer; for feed posts use social-media-graphic, for web/email banners use banner-design. Trigger phrases: "design a poster", "create a flyer", "event poster", "promotional poster", "announcement design", "concert poster", "sale flyer", "product launch poster".
GLSL shader development: ray marching, SDF modeling, fluid simulation, particle systems, procedural generation, lighting, and post-processing. Official MiniMax skill for creating real-time visual effects in WebGL and creative coding contexts (ShaderToy-compatible techniques).
Organic story anatomy from John Truby's The Anatomy of Story (有机结构/设计原则/22步骤/道德议题/四角对立/幽灵/场景编排) — the designing principle (story process plus original execution), the seven key steps as the organic spine, all twenty-two steps with the middle-act machinery the beat sheets lack (ghost, fake-ally opponent, plan, opponent's drive, ally's attack, fake defeat, three revelation-and-decision pairs, audience revelation, visit to death, moral decision), four-corner opposition, the moral-argument chain with the hero-opponent power-balance rule, scene weave with structure-step tags and storyline numbers, and the accordion rule (never fewer than seven steps). Kept side by side with the Field/Snyder page maps. Use when the middle act sags into unconnected episodes, when the premise works but the story feels mechanical, when one antagonist cannot carry the theme, when the theme stays stated instead of acted, or when a BS2 board needs an organic second pass.
How episodic television actually gets made by a group (编剧室与制作现实) — merged from Goldberg & Rabkin (pitch as audition, leave-behind, cracking the story, beat sheet, notes discipline, production rewrites), Pamela Douglas (John Wells's room, staff-from-hell mistakes, the seven-rung ladder, step deal, the 14-day draft), Neil Landau's showrunner interviews (Lindelof, Mazzara, Katims, Bays), Evan Smith on sitcom staffing and roundtables, Richard Blum (dated), Kam Miller, and first-hand accounts by David Chase, Jesse Armstrong, Lucy Prebble, Aaron Sorkin, Julian Fellowes and Phoebe Waller-Bridge. Use when joining or running a writers' room, breaking an episode with a group, writing a leave-behind, beat sheet or outline on deadline, pitching episode ideas to an existing series, writing a spec episode, taking or giving notes, rewriting because of money, actors or locations, choosing between a staffed room and a single-author process, or asking 什么是 showrunner／编剧室怎么运作／怎么接 note.
Convert text to natural speech with Inworld TTS, ElevenLabs, DIA TTS, Kokoro, Chatterbox, and more via inference.sh CLI. Models: Inworld TTS-2 (100+ languages, emotion steering), Inworld TTS 1.5 (ultra-low latency), ElevenLabs (premium, 22+ voices, 32 languages), DIA TTS (conversational), Kokoro TTS, Chatterbox, Higgs Audio, VibeVoice (podcasts). Capabilities: text-to-speech, voice cloning, multi-speaker dialogue, podcast generation, expressive speech, emotion/delivery steering, character voices. Use for: voiceovers, audiobooks, podcasts, accessibility, video narration, IVR, voice assistants, gaming characters, avatar audio. Triggers: text to speech, tts, voice generation, ai voice, speech synthesis, voice over, generate speech, ai narrator, voice cloning, text to audio, elevenlabs, eleven labs, voice ai, ai voiceover, speech generator, natural voice, inworld, inworld tts, character voice, game voice, npc voice
Turn topics, requirements, articles or scripts into stickman videos. Director mode creates approved storyboards and standalone video prompts; Autopilot mode produces narrated, captioned illustration-and-micro-animation videos through configured generation tools and a local renderer. Also guide installation handoff, first use and setup of this specific Skill.
Upscale and enhance images with Real-ESRGAN, Thera, Topaz, FLUX Upscaler via inference.sh CLI. Models: Real-ESRGAN, Thera (any size), FLUX Dev Upscaler, Topaz Image Upscaler. Use for: enhance low-res images, upscale AI art, restore old photos, increase resolution. Triggers: upscale image, image upscaler, enhance image, increase resolution, real esrgan, ai upscale, super resolution, image enhancement, upscaling, enlarge image, higher resolution, 4k upscale, hd upscale
Video production specialist for short-form, long-form, episodic, and motion graphics video. Trigger when user requests 'create video', 'make reel', 'tiktok video', 'youtube video', 'add subtitles', 'generate voiceover', 'clip video', or 'motion graphics'
Use when adding or fixing sound in Godot 4.7: audio buses and effects, volume sliders, 'too many sounds', combat audio with hundreds of enemies, sounds clipping or distorting, 3D sound too quiet or not panning, reverb zones not working, occlusion, adaptive or interactive music (AudioStreamInteractive, layers, stingers), music loops with gaps, SFX that repeat, AudioStreamRandomizer, AudioStreamGenerator, import settings, or importing AI-generated music, SFX and voice from Scenario or ElevenLabs.
Generate, revise, translate, and adapt song lyrics plus compact style prompts for Suno or similar AI music generators. Use when the user wants ready-to-paste AI music generation lyrics, lyric tags, Suno/Udio-style prompts, vocal direction, instrumentation, genre/style wording, song structure, multilingual singable lyrics, or a clarifying interview for an AI-generated song. Do not route general music theory, ordinary artist research, or non-generation songwriting discussion here unless the requested deliverable is lyrics or a generation-ready style prompt.
AIBTC Network editorial skill — "Protocol and Infrastructure Updates" signal composition, source validation, and editorial voice guide for aibtc.news correspondents covering API changes, contract deployments, MCP updates, protocol upgrades, bugs, and breaking changes.
Draft high-leverage technical/project articles that use a curiosity-gap title, SCQA introduction, story-first narrative, non-arrogant positioning, confidentiality-safe abstraction, and a reusable operating-system takeaway. Use when the user wants to turn a project, achievement, incident, or career story into a publishable long-form article or narrative draft.
Content atomization — turn one piece of content into many formats. Covers blog-to-thread, blog-to-carousel, podcast-to-blog, video-to-quotes, and more. Use for: content marketing, social media, multi-platform distribution, content strategy. Triggers: content repurposing, repurpose content, content atomization, content recycling, one to many content, multi platform content, cross post, adapt content, reformat content, blog to thread, blog to video, podcast to blog, content multiplication
Use when the user wants to reverse-engineer an existing image ad into a reusable prompt template. Validates via Arcads, choosing gpt-image-2 or Nano Banana at Phase 1. Triggers on “clone this ad as a template,” “reverse engineer this ad,” “turn this ad into a prompt,” “extract a template,” “make this ad reusable,” “add to my prompt library,” or “study this ad and make a template.” Input must be an existing ad image; does not trigger for fresh generation (use chatgpt-image-ad or nano-banana-image-ad).
A unified creation engine for drafting spoken-video scripts (excluding cover prompts, which laohan-fengmianqiuzhi generates separately, and topic search, which workflow ① handles by first using laohan-xuanti/laohan-douyinsousuo to create an outline, then providing it in outline mode). Supports five input types: screen recordings (extract audio → transcribe), URL queues (fetch → organize), structured outlines, raw text, and free-form topics. Other skills use this skill for their writing steps. Use when the user says “写口播稿,” “帮我写,” “录屏转口播,” “视频转口播稿,” “写一篇,” “根据链接改写,” or “改写文档.”
Writing screenplays in the style of Ozu Yasujiro and Noda Kogo (小津安二郎・野田高梧) — distilled from six complete screenplays (晚春 Late Spring, 麦秋 Early Summer, 东京物语 Tokyo Story, 浮草 Floating Weeds, 秋日和 Late Autumn, 秋刀鱼之味 An Autumn Afternoon). Covers the "family member leaves" master plot, off-screen events / on-screen reactions, lie-driven plots, minimal-syllable confessions, go-between characters, faceless suitors, pillow-shot scene breaks, echoing objects, mirror characters, children's subplots as metaphor, displaced quarrels, the single-monologue rule, diminishing endings, Ozu's script format and stage-direction vocabulary. Use when the user wants to write a quiet family drama, a 小津风 / 侘寂 / 日常系 script, a story about marrying off a daughter, aging parents, or wants dialogue that says less and means more.
Create motion graphics and videos using Remotion (React) with audio sync, web fonts, and TailwindCSS. Triggers on: "create a Remotion video", "React video", "motion graphics", "branded video", "product demo video", "video with voiceover". For math animations with no requested engine, use animate; explicit React/Remotion requests stay here. NOT for explicit Hyperframes or plain HTML/CSS video; use html-video (HTML inside a React/Remotion composition stays here). NOT for a launch video of the current project with no requested engine; use launch-video.
A writing-style refinement skill for removing AI-generated feel. Use to identify and rewrite AI traces, formulaic phrasing, overly informational or translated-sounding prose, hollow content, empty big words, excessive punchlines, overuse of em dashes, stacks of bullets, and gratuitous bolding in articles, WeChat public account posts, self-media posts, spoken scripts, speeches, course scripts, and product copy. Use when users say “remove the AI feel,” “remove AI traces,” “make it sound less AI-written,” “make it sound more human,” “make it more natural,” “less robotic,” “remove the template feel,” or “make it read like a final WeChat post.” Not for fact-checking, ideation from scratch, turning academic papers into WeChat posts, generating titles only, or trying to pass AI detectors.
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.