Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Creative & media
Author, diagnose, and refine Blender animation for articulated props, mechanical assemblies, material-transfer sequences, and game-ready actions. Use when motion timing, pivots, physical connections, critical poses, trajectories, visibility states, or exported GLB actions must be created or reviewed.
Generate images, videos, audio, and more using Civitai's orchestration API. Use when the user wants text-to-image, video generation (11+ engines), text-to-speech, music, transcription, bulk batches, experiment sweeps, or buzz cost estimation. Not for browsing or searching Civitai models (use the Civitai MCP server).
Creative writing skill for creating canonical reference documentation (wikis) for fictional worlds, characters, and story events. Use when creating or updating wiki pages, official documentation, character profiles, location documentation, or lore pages. Creates polished, sourced, encyclopedic reference material.
Use when a user has podcast, interview, or talking-head audio that needs cleanup—denoise, de-hum, level dialogue, and duck music under voice. Triggering symptoms include phrases like “podcast audio is noisy,” “background hum in interview,” “music too loud under voice,” “level out my voiceover,” “fix my podcast,” or any DaVinci Resolve Fairlight audio cleanup question.
Yamane Super Director Master — a directing and audiovisual skill designed by @山音, linked with "Yamane Super Screenwriter Master". Starting from the script, it completes director tone-setting, pacing planning, script fine-tuning, and storyboard breakdown, finally generating a standard nine-column storyboard table (xlsx). It analyzes the audiovisual theories of the world's top directors, includes a director-style template library for dozens of film genres, and supports cross-genre combinations. It covers storyboards in all formats, from concept super-short films to features. Be sure to use this skill when the user mentions storyboard, storyboard table, director, shot language, camera movement, composition, shot size, editing rhythm, audiovisual style, camera angle, director style, shooting plan, storyboard breakdown, storyboard, or any request involving turning a script into an executable shooting plan. Trigger it even if the user only says "help me break down the storyboard", "how should this scene be shot", or "give me a director's plan". Also trigger it when the user already has a script generated by the Screenwriter Master and wants to move into the directing stage.
Edit Vietnamese text that is mechanical, hollow, or monotonous so the wording is natural, clear, and true to context. Use when the user asks to make text less formulaic, adjust the voice, or preserve the author's voice; do not use it to guess whether an author is AI, evade detectors, fix pure grammar, or turn specialized text into speech.
Make a launch video for your startup or product with Pexo. Describe your product (or paste your landing-page URL or a screenshot) and Pexo writes the script, generates every shot, picks the models, and returns a finished, publish-ready launch video with music — built for Product Hunt, your landing page, or launch-day socials. Use for product and startup launches: "launch video", "product launch video", "make a launch video", "launch day video". NOT for ongoing ad campaigns (use the video-ad skill).
Generate videos from text prompts or animate static images using ModelsLab's v7 Video Fusion API. Supports text-to-video, image-to-video, video-to-video, lip-sync, and motion control with 40+ models including Seedance, Wan, Veo, Sora, Kling, and Hailuo.
Writing style distillation skill — analyze multiple articles by one author, deeply reconstruct their thinking patterns and writing style, and generate a dedicated writing-twin sub-skill and style prompt. Supports automatic material collection across platforms such as WeChat Official Accounts and Douyin, and also allows manually pasting articles or specifying file paths. Trigger words: distill writing style, writing twin, clone writing style, replicate and distill writing skill.
Full NotebookLM API via notebooklm-py CLI: create notebooks, add sources, generate podcasts, videos, infographics, slides, quizzes, flashcards, mind maps. Triggers on: "notebooklm", "create a podcast", "audio overview", "generate flashcards", "generate infographic", "/notebooklm".
Generate multiple app, favicon, or website icon candidates with either the local QM Icon Studio CLI or Codex built-in image generation with reference icons, then present a contact sheet so the user can choose. Use when building websites or apps and needing reusable icon options.
When the user wants to write a YouTube video script, structure content, improve pacing, or design retention beats. Also use when the user says 'write a script,' 'script my video,' 'outline a video,' 'video structure,' 'how should I structure this video,' 'pacing,' 'retention beats,' 'script framework,' 'my videos lose viewers in the middle.' For the opening hook specifically, see hook-writing. For editing-focused retention, see retention-editing.
Make a video for your startup with Pexo. Describe your company, product, or vision (or paste your site) and Pexo writes the script, generates the shots, picks the models, and returns a finished, publish-ready startup video with music — for your homepage, fundraising deck, or social channels. Use for startup brand and intro videos: "startup video", "video for my startup", "company intro video", "about us video". NOT for paid ad campaigns (use the video-ad skill).
Build coupled precipitation and affected surfaces in Three.js. Use for falling snow, snow accumulation, model snow caps, wet asphalt puddles, procedural ripple normals, splash flipbooks, rain streaks, shared weather envelopes, and surface wetness or coverage transitions.
Author procedural planetary bodies in Three.js. Use for spherical terrain, continents, ridges, craters, biome masks, coastlines, material variation, analytic normals, altitude LOD, and bodies that must hold up from orbit through close approach.
Build large procedural oceans and coast transitions in Three.js. Use for WebGPU/TSL FFT oceans, multi-cascade wavelength bands, coastal breakers, finite-volume shallow-water beach waves, signed-distance coastlines, shallow-water swash films, wet-sand transitions, rock-impact spray, stylized above/below surface optics, permanently submerged Snell-window views, total internal reflection, forward-refracted structures through an interface, pixel-footprint spectral LOD, aquatic perspective, caustic god rays, choppy displacement, spectral derivatives, Jacobian whitecaps, windrow and temporal foam, analytic sky reflection, underwater absorption, crest scatter, and GPU validation.
Unity 6 lighting and visual effects guide. Use when working with lights, baked/realtime/mixed lighting, light probes, reflection probes, Adaptive Probe Volumes (APV), global illumination, Particle System, VFX Graph, or post-processing effects. Based on Unity 6.3 LTS documentation.
Complete platform upload specifications for viral video creation across TikTok, YouTube Shorts, Instagram Reels, Facebook Reels, Snapchat Spotlight, and Twitter/X. PROACTIVELY activate for: (1) Platform-specific video encoding, (2) Upload requirements lookup, (3) Multi-platform export, (4) File size optimization, (5) Aspect ratio conversion, (6) Duration limits, (7) Audio requirements, (8) Caption/subtitle specs, (9) Thumbnail requirements, (10) Quality vs compatibility trade-offs. Provides: Comprehensive spec tables, FFmpeg presets per platform, optimal encoding settings, file size calculators, batch export workflows, and 2025-2026 platform-specific algorithm insights.
Generate AI images from text prompts — one API key for GPT Image, Gemini, Seedream, and 10+ models. No juggling subscriptions. Images saved to your YouMind knowledge board. Use when user wants to "generate image", "create image", "AI image", "text to image", "生成图片", "AI 生图", "画像生成", "GPT image", "Gemini image", "Seedream", "DALL-E", "Midjourney".
Cinema 4D MCP expert for extracting scene data, writing C4D Python scripts, and controlling Cinema 4D through MCP tools. Activate when: (1) using cinema4d MCP tools (get_scene_info, list_objects, execute_python_script, add_primitive, etc.), (2) writing Python scripts for Cinema 4D extraction or manipulation, (3) working with MoGraph cloners/effectors/fields, (4) baking animation data from C4D scenes, (5) debugging C4D Python API errors, (6) extracting Redshift material or camera data. Covers critical gotchas, correct extraction patterns, MoGraph baking, timeline evaluation, API compatibility, and known failure modes.
Creative writing skill for creating style skills that teach Claude to write in specific styles. Use when you want to create style guides that the cw-prose-writing skill can follow. Creates either simple markdown files or full .skill packages. Audience is AI (Claude), format is directive and example-based.
Create, generate, refine, or critique bold playful app icons using a text-only visual system with measurable composition rules, compact palettes, mascot and dimensional style recipes, originality safeguards, and small-size quality checks. Use for app-icon concept development, production-ready image prompts, icon reviews, visual iteration, and iOS or Android handoff when no reference images should be bundled or required.
Creative technologist specializing in algorithmic art, shaders, and generative systems Use when "generative art, creative coding, processing, p5.js, shader art, algorithmic art, art from code, nft art, creative-coding, generative, shaders, processing, p5js, algorithmic-art, nft-art" mentioned.
Agent-im session skill — generates and edits images/videos using liblib.tv’s AI capabilities. Covers generation (text-to-image, text-to-video, image-to-video, animation, drawing, video clips), editing (replacing, removing, adding, changing, adjusting, local edits, changing shots), style transfer, extending videos, recreating videos/TVCs/promotional films, generating short dramas/comics, music videos, product ads/showcases, storyboards, educational videos, and short-form videos. Also trigger when users mention liblib, libtv, uploading reference images/videos, or checking generation progress. Key rule: trigger whenever a request involves creating, generating, editing, or modifying AI images or videos, regardless of wording.
Arrange opening positions for every scene in an AI short drama: first identify objects in the scene image that can be sat or stood on (projected onto a top-down plane), then assign each character in every scene to a side of an object, sitting or standing, facing direction, and whether extras are present. The program writes an opening blocking sentence for each scene; copy it into the first segment of that scene's storyboard. By default, deliver a draggable HTML tool report for adjusting positions; it can export staging.json in the page. JSON is also saved as working data, and Markdown can be exported as needed. All 8 quality gates are checked deterministically by script (number of identified objects, objects present in the image, exact cast count, every present character assigned to an identified object, no overlapping characters on the same side, specified extra positions, and more). Pre-fills the skeleton from novel-script's script.json and novel-art's art.json. Zero dependencies, zero API keys. Use when asked about blocking, staging, who sits where, seating arrangements, or staging for an AI short drama.
Expert skill for building pixel art idle/incremental games with procedural sprite generation, React/TypeScript/Zustand architecture, and contemplative game design. Use when creating pixel art games, implementing idle game mechanics, generating procedural sprites via Canvas API, building collection-based games, or implementing incremental game economies. Triggers on requests for pixel art, idle games, sprite generation, incremental games, collection games, or contemplative game experiences.
Generate avatar images, surreal paper-art portraits, and reusable image prompts from the shared Punk style library for people, pets, objects, profile pictures, pet portraits, and keepsake cards. Use this skill to identify the subject from image or text, choose one avatar-capable style and any required style mode, compile the selected style atom into the avatar blueprint, save the final prompt, and generate the image when an image-generation tool is available.
Create, adapt, and evaluate images in Ruben's Quiet Impossibility house style: tactile conceptual editorial photographs with one calm physical or material anomaly. Use when Ruben asks for the established aesthetic, Quiet Impossibility imagery, matching surreal still lifes, or Notion covers in the same visual system. Do not use for unrelated image styles.
Human-feel writing — when polishing, refining, or rewriting someone else's text, preserve the presence of the person behind the words. Use when: the user brings a piece of their own writing and asks to polish, refine, revise, tighten, or rewrite it, with asks like "help me fix this up" or "how is this passage". Also applies to rework scenarios where, after ghostwriting, the user says "this feels too AI-generated", "there's no human feel", or "I can't feel me in it". Trigger words: polish copy, refine, help me revise, rewrite, revise this passage, human feel, AI feel. Two built-in layers: underlying principles (when to touch and how to touch) + a post-check list (does what was touched have an AI feel, based on Wikipedia Signs of AI writing / blader humanizer).
Chinese AI/tech writing de-AI editor for posts, X/Twitter threads, technical essays, product notes, model reviews, and public-writing drafts. Use when the user asks to 去AI味, 改得像本人, 写推特post, 精修中文AI技术文章, or complains about AI-flavored shells such as 不是A而是B, 真正/其实/本质上, 更重要的是, 冒号讲义腔, 空泛总结, 顺滑但没作者判断的稿子.
Signed Distance Functions (SDFs) in GLSL—2D/3D shape primitives, boolean operations (union, intersection, subtraction), smooth blending, repetition, and raymarching fundamentals. Use when creating procedural shapes, text effects, smooth morphing, or raymarched 3D scenes.
Rebuild a public X/Twitter status into a deterministic local replica with frozen assets, HTML/CSS, Playwright capture, MP4, and GIF. Trigger on replicate tweet, X post to MP4, make tweet GIF, or freeze status locally. Do NOT use for text extraction, auth pages, or DMs.
Expert vehicle designer combining industrial design rigor with entertainment artistry. This skill embodies the methodologies of Scott Robertson's "How to Draw" precision, Syd Mead's future industrial aesthetic, and the functional-aesthetic balance demanded by AAA racing games like Gran Turismo, Forza, and sci-fi franchises like Halo and Star Wars. Every vehicle tells a story through its form. A racing car must look fast standing still. A military vehicle must communicate power and protection. A spacecraft must suggest propulsion physics even when none exist. This skill bridges the gap between "cool looking" and "believably functional" - the difference between concept art that ships and concept art that gets rebuilt from scratch. Use when "vehicle design, car design, spaceship design, aircraft design, tank design, mech design, motorcycle design, racing car, futuristic vehicle, sci-fi vehicle, military vehicle, hover vehicle, flying car, starship, fighter jet, boat design, submarine design, cockpit design, vehicle interior, vehicle customization, damage states, vehicle livery, form language, vehicle proportion, wheel design, hard surface vehicle, vehicle modeling reference, vehicle turnaround, vehicle, automotive, industrial-design, concept-art, hard-surface, sci-fi, racing, military, spacecraft, mech, transportation, game-art, form-language" mentioned.
Generate clean, playful low-density isometric voxel icon illustrations and explicitly requested four-frame physically credible loops built from large opaque face-lit acrylic blocks on an exact #F4F4F4 background. Preserve the subject's native palette by default, with optional explicitly selected Oreo preset-directed modes. Use for voxel art, macro-voxel 3D icons, isometric block-built objects, animated voxel icon loops or GIFs, blocky editorial symbols, emoji-to-voxel objects, or a visually consistent series. Prefer this skill for isolated objects rather than dense cube grids, Minecraft scenes, smooth low-poly renders, glossy edge-lit toys, transparent glass objects, or 2D pixel art.
Motion-first AI video director for topic-to-video creation. Use when the user gives a theme, idea, article, script, or brief and wants AI to freely create a real animated video instead of a PPT/slideshow-style explainer; when deciding visual metaphors, motion grammar, scene beats, component choices, generated image needs, HyperFrames/Remotion implementation strategy, and anti-PPT QC.
Generate AI short-video scripts, shot breakdowns, visual prompts, caption copy, and prompts ready to enter video-generation testing. Use it to quickly turn a topic into an executable video plan, especially for short-video topic selection, storyboard scripts, AI video prompts, Yijia/Sora/Grok text-to-video testing, image-to-video testing, and structured planning of viral short videos.
Use when generating talking, singing, or presentation videos from a single character image and audio with Alibaba Cloud Model Studio digital-human model `wan2.2-s2v`. Use when creating narrated avatar videos, singing portraits, or broadcast-style talking-head clips.
Generate audio narration of blog posts using Google Gemini TTS. Supports summary narration, full article read-aloud, and two-speaker podcast/dialogue mode with 30 voice options. Outputs MP3 with HTML5 audio embed code. Works standalone via /blog audio or internally from blog-write. Falls back gracefully when API key is not configured. Use when user says "blog audio", "narrate blog", "audio version", "text to speech", "tts", "podcast mode", "read aloud", "audio narration", "voice", "narration", "generate audio".
AI image generation and editing for blog content powered by Gemini via MCP. Claude acts as Creative Director - interpreting intent, selecting domain expertise, constructing optimized 6-component prompts (Subject + Action + Context + Composition + Lighting + Style), and orchestrating Gemini for blog-quality results. Generates hero images, inline illustrations, social preview cards, and OG images. Edits existing blog images. Supports 6 blog-optimized domain modes (Editorial, Product, Landscape, UI/Web, Infographic, Abstract). Works standalone via /blog image or internally from blog-write and blog-rewrite workflows. Falls back gracefully when MCP is not configured. Use when user says "blog image", "generate hero image", "blog illustration", "social card", "generate blog image", "edit blog image", "image generate", "blog cover image", "inline image", "OG image".
Enhanced speech recognition (ASR Pro): transcribe audio/video to text with enhanced analysis such as noise reduction and speaker diarization. Triggered when the user wants to transcribe recordings/videos, generate subtitles, distinguish speakers, or perform enhanced speech analysis.
Use when the user needs HTML Canvas, SVG graphics, data visualization, generative art, or interactive visual elements with D3.js or similar libraries. Triggers: user says "canvas", "SVG", "chart", "data visualization", "D3", "generative art", "animation", "interactive graphics", drawing on screen.
Create or refine custom icon assets as native or traced SVGs and transparent PNG/WebP files. Use when the user asks for a bespoke icon or cohesive icon set, wants an image traced into a clean vector, or needs a detailed or 3D icon with transparency.
Tighten a long recording aggressively — remove silences, fillers, hedges, false starts, and repetitions while preserving laughs and comedic pauses. Cuts are driven by Montreal Forced Aligner (MFA) word boundaries (auto-installs on first run), not raw Whisper timestamps. Use when the user pastes a video and says "cut this", "tighten this video", "remove silences", "strip ums", "clean this up", or any variant of "make this video shorter without losing the good parts".
Complete FFmpeg video stabilization and 360/VR video processing. PROACTIVELY activate for: (1) Video stabilization (deshake, vidstab), (2) Hardware-accelerated stabilization (deshake_opencl), (3) 360/VR video transforms (v360), (4) Perspective correction (perspective), (5) Ken Burns/zoom-pan effects (zoompan), (6) Lens distortion correction (lenscorrection, lensfun), (7) Action camera footage, (8) Drone video processing, (9) VR headset formats. Provides: Stabilization workflows, 360 projection conversions, motion effects, lens correction.
Invoke when the user wants feedback on a game design document, GDD review, design evaluation, or consistency check on an existing design. Triggers on: "review my GDD", "design feedback", "evaluate design", "design document review", "GDD critique". Do NOT invoke for brainstorming new ideas (use game-brainstorm) or balance tuning (use game-balance-check). Part of the AlterLab GameForge collection.
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.