Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Creative & media
Build deterministic, editable, free-viewpoint Three.js worlds from text or structured briefs. Use for cinematic 3D terrain, semantic regions, procedural biomes, explicit landmarks, environmental scattering, camera fly-throughs, world diagnostics, or requests for a real 3D environment rather than generated 2D footage. Integrates OpenMontage's threejs_world tool with HyperFrames; do not use for a single isolated 3D object or a flat parallax scene.
Direct visual and creative work for campaigns, photography, illustration, video, and branded experiences. Use this skill whenever the user wants to brief a photographer, direct illustrators, plan a creative campaign, develop visual concepts, or evaluate creative work for fit. Triggers on art direction, photo brief, photography brief, illustration brief, campaign concept, creative concept, visual direction, mood board, look and feel, visual treatment, video direction. Also triggers when the user has approved brand identity but needs to extend it into specific creative deliverables. Use `creative-direction` instead when the ask is the project-wide aesthetic brief that this skill consumes as input.
Use when an AI agent needs to work with VidMuse projects, account state, subscription credits, video/audio/image/text/tool models, generated or uploaded assets, style library entries, voice library entries, generation parameters, threads, messages, or long-term memory. Installs and uses the `vidmuse` command runtime when needed.
The model-agnostic AI-video router and brief — the counterpart to image-prompt. Use when someone asks "which AI video tool should I use," "make an AI video," "generate B-roll / a talking-head / a voiceover," "turn this long video into Shorts," or needs a video brief. Routes the job to the right tool by fit and writes a portable brief; the tool generates, the human assembles, WoopSocial schedules/publishes. Sits above the tool skills: veo-3, kling, luma (generative scenes), heygen, synthesia (avatars), ai-voiceover, captions-and-clipping. A real human on camera routes to talking-head-and-piece-to-camera. Never routes to discontinued tools
Apply Disney's 12 principles as practical design and engineering rules for procedural animation. Use when creating, improving, reviewing, or debugging code-driven motion in web, SVG, canvas, React, Remotion, game, UI, character, camera, or 3D scenes; especially when motion feels stiff, weightless, mechanical, unclear, or physically correct but visually weak.
Generates original sports journalism articles by consuming real-time data from the sports-skills skills. Covers game previews, live reports, post-game, team analysis, and player profiles for all supported sports. Use when: the user asks to write, generate, create, or draft an article, preview, report, analysis, summary, or journalistic coverage about games, teams, players, scores, statistics, or sports results. Do not use when: the user only wants raw data without journalistic text — use the sport-specific skill directly (nfl-data, nba-data, football-data, etc.). Do not use when: the user wants to search for news published by third parties — use sports-news.
Use this skill when the user asks to "make a fake text message video", "animate an iMessage conversation", "create a text story video", "do a chat reply animation", "WhatsApp/SMS conversation video", "typing indicator animation", "render a chat thread to a video", or "batch text-message videos from a script/CSV". Covers sent/received bubble layout, staggered appear timing with typing indicators, read receipts/timestamps, per-message pop sound-sync, 9:16 safe-area, and data-driven render from a messages array.
Route generative media requests before any creative planning or provider execution. Use this when the user asks to generate, modify, dub, animate, or assemble image, video, audio, workflow, or analysis-derived media and the first decision is which generation controller should own the job.
Generate MiniMax H3 (Hailuo 3.0) video through the official MiniMax v2 API, fal.ai, Runway, ComfyUI Partner Nodes, or local open weights in ComfyUI. Use for 4-15 second 2K clips, first/last-frame animation, and image/video/audio reference-conditioned video.
Manage multi-level novel revisions while preventing cascade problems. Use when editing novels, when changes at one level break things at others, when you need systematic change management for long-form fiction, or when revisions keep creating new problems.
Clone or update https://github.com/vibe-motion/threejs-earth and render the Three.js Earth route animation with Puppeteer frame capture. Use when users ask for 三维地球航线动画, Three.js Earth, 地球飞线, globe route animation, or exporting an Earth GIF/MP4/PNG sequence.
Expert Godot shader patterns for batch-safe hitflash, alpha-scissor foliage/dissolve, screenspace postFX, depth reconstruction, triplanar, and instance uniforms — not first-shader tutorials. Trigger on draw-call batching breaks, discard vs depth-prepass, foliage shadows, post-process quads, or world-position FX. Keywords: instance uniform, ALPHA_SCISSOR, hint_screen_texture, hint_depth_texture, global uniform, sampler2DArray, canvas_item, spatial, post-processing.
Orchestrate the public UGC creative production line from product or research evidence through creator logic, storyboard, image/video/audio generation handoffs, montage planning, and QA. Use this when the user asks for a repeatable UGC-style ad or creator video workflow rather than one isolated media asset.
The AI music + sound-design skill for social — original/licensed audio beds and sound design for Reels/TikToks/Shorts/videos. Use when someone needs background music, a track, or sound effects for a social video, asks which AI music tool is safe to use, or asks "can I use this trending sound/song on my brand video?". The real brief is "audio that won't get muted, claimed, or sued," so it picks the safest licensed source and never uses copyrighted or trending music without a license. Uses the SCORE framework. Reads brand-profile + the video it scores first. The agent briefs the music + sound design, picks the safest licensed source (ElevenLabs Music/SFX or stock libraries over Suno/Udio; paid tier for commercial rights), and advises licensing/Content-ID/disclosure. The tool generates/licenses the audio; the creator bakes it in; WoopSocial publishes the video and does NOT generate music. Pure AI music may not be copyrightable; never "100% legally safe." Pairs with ai-voiceover.
Expert patterns for 2D animation in Godot using AnimatedSprite2D and skeletal cutout rigs. Use when implementing sprite frame animations, procedural animation (squash/stretch), cutout bone hierarchies, or frame-perfect timing systems. Trigger keywords: AnimatedSprite2D, SpriteFrames, animation_finished, animation_looped, frame_changed, frame_progress, set_frame_and_progress, cutout animation, skeletal 2D, Bone2D, procedural animation, animation state machine, advance(0).
Use to write great prompts for Nano Banana (Google's Gemini image model: Nano Banana Pro = Gemini 3 Pro Image) to generate or edit images for social media — the image-prompt-craft mini-skill. Run when the user wants a nano-banana / Gemini image prompt, an AI image for a post (quote graphic, carousel slide, thumbnail, infographic, product shot, ad creative), or conversational image editing. Reads brand-profile for brand colours/style. Strengths: best-in-class legible in-image text (route typography/layout-led design to ideogram), multi-image consistency, conversational editing, and Google's photoreal lane (Imagen deprecated); surreal art stays Midjourney's. Teaches prompt anatomy, the text-first approach, reference-image consistency, and per-platform aspect ratios. Honest: SynthID watermark + AI disclosure; never real identifiable people or copyrighted characters/logos; verify spelling/data. The API/connection and WoopSocial upload flow live in tools/integrations/nano-banana.md.
Write an Instagram Reel from a raw idea: hook options based on 26 formulas, the spoken script, on-screen text, and a timed beat sheet, all in the user's own voice and scored before they shoot. Use whenever the user wants a Reel, a short-form video script, a hook, a voiceover, asks “make a reel about X” or “what should I say in this video,” or is about to record without having the first line yet.
This skill should be used when the user asks "what are the specs for Instagram Reels / TikTok / YouTube / broadcast", "export settings for social", "what aspect ratio and bitrate", "how do I repurpose 16:9 to 9:16", "safe area / title-safe for vertical", "pre-delivery checklist", or "collect files for handover". It outputs per-platform spec sheets, a cutdown matrix, captioning/accessibility notes, and a QC + collect-files checklist.
This skill should be used when the user asks to "write motion guidelines", "create a brand motion system", "define easing and timing tokens", "document our animation principles", "build a motion language like Slack/IBM/Klarna", "set up entrance/exit/transition rules", or "add a reduced-motion / accessibility section". It outputs a fill-in-ready brand motion guidelines document.
The cultural-fluency + meme-craft skill — participate in internet culture and meme formats as a brand without being cringe, tone-deaf, or legally exposed. Use when someone wants to make a meme, join a cultural moment, build a meme/humor pillar, or decide whether to jump on a format. Meme marketing done wrong is worse than none. Uses the VIBES framework. Reads brand-profile + the meme/moment first. Two hard gates: brand-fit (would it work without your logo?) and safety + IP (never tragedies/divisive/ appropriation/punching-down; original visuals only, no copyrighted characters or celebrity likeness). The agent advises fit/safety/IP and writes the copy/concept; the human/creator makes the asset and adds the final wit pass; WoopSocial publishes/schedules (reactive ones often post in the moment). Sitting a meme out is valid; never fabricates relevance or virality. Distinct from trend-jacking, image-prompt/design-and-templates, community-management, and ai-music-and-sound.
Generates AI images using the nano-banana CLI (Gemini 3.1 Flash default, Pro available). Handles multi-resolution (512-4K), aspect ratios, reference images for style transfer, green screen workflow for transparent assets, cost tracking, and exact dimension control. Use when asked to "generate an image", "create a sprite", "make an asset", "generate artwork", or any image generation task for UI mockups, game assets, videos, or marketing materials.
Use when the user asks for anime soccer or a task matching the examples below. Put the USER into a ~45s Japanese-anime football short as the hero — from their photo + their favorite team + the opponent. Anime-fies the user's face into a consistent character sheet, designs a dramatic 3-act match (come on → equalizer → winner) with the user scoring, writes three 15s cel-shaded scene prompts (CAPS names + Japanese dialogue), generates them on Seedance off the sheets, and stitches them. A Japanese-anime football short built on the Pika MCP, but the star is YOU. Triggers: "/anime-soccer", "put me in an anime soccer video", "make me the anime football hero", "anime match with my photo". Requires the Pika MCP.
Create meme-style images, funny meme drawings, captioned photos, and lightweight social visuals with AnyCap. Use when an agent needs to turn a joke, reaction, campaign hook, quote, or screenshot into a meme image, funny doodle-style meme drawing, captioned image, or short meme-video concept. Combines AnyCap image generation and editing with deterministic local text overlay, optional video generation, and Drive or Page delivery.
Generate neural narration audio using Azure AI Speech (REST text-to-speech). Use when synthesizing voiceovers or narration in OpenMontage. Optional cloud TTS provider — preferred when AZURE_SPEECH_KEY is configured; the local piper_tts remains the default offline path. Shares one Speech resource with azure_stt.
Use this skill when the user asks to “write a creative brief,” “build a motion brief,” says “the client doesn't know what they want,” asks to “turn this vague client request into a brief,” “what questions should I ask the client,” or “make a brief I can get sign-off on.” It turns a fuzzy client ask into a structured, sign-off-ready motion design brief and the exact clarifying questions to send back.
Generate images with GPT Image 2 (ChatGPT Images 2.0) inside Claude Code, using your existing ChatGPT Plus or Pro subscription — no separate OpenAI access, no per-image billing. Supports text-to-image, image-to-image editing, style transfer, and multi-reference composition via the local Codex CLI. Triggers on "gpt image 2", "gpt-image-2", "ChatGPT Images 2.0", "image 2", or any explicit ask to generate or edit an image through the user's ChatGPT plan.
Use when the user asks for voxel it or a task matching the examples below. Voxel-It — turn any photo into a high-quality Minecraft screenshot, keeping the HUMAN subject(s) fully photorealistic while the rest of the frame becomes detailed Minecraft block geometry, then cinematic-color-grade the whole frame to the photo's mood so the real person and the voxel world read as one image. A Step 0 router reads the photo and picks ONE of three input-driven modes: object-only (voxelize just the held/featured object + its tableware, keep the person AND background photoreal, float Minecraft loot-tag labels), background-only (voxelize the background/environment, keep the person and any incidental object photoreal, no tags), or object+background (voxelize everything except the person). Single still-image edit via one generate_image_edit call. This skill absorbs the old minecraft-food and minecraft-world trends. Triggers: "voxel it", "voxelize this", "minecraft world", "minecraft food", "minecraftify this", "minecraftify the background", "voxel food", "minecraft my photo", "put me in minecraft but keep me real", "loot tags on my food", "minecraft everything but the person", "/voxel-it".
The AI image-editing router — inpainting/object removal, background removal, upscaling, outpainting, old-photo restoration, and retouch, routed task-first to the right engine. Use when someone wants to remove an object/person from a photo, cut out backgrounds, upscale an image, extend an image to new aspect ratios, restore an old photo, fix a generated image, or asks which editing tool to use. Uses the TOUCH framework. Reads brand-profile + design-and-templates first. The agent names the task, routes to the right engine, writes the spec, and can call APIs where connected; the HUMAN judges every result at 100%; WoopSocial publishes. Honesty spine: an edited real photo is an edited claim — creative upscalers hallucinate detail (never on products/documents), no defect concealment, body-retouch disclosure honored, no watermark/provenance stripping. Distinct from image-prompt/flux/nano-banana (generation), canva (the design workflow), and before-after-and-transformation (the claim rules).
Generate or edit images and videos through the Atlas Cloud gateway. Use for Atlas-hosted Seedance 2.5/2.0, Gemini Omni Flash, MiniMax H3, Seedream 5.0, GPT Image 2, Nano Banana 2, or when one ATLASCLOUD_API_KEY should access multiple media model families.
Generate expressive, multilingual narration with fish.audio (S1 / S2-generation models) and reuse cloned voices via reference_id. Use when the user prefers fish.audio/Fish Audio TTS, wants a specific playground voice model, or needs high-emotion voice-clone narration.
Manga-style video generator - Specializes in generating animated videos in manga styles such as Japanese healing style, Chinese ink wash style, and American cartoon style. Built-in 8 manga style templates, supports image-to-video, and generates high-quality manga animations with one click. Use this skill when the user needs to generate manga-style, animation-style, or hand-drawn-style videos.
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.