Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Creative & media
Generate AI avatar and digital persona video prompts for Seedance 2.0 on Higgsfield. Use for virtual spokesperson content, digital twin videos, AI presenter clips, avatar-based marketing, virtual influencer content, or any video featuring a digital/AI-generated character as the main subject. Triggers on avatar, digital persona, virtual presenter, AI character, digital twin, virtual influencer, synthetic media, animated spokesperson.
Generate cinematic short-form video with ByteDance Seedance 2.0 Pro on RunComfy. Documents Seedance 2.0 Pro's strengths (multi-modal references — up to 9 images, 3 videos, 3 audio — synchronized in-pass audio with natural lip-sync, cinematic motion refinement), the 4–15s duration schema, and when to route to HappyHorse 1.0 / Wan 2.7 / Kling instead. Calls `runcomfy run bytedance/seedance-v2/pro` through the local RunComfy CLI. Triggers on "seedance", "seedance 2", "seedance v2", "seedance pro", "bytedance video", or any explicit ask to generate video with this model
Create Spine 2D skeletal animations from pre-existing character assets (separated body-part PNGs, atlas spritesheet, or a full character image). Use this skill whenever the user wants to animate a 2D character, create Spine JSON from existing art assets, rig a character with bones, build walk/idle/run/attack animations, produce an interactive Spine Web Player preview, or generate Spine-compatible export files (.json + .atlas + .png). Also trigger when the user mentions "Spine animation", "2D rigging", "skeletal animation", "bone animation", "cutout animation", "animate this character", "make this walk", "create walk cycle", or uploads separated character body parts and wants them animated. This skill handles the full pipeline: asset analysis, skeleton rigging, animation keyframing, Spine JSON export, and interactive HTML5 preview.
This skill should be used when the user asks to "create a Suno prompt", "write a Suno song", "generate music with Suno", "help me with Suno", "make a song prompt", "create lyrics for Suno", "build a music prompt", or mentions Suno AI music generation. Provides comprehensive guidance for creating professional Suno prompts using advanced prompting strategies, structured formatting within 1000 character limit (NO blank lines between sections), parameter optimization, genre-specific techniques, interactive questioning with efficient project name collection, automated artist/song research via sub-agent (web fetching + pattern extraction), automatic file export to organized project directories, AI-slop avoidance for authentic human-centered lyrics, copyright-safe style descriptions that avoid artist/album/song names, character counting utilities for accurate verification, and optional independent quality review via sub-agent for professional assessment.
Generates dynamic videos from plain text descriptions using meitu-cli, covering the high-quality default mode and the high-motion fast mode. Triggers when the user mentions text-to-video, generating video from text, "help me generate a video", "make a video", advertising video, product promo, or short video.
Production guidance for planning, building, animating, capturing, and reviewing complete Three.js scenes for rendered media. Use for browser-native 3D product shots, title sequences, procedural worlds, glTF scene assembly, camera and lighting animation, shaders, post-processing, deterministic frame export, and Three.js render QA; not for modeling standalone assets, WebXR interaction, or generic website decoration.
Route ambitious Three.js graphics work to the smallest expert skill set. Use for new visual experiences, graphics rewrites, reference matching, or requests spanning geometry, materials, atmosphere, shadows, temporal effects, and final image treatment.
Use for video-conditioned audio and automated Foley production: adding synchronized sound effects, ambience, impacts, footsteps, cloth, prop, and environmental audio to silent or under-sounded video using video-to-audio models, text-to-sound tools, manual spot lists, editing, rights checks, and QA.
Use this skill to turn generated, captured, scanned, or modeled 3D output into production-ready standalone assets for DCC, real-time engine, web, or interchange delivery. It covers requirements, topology repair, scale and axes, UVs, PBR baking, LODs, static and skeletal readiness, rig handoff, optimization, glTF/USD/FBX delivery, validation, QA, and rights/provenance. Do not use it for provider-specific generation prompts, full scene/world building, mocap operation, or exact CAD/manufacturing work.
Brief and plan Amazon product photography. Builds the photographer brief for the main image and gallery, specifies lighting, angles, props, and styling per shot, and plans the lifestyle and infographic source shots. Use when a user asks about product photography, a photo shoot, photographer brief, lighting setup, studio shots, or how to get photos taken for a listing. Trigger phrases: "product photography", "photo shoot", "photographer brief", "lighting setup", "studio shots", "photograph my product". Works with zero tools. For image strategy and gallery order, pair with amz-listing-images.
Plan a Sponsored Brands Video ad. Writes the 30-second script, the hook, the on-screen text, the end-card CTA, and version variants for testing. Use when a user asks about Sponsored Brands Video, SBV, video ad script, video ad creative, or running video ads on Amazon. Trigger phrases: "sponsored brands video", "SBV", "video ad", "video script", "video ad creative". Works with zero tools.
Internal sub-procedure (not a standalone entry point) — the shared footage-analysis pipeline that produces audio transcripts, contact sheets, and Sonnet-written summaries. Invoked end-to-end by the process-library and reprocess-with-contact-sheets skills; don't trigger it on its own.
Collaborative brainstorming partner for multi-session ideation projects. Use when the user wants to brainstorm, ideate, explore ideas, or think through problems—whether for SaaS products, software tools, book ideas, newsletter content, business strategies, or any creative/analytical challenge. Handles session continuity across days/weeks via versioned markdown documents. Includes brainstorming methods catalog and supports both connected (cross-project awareness) and clean-slate modes.
Acts as a director and previs supervisor for film, video, and AI filmmaking. Turns scripts, prose, briefs, or existing image and video assets into production deliverables — subtext breakdown, beat sheet, director's book, blocking and staging, shot list with coverage, keyframe and storyboard prompts, image-to-video motion prompts, sound and dialogue plans, edit timelines, continuity bibles, and QC repair notes. Carries genre playbooks, a controlled prompt lexicon, a coded failure-diagnosis manual, and capability-first adapters for current video and image models. Optionally applies one named director's style lens — Spielberg, Hitchcock, Kubrick, Kurosawa, Scorsese, Fellini, Bergman, Tarkovsky, Wong Kar-wai, Nolan, Villeneuve, Fincher, Refn, Bi Gan, Zhang Yimou, Hou Hsiao-hsien, Park Chan-wook, Malick, Michael Mann, Coen Brothers. Use for shot planning, blocking, staging, camera movement, visual continuity, storyboard and keyframe design, prompt repair, "in the style of X" direction, and any AI video workflow.
Pose-conditioned generation on RunComfy via the `runcomfy` CLI. Routes across Kling 2-6 Motion Control Pro / Standard (transfer the motion / blocking of a reference video onto a target character), community Wan 2-2 Animate (audio-driven character animation with pose conditioning), and Z-Image Turbo ControlNet LoRA (pose-conditioned image generation from an OpenPose / DWPose / canny / depth control image). Picks the right route based on video vs still and stylized vs photoreal. Triggers on "controlnet", "control net", "pose control", "openpose", "DWPose", "transfer pose", "motion control", "pose driven", "character pose", "depth control", "canny edge", "use this pose", or any explicit ask to condition generation on a pose / skeleton / motion / depth / canny reference.
SVG Style Studio (/create-svg) - art director + vector illustrator that makes polished, editable SVGs (illustrations, logos, icons, posters, infographics, stickers) in 44 styles - pixel art, 8/16-bit, cyberpunk, Y2K, Frutiger Aero, glassmorphism, clay, isometric, low poly, paper cutout, doodle, comic, manga, sumi-e, ukiyo-e, art nouveau, art deco, bauhaus, brutalist, vintage poster, screen print, risograph, blueprint, technical/scientific, medieval, graffiti, sticker, children's, editorial, infographic, cinematic, fantasy, sci-fi, horror, retro futurism, gothic, luxury, monochrome, geometric, botanical. Use for any request for SVG/vector art, style blends ("cyberpunk + minimalist", "ukiyo-e but darker"), one subject in several styles ("in 5 styles"), or converting an SVG/image to a style. Routes the style, applies its design rules, then validates, optimizes, renders and inspects before delivering.
This skill should be used when the user asks to create a monochrome technical diagram, schematic, or systems/architecture diagram in black-and-white line-art style. Trigger phrases include "create a diagram", "monochrome diagram", "systems diagram", "draw a schematic".
Edit images with Flux 1 Kontext Pro (Black Forest Labs' precise local image-edit model) on RunComfy — bundled with the model's documented prompting patterns so the skill gets sharper output than naive prompting against the same model. Documents Flux Kontext's strengths (single-reference precise local edits, strong prompt control, consistent high-fidelity outputs), the schema (single image + prompt), and when to route to Nano Banana Edit / GPT Image 2 edit / Flux 2 Klein instead. Calls `runcomfy run blackforestlabs/flux-1-kontext/pro/edit` through the local RunComfy CLI. Triggers on "flux kontext", "flux-kontext", "flux 1 kontext", "kontext", "BFL kontext", or any explicit ask to edit with this model
Build never-cheap, motion-crafted promo videos as Remotion compositions — cinematic HyperFrame-style clips (3D poster cubes, capsule theme-flips, architecture data-pulse, particle-burst photo albums) and vertical short-video for 抖音/小红书/视频号. frame-smith is the DIRECTOR, not the renderer: it reads the brief, sets the register (landscape cinematic vs. vertical short), picks ONE effect engine done at 100%, lays a beat timeline, writes the .tsx, and registers it in the Remotion Root. It runs ON TOP OF a video runtime — it needs the `hyperframe` OR the `remotion` skill installed, checks for them FIRST (§0), and guides install if neither is present. Ships a motion craft floor (30fps, second→frame helper, S-scale for vertical, 抖音 safe zones, easing library, export三件套), an effect-engine catalog lifted from shipped HyperFrames, a beat-timeline architecture, and a motion anti-slop blacklist (no everything-fades-up, no linear easing, no janking engine). Supports verb commands (craft · env · beats · engine · restage · slower|faster · register · audit). Triggers on "做个视频", "视频动效", "promo video", "motion graphics", "Remotion 合成", "HyperFrame", "片头动画", "产品宣传片", "3D 立方体动画", "粒子相册", "数据可视化视频", "竖屏短视频", "抖音视频", "小红书视频", "opener animation", "转场", "beat timeline", "把这个页面做成视频", "/frame-smith".
Edit images with OpenAI GPT Image 2 (the `/edit` endpoint of ChatGPT Images 2.0) on RunComfy — bundled with the model's documented prompting patterns so the skill gets sharper output than naive prompting against the same model. Documents GPT Image Edit's strengths (preservation language, multilingual in-image text editing, multi-reference up to 10 images, layout / typography precision), the schema, and when to route to Nano Banana Edit / Flux Kontext / GPT Image 2 t2i instead. Calls `runcomfy run openai/gpt-image-2/edit` through the local RunComfy CLI. Triggers on "gpt image edit", "gpt-image-edit", "chatgpt image edit", "edit with gpt image 2", or any explicit ask to edit with this model
Mask-driven image inpainting on RunComfy via the `runcomfy` CLI. Routes to Tongyi MAI Z-Image Turbo Inpainting (the dedicated inpainting endpoint with mask, strength, and control-scale) and to identity-preserving edit models (Nano Banana 2 Edit, GPT Image 2 Edit, FLUX Kontext Pro) when a mask isn't available and the region must be described instead. Use for object removal, watermark removal, region replacement, blemish cleanup, and any controlled local edit where a binary mask defines the target area. Triggers on "inpaint", "inpainting", "image inpaint", "remove from image", "fill region", "mask-driven edit", "remove watermark", "remove object", "patch the photo", "fill the hole", or any explicit ask to edit a specific masked region of a still.
Generate dynamic videos driven by images, covering single-image generation, multi-image reference fusion (1–9 images), and first-last frame transitions (1–2 images). Triggered when the user mentions image-to-video, turning images into videos, making images move, photo animation, multi-image fusion, first-last frames, transition videos, from A to B, or turning this image into a video.
Animate a still image into a finished, moving video with Pexo. Upload a photo and Pexo adds natural motion, camera moves, and transitions, auto-picks the best image-to-video model (Seedance, Kling, Wan, and more), and returns a publish-ready clip with music. Use when the user has an IMAGE to bring to life: "image to video", "animate this photo", "make a video from this picture", "turn my image into a video". NOT for text-only prompts (use the text-to-video skill) or editing an existing video.
Intelligently adapts any image to a target aspect ratio, automatically rebuilding the composition logic while keeping the subject undistorted and the content complete, with natural, seamless background extension. Triggers when the user mentions image adaptation, image extension, image expansion, outpaint, converting a portrait image to landscape, or fitting Xiaohongshu/Douyin/WeChat Official Account dimensions.
Transfers the motion in a reference video (dance, gestures, movement) onto a target person or character image to generate a motion video. Triggers only when the user explicitly provides a target person image and a reference motion video and expresses intent such as motion transfer, dance replication, making a photo dance, or making a person move.
Use this skill when producing speech, narration, dubbing, localization, advertising voice, voice-clone previews, or interactive voice with MiniMax speech/audio APIs. It covers MiniMax T2A HTTP, WebSocket streaming, async long-form TTS, Speech 2.8/2.6/02 model selection, system and custom voices, rapid voice cloning, voice design, pronunciation/language/emotion controls, pricing and limits, artifact custody, consent and rights checks, and production QA.
Creates showreel-grade motion graphics videos entirely from code — HTML scenes rendered frame by frame in headless Chrome with real motion blur, plus an original score composed for each video on the same beat grid. It directs the film itself from whatever the person gives — their words, a site, a GitHub repository, an app, screenshots, their own video clips and photos, or reference clips — and sets the pace and the energy of the music from them. Use for any promo, ad, launch video, explainer, reel, Shorts or TikTok, intro, kinetic type or logo animation for a business, product, app, site, bot, channel or person, even when all you have is a link or a name.
Relight a still image — change the lighting setup, color temperature, direction, or mood — on RunComfy via the `runcomfy` CLI. Routes to Qwen Edit 2509's dedicated `relight` LoRA endpoint for purpose-built relighting, with fallback to identity-preserving edit endpoints (Nano Banana 2 Edit, GPT Image 2 Edit, FLUX Kontext Pro) when prose lighting language is enough. Use for product relighting (studio softbox → window light), portrait mood shift (overcast → golden hour), or color-grade change. Triggers on "relight", "relighting", "change the lighting", "make it golden hour", "studio lighting", "rim light", "blue hour", "soft window light", "change light direction", "color temperature", or any explicit ask to alter how a still is lit.
Generate podcast clip visualization video prompts for Seedance 2.0 on Higgsfield. Use for podcast clip videos, audio-to-visual content, audiogram alternatives, podcast highlight reels, interview clip visuals, or any video that transforms audio content into engaging visual format. Triggers on podcast, audio clip, audiogram, interview clip, sound bite, audio visual, podcast video, episode highlight, podcast clip.
Use when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation via the OpenAI Audio API; run the bundled CLI (`scripts/text_to_speech.py`) with built-in voices and require `OPENAI_API_KEY` for live calls. Custom voice creation is out of scope.
Korean and French screenwriting practice (韩国/法国编剧方法) — from the international masterclass; Oh Seung-uk (Christmas in August, The Shameless; field research in disguise, "write the emotion", first act and last act first, spaces as skeleton, reading to hostile listeners, surviving producers), Choi Seok-hwan (King and the Clown; genre as promise to the audience, "story = deepening crisis + intensifying desire", two reversals and bittersweet endings, the producer/director/writer trio), and Frédéric Auburtin (Paris je t'aime; dialogue last, Italian-style table reads, "12 lines not 13", dignity for characters, originals born from commissions, editing by emotion). Use when working in a Korean-style commercial drama or genre film, a French auteur/commission context, when planning field research, when a producer relationship is the problem, or when you need the Korean "three live together" development model or the French "emotion first, structure second" editing approach.
Author production real-time VFX in Three.js. Use for filmic HDR lens-flare compositors, highlight-derived ghosts, field-angle pupil deformation, localized glare and bloom, raymarched aurora curtains, finite-footprint emissive slabs, uniform volume integration, equirectangular radiance probes, WebGPU voxel fire and smoke, coupled volumetric fluid fields, mesh-surface emitters, signed-distance fire collisions, ship-conforming reentry plasma, generated capsule wakes, instanced analytic sparks, timed dissolving debris, dense-swap effect pools, additive holographic projections, Fresnel rim shells, scanline banding, glitch displacement, swept shape-to-shape handovers, and explicit scene-relative HDR emission hierarchy.
Use when enhancing, upscaling, restoring, denoising, sharpening, deinterlacing, stabilizing, motion-deblurring, colorizing, SDR-to-HDR converting, or frame-rate/slow-motion converting video (and secondarily images) with Topaz Labs — whether cleaning up AI-generated video, compressed UGC, or old archival footage, or building a generate-low-res-then-upscale delivery pipeline. Covers choosing the right named Topaz model for a specific footage problem, setting parameters, driving the Topaz Platform (Video/Image) REST API's async job lifecycle, judging when enhancement helps versus when it introduces artifacts (over-smoothing, temporal shimmer, face hallucination), and QA of enhanced output. Do not use for originating new video content, non-Topaz upscalers, or purely editorial cuts.
Use meitu-cli to replace content elements in videos (people/scenes/clothing/garments) while preserving the original camera work and motion, supporting text instructions and reference-image driving. Triggered when the user mentions video replacement, changing video content, changing xx in a video into something, replacing the video background, replacing a person in a video with this image, or reference-image replacement.
Applies creative processing to videos or images with meitu-cli: preset style effects (video input), AI creative effects (image input), and long-video style transfer (anime/pixel/clay and more). Triggers when the user mentions video effects, adding effects, creative play, preset styles, AI creative video, style transfer, anime style, pixel-style video, or clay style.
10 proven viral video hook templates with FFmpeg implementations for maximum first-3-second retention. PROACTIVELY activate for: (1) Video hook creation, (2) Opening sequence optimization, (3) Attention-grabbing techniques, (4) Pattern interrupt effects, (5) Curiosity gap implementation, (6) Text overlay hooks, (7) Visual hook effects, (8) Audio hook strategies, (9) Retention optimization, (10) Scroll-stopping content. Provides: Research-backed hook formulas, FFmpeg filter implementations, psychological triggers, platform-specific hooks, A/B testing workflows, and real-world examples with measurable impact.
Capture a website and create a HyperFrames video from it. Use when: (1) a user provides a URL and wants a video, (2) someone says "capture this site", "turn this into a video", "make a promo from my site", (3) the user wants a social ad, product tour, or any video based on an existing website, (4) the user shares a link and asks for any kind of video content. Even if the user just pastes a URL — this is the skill to use.
Add smooth zoom-ins at the moments that matter in an existing video - clicks, form fills, small UI the viewer would otherwise miss - then pull back out. Use when the user says "add zooms", "zoom into the clicks", "zoom in on the important parts", "emphasize the action", "the UI is too small to follow", or "add camera movement to my recording".
Provider-independent production guidance for translating measured audio features into deterministic video timing and motion. Use for beat-, onset-, phrase-, energy-, silence-, or spectrum-reactive visualizers, edits, typography, and generated compositions; not for music-video concept direction, audio generation, or a runtime-specific recipe.
Turn a lesson outline or SME notes into an LMS-ready course module video with learning objectives up front, a chaptered demo mapped one-to-one to those objectives, mini-recaps, and a final recap with a knowledge-check prompt. Use when the user says "make a course module", "turn this lesson outline into a video", "LMS video for this topic", "academy lesson video", or "training module video for our customers".
Produce short, punchy iOS app onboarding videos in Remotion that showcase a feature in action by animating isolated pieces of the UI (cropped components, not full screens) with nice UI-like transitions. Use when the user asks to create, build, or generate an onboarding video, app preview, feature demo clip, App Store preview, or any short video that demonstrates a mobile app feature using supplied screenshots.
Swap a face / character into video or images on RunComfy via the `runcomfy` CLI. Routes across community Wan 2-2 Animate (audio-driven character animation + identity swap), GPT Image 2 Edit (single-shot precise face swap on still images via reference composition), Nano Banana Edit (batch identity-preserving swap), Flux Kontext (single-ref high-fidelity local face edit), and Kling 2-6 Motion Control Pro (transfer motion from one performance onto a target character). Picks the right model for the user's actual intent — single still vs video, full character vs face only, dialog scene vs silent motion. Triggers on "face swap", "swap face", "deepfake", "face replacement", "character swap", "head swap", "put X's face on Y", "make this video star X", "replace the actor in this video", "swap the character in the photo", "deepfake video", "ReActor alternative", or any explicit ask to substitute one identity for another.
Generate images and videos with Kling O3 — Kling's most powerful model family. Text-to-image, text-to-video, image-to-video, and video-to-video editing. Use when the user requests "Kling", "Kling O3", "Best quality video", "Kling image", "Kling video editing".
Use when building a finished product ad from FLUX 3 - shot design, voiceover, action-to-word sync, evidence-gated copy, deterministic assembly, and QC gates that catch clipped audio, floating products, off-model plates, and reports that claim a pass the build did not give.
Start a new framefields video project, or add framefields to an existing Node.js project. Use when the user wants to make a video with framefields and the project has no framefields setup yet, or asks how to install framefields, scaffold a composition and render script, get from an empty folder to a first MP4, generate images, video, music, or voice for a film with AI models (`ai` from framefields, the framefields AI gateway), or add ready-made components (pointers, captions, title cards, device frames …) with `npx framefields add`. Hands off to framefields-compose, framefields-effects, and framefields-render for the details.
Render, inspect, test, and export high-performance WebGPU video and frame grids with the framefields headless engine. Use when verifying compositions, diagnosing blank frames, profiling GPU pipelines, running visual frame grids, or exporting final MP4 video in framefields.
Make and review videos and storyboards with the user in the loop, with any video tool (Hyperframes, Remotion, Motion Canvas, ffmpeg, screen recordings). Use when the user wants to make or edit a video, motion graphic or animation, wants a storyboard or shot list reviewed before animating, wants to pick a visual style or a playbook (a method for one kind of video, like a music video, a talking-head short or a product launch), or wants to review a render and send timestamped feedback. Requires the framejam MCP server.
Production guidance for authoring, integrating, and reviewing GSAP animation in browser-rendered media. Use for deterministic kinetic typography, SVG drawing and morphing, motion paths, FLIP transitions, responsive motion systems, or frame-seekable GSAP timelines inside HTML video composition and React-based renderers; not for ordinary CSS transitions or generic frontend development.
Generate text-to-video with HappyHorse 1.0 on RunComfy. Documents HappyHorse 1.0's strengths (#1 on Artificial Analysis Video Arena, native 1080p with in-pass synchronized audio, multi-shot character consistency, 6-language prompt support), the duration / aspect-ratio / resolution schema, and when to route to Wan 2.7 / Seedance 2 / LTX 2 instead. Calls `runcomfy run happyhorse/happyhorse-1-0/text-to-video` through the local RunComfy CLI. Triggers on "happyhorse", "happy horse", "happyhorse 1.0", "happyhorse video", or any explicit ask to generate video with this model
Use when producing game environments with Layer: background and environment concept art, a side-scroller parallax background split into scrolling layers, a 360 skybox or panorama, or a generated world. Also when parallax layers do not line up or loop, when a background is too busy to read gameplay against, or when exporting layers to Godot or Unity. Keywords: environment, background, parallax, layers, side-scroller, platformer, skybox, 360, equirectangular, panorama, world
Use when making game UI with Layer: buttons, panels, frames, dialogue boxes, tabs, tooltips, HUD elements, ability and inventory icons, currency symbols, or card and badge plates. Also when a button must stretch to any width without distorting its corners, when a UI kit must import into Unity, Godot or CSS, or when an icon set must read at 64px and match approved icons. Keywords: game UI, 9-slice, nine-slice, UI kit, button, panel, frame, HUD, icon set, NinePatch, border-image
Use when producing content for a live game with Layer: item evolution and upgrade chains, weapon or gear tiers, currency packs and store bundles, character level-ups and skins, seasonal and event reskins, or batches of themed items. Also when tiers stop reading as one item, a reskin loses the silhouette, or an event set drifts off-style. Keywords: live ops, upgrade chain, evolution, tier, rarity, currency, IAP, skin, reskin, seasonal event, battle pass, themed items
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.