Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Creative & media
Invoke when the user asks about art style, visual language, style guide, character design, environment art, UI art direction, asset pipeline, reference boards, color palette, or shape language. Triggers on: "art style", "visual", "style guide", "character design", "environment art", "asset pipeline", "color palette", "shape language". Do NOT invoke for UI/UX layout (use game-ux-designer) or creative vision (use game-creative-director). Part of the AlterLab GameForge collection.
AI image generation via Gemini, or Atlas Cloud with `-p atlas`. Use when the user wants to generate, create, or make an image, or when you need to create visual assets like logos, diagrams, or illustrations. Requires GEMINI_API_KEY or GOOGLE_API_KEY, or ATLASCLOUD_API_KEY when using `-p atlas`.
Production guidance for assessing, exporting, packaging, integrating, capturing, validating, and handing off Lottie vector animations. Use for Bodymovin/Lottie JSON, dotLottie archives, renderer and player compatibility, fonts and glyphs, image assets, markers and segments, deterministic video capture, responsive sizing, optimization, accessibility, and cross-platform QA; not for general After Effects animation craft or live-action/video delivery.
Direct and operate Luma Ray video generation through the current Luma Agents API and distinguish it from the consumer Luma App and legacy Dream Machine API. Use for Ray 3.2 text/image/multi-keyframe video, edits, extends, reframes, HDR/EXR, pricing and approvals, async delivery, migration, rights, privacy, and production QA.
Creative direction and design intelligence for Remotion motion graphic videos. Use when an agent needs to (1) convert a script or SRT into a shot-by-shot visual design document, (2) ideate motion graphics with editorial intent for each scene, (3) produce a design brief for user approval before writing Remotion code. Always use before generating any Remotion video code from a script.
Produce and understand audio with OpenAI request-based audio APIs and audio-capable chat models, including text-to-speech, transcription, translation, multimodal audio input/output, model routing, prompt and performance direction, artifact custody, approval gates, and safety/rights review. Use for non-realtime OpenAI audio production; route continuous live voice agents to the separate realtime voice skill.
Tighten prose by stripping AI tics and applying Orwell/Gowers plain-English rules. Use when the user asks to rewrite, tighten, simplify, or detox writing — phrases like "plain English", "make this clearer", "cut the AI voice", "fix the writing", "rewrite plainly", "tighten this", "detox this". Also run as a self-audit pass before delivering long-form prose (essays, blog posts, articles, reports) so the output isn't recognisably AI-generated. Three modes: audit (flag + suggest), rewrite (deliver cleaned prose), edit (fix a named file in place). Technical documentation routes to the simple-english skill instead.
Post-processing visual effects including chromatic aberration, vignette, depth of field, film grain, color grading, and LUT support. Use when adding cinematic polish, retro aesthetics, camera simulation, or atmospheric effects to 3D scenes. Essential for mood, style, and visual storytelling.
Turn talking points, objection lists, or pitch guidance into an energetic sales enablement training video: the real scenario a seller faces, a wrong-way vs right-way contrast, the exact phrasing shown on screen as it's narrated, and a three-takeaway recap. Use when the user says "make a pitch training video", "turn these talking points into a training video", "objection handling video for my SDRs", "sales enablement video", or shares a battlecard and wants reps trained on it.
Turn a steps list, SOP doc, or rough recording into an internal software training video - role-framed intro, numbered step scenes with visible step markers, attention guided to every field and click, and a "what changes for you" close. Use when the user says "make a training video for this tool", "teach the team how to use X", "onboarding video for this workflow", "rollout video for the new system", or "turn this SOP into a training video".
Generate AI lip sync and visual dubbing with Sync Labs (sync.so) — choose the right model (sync-3, lipsync-2, lipsync-2-pro, lipsync-1.9.0-beta, react-1), build the POST /v2/generate request, host inputs, handle async jobs via polling or webhooks, run batch dubbing/localization, and review output for sync accuracy and identity preservation. Use when an agent must re-voice, dub, translate, personalize, or re-time the mouth of a talking-head video (or animate a still face from audio), or must debug a failed/rejected Sync generation. Also covers consent, likeness, and rights obligations for editing a real person's face.
Build production analytic and bounded water in Three.js. Use for luminescent shallow-water rivers with coupled flow, bioluminescent excitation, advected foam and RGB caustics, photoreal shallow water with gravity-capillary FFT waves, dispersive caustics and diffraction glare, shared multi-wave displacement and normals, bounded RGBA heightfield pool simulation, local drops, object-driven ripples, differential-area caustics, ray-traced pool/water/sphere volume optics, derivative-filtered normal bands, analytic sky reflection, side-aware Fresnel, heuristic screen refraction, Beer-Lambert absorption, and crest foam.
Cut a video's script down to its essentials so it hits a target length - trim redundancy, keep every step, regenerate the narration, and re-align the visuals. Use when the user says "tighten the narration", "the voiceover is too wordy", "get this script down to 60 seconds", "make the narration punchier", or gives a video plus a target length the current script overshoots.
Turns an informational or content video (a talking-head explainer, an opinion or analysis piece, a product-review-style clip, anything that isn't a software walkthrough) into a clean written article, built as a real, live article inside a Clueso project. Structured by argument or topic beats, not numbered UI steps. Supporting visuals come from real frames pulled out of the video where something on screen actually helps (a chart, a labeled object, a demonstrated comparison), and from generated images everywhere else a real frame wouldn't convey the point. Use when the user says "turn this video into an article", "write up this clip as a blog post", "make a written version of this explainer video", or uploads a piece of content (not a screen recording of software) and asks for an article from it.
Use Amazon Polly for production text-to-speech work: selecting Standard, Neural, Long-form, or Generative engines and compatible voices; authoring SSML; creating speech marks for captions, word highlighting, or lip-sync; managing pronunciation lexicons; running synchronous, streaming, or asynchronous S3-backed synthesis; planning quotas, pricing, IAM, privacy, and QA for narration, audiobooks, accessibility audio, avatars, and multilingual media.
Binding audio analysis data to visual parameters including smoothing, beat detection responses, and frequency-to-visual mappings. Use when creating audio visualizers, music-reactive animations, or any visual effect driven by audio input.
Produce full-length audiobooks and long-form narration with generative voice tools. Use when the task is to turn a manuscript or long text into hours of spoken audio: preparing the manuscript for narration (front/back matter, footnotes, tables, dialogue), casting a single narrator or full cast, controlling pronunciation and voice consistency across a whole book, running a proofing/QC listen, meeting a retailer's technical delivery specs (RMS, peak, noise floor, room tone, chapterized files, metadata), and choosing a distribution route under each platform's current AI-narration policy. Not for short TTS clips, single-line voiceover, podcast production, or captioning existing video.
Build or substantially refine reproducible Blender models through Python and the Blender CLI. Use for user requests to create meshes, props, hard-surface assets, stylized objects, assemblies, procedural geometry, game-ready GLB assets, or to iterate on a scripted Blender model from visual feedback.
Generate high-density editorial HTML info cards in a modern magazine and Swiss-international style, then capture them as ratio-specific screenshots. Use when the user provides text or core information and wants: (1) a complete responsive HTML info card, (2) the design to follow the stored editorial prompt, (3) output in fixed visual ratios such as 3:4, 4:3, 1:1, 16:9, 9:16, 2.35:1, 3:1, or 5:2, or (4) both HTML and a rendered PNG cover/card from the same content.
Use for ElevenLabs provider-specific dubbing, localization, voice changer, speech-to-speech, and voice isolation/enhancement workflows. Applies when an agent must prepare source media, choose ElevenLabs dubbing versus voice conversion, manage language/speaker/timing decisions, handle voice identity and consent, call or plan against documented ElevenLabs APIs, export dubs/transcripts, estimate cost/limits, or quality-control localized speech while avoiding generic text-to-speech guidance.
Use Hume Octave for emotionally expressive speech and voice production: text-to-speech, voice design, voice cloning, voice conversion, streaming/realtime TTS, multilingual narration, dialogue continuity, timestamps/lip-sync, safety/rights review, and production QA.
Use this skill to plan, direct, finish, and QA provider-independent mono or stereo 180-degree, 360-degree, spherical, spatial, wide-FOV, and immersive video. It covers format choice, capture rigs, stitching, nadir and seam management, stereoscopic comfort, attention direction, stabilization, ambisonic and spatial audio, titles, captions, accessibility, edit, color, VFX, projection metadata, Vision Pro, YouTube, headset delivery, device QA, and privacy, location, and likeness rights. Do not use it for interactive XR apps, volumetric/world-model generation, game-engine experiences, or provider-specific video generation prompts.
Create, edit, guide, upscale, and quality-control still images with Leonardo.Ai's official Production API, including native Lucid and Phoenix models, uploaded or generated references, image-to-image, ControlNet guidance, realtime-canvas inpainting, Pro and Universal upscalers, and custom Elements or models. Use for Leonardo image API implementation, async polling or webhooks, dry-run and cost governance, secure artifact handling, prompt iteration, or production troubleshooting. Do not use for Leonardo video, 3D generation, unofficial wrappers, or third-party gateway APIs.
Generate Chinese voiceover audio from text files via the MiniMax TTS API, automatically handling frequent pronunciation errors such as polyphonic characters, English abbreviations, mixed model names, and number reading. Triggers when the user says "use MiniMax to generate voiceover audio".
Use this skill when planning, capturing, processing, validating, troubleshooting, or exporting markerless human motion capture with Move AI products, including Move One single-camera workflows and Genesis multi-camera studio systems. It covers provider selection, setup, calibration, wardrobe and lighting constraints, documented multi-person operation, processing, cleanup, skeleton and retargeting choices, DCC/game-engine export, data management, consent, and privacy. Do not use it for general keyframe animation, non-Move mocap systems, 3D asset generation, or generic animation cleanup unrelated to Move AI outputs.
Use NVIDIA Maxine / NVIDIA AI for Media audio effects for speech cleanup and enhancement in live or offline media pipelines, including Background Noise Removal, denoise+dereverb, room echo removal, acoustic echo cancellation, audio super-resolution, Studio Voice, Speaker Focus, and Voice Font. Use when selecting, integrating, prompting around, QAing, or privacy-reviewing NVIDIA AFX SDK or BNR NIM workflows for conferencing, broadcast, podcast, avatar, ad, social, and video post-production audio.
Create and edit Remotion videos with domain-specific knowledge. TRIGGERS - Use this skill when: - User mentions "Remotion" in their request - User references a Remotion project path (remotion-videos/*, contains remotion.config.ts) - User asks to create, animate, or edit video content in a Remotion context - User wants to build compositions, animations, or video sequences in React Always invoke this skill BEFORE writing any Remotion code.
Resource recommendation article generator with multi-turn workflow and domain adaptation. Creates structured articles with verifiable data, proper formatting, and professional style. Use when user explicitly requests to generate/write/create a recommendation article (生成/写/创建 + 推荐文章/资源列表). Must include both action + article intent. Don't trigger on simple questions like "推荐几个工具".
Generate, edit, and iterate still images with Runway's official API, especially native Gen-4 Image and Gen-4 Image Turbo reference workflows. Use when implementing Runway text-to-image, reference-driven image generation or natural-language image edits, task polling, secure artifact handling, production retries, cost controls, or Runway image API QA. Do not use for Runway video generation or third-party gateway APIs.
[Manju Lao Li AIGC End-to-End Skill · V7.4.26 Multi-Skill Suite] An industrialized screenwriting and audiovisual directing system for Douyin/Hongguo hit short dramas and manhua dramas (1 controller + 12 sub-skills · four layers deep). Covers the full pipeline from script development → storyboards → asset prompts → fight scenes → feeding scripts → output QA, producing video prompt sets that can be fed directly to Seedance 2.5 / 2.0 (model version is locked). Six required preflight locks before work begins (① genre routing ② source of materials ③ model version ④ aspect ratio ⑤ deliverable format ⑥ scene transitions), plus a style lock: if any are unspecified, stop and ask the user to choose from the options. Never skip by default or infer on the user's behalf—this is a hard gate, not a suggestion. Also includes three levels for locking action intensity. Use for short-drama scripts, novel adaptations, episode outlines, storyboards, 3×3 scene boards and character portrait prompts, fight-scene storyboards, dialect dubbing annotations, narration scripts, feeding-script generation, and output self-checks. The user can simply state the request; the controller routes it to a sub-skill automatically, with no need to know the division of work (but the locks must be asked).
Generates a deliverable (project.md + /brag video + logo + visuals) ready to be added to TeamSpark, the team screen that showcases projects on a loop. Use when the user says "/spark-gen", "/sparck-gen", "génère une fiche TeamSpark", "prépare mon projet pour TeamSpark", or wants to showcase their project on the team screen.
Operate Stability AI image generation, image-to-image, edit, control, background, and upscale APIs safely and reproducibly. Use when selecting or calling Stable Image Ultra, Core, Stable Diffusion 3.5, v2beta image edit/control services, or Stability open-weight image models; when debugging schemas, moderation, rate limits, cost, lifecycle, licenses, privacy, provenance, or migrations; and when planning production QA for Stability-generated images.
Combine two or more videos into one coherent piece with consistent styling and bridging narration between the parts. Use when the user says "stitch these videos together", "combine these recordings into one", "merge these two videos", "join my clips into a single video", or has several separate captures that should play as one.
Build authored procedural buildings and architectural kits in Three.js. Use for massing grammars, exposed-edge analysis, façade bays, profiles, arches, cornices, roofs, ornaments, material-slot mesh compilation, deterministic variants, and procedural city assets.
Build raymarched space phenomena in Three.js. Use for black-hole lensing, accretion disks, wormhole throat transits, curved-ray and null-geodesic integration, lensed celestial spheres, procedural star fields and galactic skies, relativistic-looking distortion, bounded volumetric structures, and GPU effects that need controlled numerical integration.
Implement stable, scalable directional-shadow systems for Three.js. Use for large procedural worlds, city scenes, terrain, moving cameras, WebGPU/TSL shadow nodes, cascades, cached clipmaps, texel stabilization, update budgets, and targeted invalidation.
Create scroll-stopping video ads with Pexo. Give it your product, brand, or a photo and Pexo writes the hook, sequences the shots, picks the best models, and delivers a finished ad with music — ready to run on Meta, TikTok, or YouTube. Use for advertising/promo video: "video ad", "make an ad", "product ad", "promo video", "commercial". NOT for explainer or tutorial content (use the explainer-video skill).
Help users write professional-grade AI video prompts and generate an MP4 video straight from them. Supports multiple creative scenarios and problem diagnosis to ensure prompts are accurate and executable. Trigger words: video prompt, video generation prompt, AI video creation, write video prompt, director instruction, text-to-video prompt, video script, generate video
Plan and integrate ShengShu Vidu Open Platform video generation with current model/mode selection, reference consistency, pricing, exact approval, async task handling, and safe artifact custody. Use for Vidu API text-to-video, image-to-video, start/end-frame, multi-subject reference, media-reference, or Q2 multi-frame work; do not conflate the API with vidu.com consumer plans or Vidu-S1 streaming digital humans.
Search a video library with natural language via the VSS Pipeline Manager — upload a video (POST /videos), generate its embeddings (POST /videos/search-embeddings/{id}), then run a query (POST /search/query) with optional tag and time filters and read the ranked clip results. Use when the user says "search my videos", "find <thing> in the videos", "when did X happen", or wants to ingest/index a video for search. Requires a search-capable deployment (--search, --dual, or --unified).
Summarize a video through the VSS Pipeline Manager — start a summary pipeline with POST /summary (full required body), poll GET /summary/{stateId} until complete, then return the summary via GET /summary/{stateId}/raw. Use when the user says "summarize this video", "create a summary", "what happens in this video" (on an ingested video), or wants to run/inspect the summarization pipeline. Requires a summary-capable deployment (--summary, --dual, or --unified).
Parse the real download URL of a WeChat Channels video in one click. Paste a WeChat Channels share link to get the video title, cover image, and a HD watermark-free download URL. Trigger words: use when the user mentions "parse WeChat Channels", "WeChat Channels download URL", "WeChat Channels download", or "WeChat Channels watermark-free download"
[MASTER ENTRY POINT] Chief director for Chinese long-form, WeChat official account articles and opinion-piece workflows that require multi-stage artifacts. Use for planning, research, writing, review and delivery tasks such as "write one", "create", "draft a long article", "start from topic selection". Simple polishing, proofreading and translation do not trigger it; when only analyzing, creating or updating a style profile, use style-modeler instead. If the user has already explicitly chosen A/B/C, accept it directly; otherwise decide the mode based on the task and do not force the user to choose a technical workflow.
Generate persistent, explorable 3D worlds/environments with Marble by World Labs — from text, a single image, multiple images, video, or a 360 panorama, plus coarse-structure blocking with Chisel. Use this skill when a task needs a navigable 3D scene, VR/immersive backdrop, virtual-production environment, previz set, game-blockout, or web/engine-ready Gaussian splat or mesh, and you must choose an input mode, a Marble model, an export format, and a plan/API route, then review world quality. Covers the Marble web app and the World API, editing/expansion, output formats and what each supports downstream, import into Unity/Unreal/Blender/Houdini/web, pricing/credits, capability limits, and rights/licensing. Not for flat text-to-image, text-to-video clips, or real-time on-the-fly world models (Marble outputs are downloadable, static 3D environments).
A Xiaohongshu image-and-text note creation workflow designed for [券商名称] Securities official/employee accounts, achieving soft-marketing traffic generation where "every topic turns to investing". Core features: (1) supports naturally steering any lifestyle or trending topic toward investing and personal finance; (2) intelligently determines whether to create from scratch or rewrite existing content; (3) two-stage creation: stage one focuses on topic exploration, high-quality first-draft creation, and review/refinement (without considering IP style or platform format); (4) stage two performs IP style transfer and platform format adaptation (choose the account style, defaulting to the [券商名称] official style, with multi-account style switching supported); (5) rewrite into a Xiaohongshu note draft (keeping the core points), outputting 5-10 title versions, a multi-page note structure (cover page + N content pages + closing promo page), and body content (including lead-in + risk disclaimer + tags); (6) Phase 3 by default outputs three-style AI drawing prompts ([视觉风格A] + Mondo master poster style + journal hand-drawn infographic style, one set per page, where the journal style supports intelligent matching of 36 infographic types), with optional additional HTML previews (Vital Geometry style or magazine info-card style); (7) evaluates viral potential and provides optimization suggestions; (8) outputs the complete note draft plus the full set of accompanying images. Every major step requires user confirmation. Applies to financial knowledge popularization, personal-finance tutorials, investment tool introductions, and scenarios turning any lifestyle topic such as food, travel, shopping, or workplace into investing and personal finance. Demonstrates professionalism while softly guiding customers to consult or open an account at [券商名称] Securities.
Download YouTube videos with customizable quality and format options. Use this skill when the user asks to download, save, or grab YouTube videos. Supports various quality settings (best, 1080p, 720p, 480p, 360p), multiple formats (mp4, webm, mkv), and audio-only downloads as MP3.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
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.