Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Creative & media
WeChat official account title generation and evaluation skill. Based on a confirmed topic, outline, and target readers, generate 8 title candidates, filter out low-quality titles, and recommend the 1 title most worth publishing. Applies at the titling stage before or after writing; does not cover the body text.
Build the setting first for Chinese web fiction. Use when the user is writing a genre with extensive worldbuilding, such as fantasy, xianxia, historical fiction, war, post-apocalyptic fiction, or esports, and wants to establish the world's rules, power systems, factions, geography, politics, economy, and history before writing; fears inconsistent worldbuilding or protagonists ignoring the rules; or wants the world to change with the story (world state). Produces archivable worldbuilding, world-state tracking, and a pre-chapter consistency checklist.
Download a Xiaoyuzhou (小宇宙) episode from a public URL and generate subtitles (.srt) plus transcript (.txt) using faster-whisper. Use when a user provides a xiaoyuzhoufm episode URL and wants full transcript text with timestamps, or needs to convert the audio into SRT/TXT files.
Write a high-retention YouTube script — explainer, tutorial, video essay, review, or talking head — on the packaging then cold-open then value-stack then retention structure that holds watch time past the drop-off cliffs. Use when asked to write a YouTube script, script a long-form or explainer video, draft a video hook, outline a video essay, or turn a blog post or talk into a video. Produces title and thumbnail concepts, multiple hook options, a beat-by-beat body with retention devices, and clear visual and audio cues.
Generate interactive 3D zoning envelope viewers from zoning analysis reports. Use when the user asks to "visualize the zoning envelope" or see buildable massing in 3D, typically after /as:zoning-analysis-nyc. Requires a zoning analysis report as input.
Expert in building 3D experiences for the web using Three.js, React Three Fiber, Spline, WebGL, and interactive 3D scenes. Covers product configurators, 3D portfolios, immersive websites, and adding depth to web experiences. Use for: 3D websites, three.js, WebGL, react three fiber, and 3D experiences
Get polished edited clips ready to post, without touching a single slider. Upload your raw video footage (MP4, MOV, AVI, WebM, up to 500MB), say something like "cut the pauses, add transitions, and export a clean final video", and download 1080p MP4 when it's done. Built for freelance video editors and content creators who move fast and want to complete editing jobs faster without manual cuts and adjustments.
This skill should be used when the user asks about "subtitles", "subtitling", "SRT file", "VTT file", "subtitle timing", "translation for film", "localization", "closed captions", "SDH", "act as a subtitle expert", "subtitle mode", "subtitle formatting", "subtitle translation", "accessibility captions", "subtitle synchronization", "burned-in subtitles", or needs expertise in SRT/VTT creation, subtitle timing, translation adaptation, and accessibility for film and video. Part of the AlterLab FC Skills collection (Cinema & Digital Media department).
This skill should be used when the user asks about "AI sound effects", "text to SFX", "generate sound effects", "ElevenLabs sound effects", "foley generation", "ambient sounds", "soundscape design", "AI foley", "sound design for film", "generate audio for video", "podcast sound effects", "game audio SFX", "act as a sound effects designer", "sound effects mode", "SFX prompting", or needs expertise in AI-generated sound effects, descriptive audio prompting, soundscape layering, and foley creation on ElevenLabs. Part of the AlterLab FC Skills collection (GenAI pack).
Generate and download images through APIMart's asynchronous GPT-Image-2 API. Use when Codex needs APIMart image generation, GPT-Image-2 text-to-image, image-to-image with reference URLs or local image files, 1k/2k/4k output, aspect-ratio control, task polling, or saving APIMart image results locally.
Add sound effects, music, audio streaming, and video players to Decentraland scenes. Covers AudioSource (local files), AudioStream (streaming URLs), VideoPlayer (video surfaces), video events, and media permissions. Use when the user wants sound, music, audio, video screens, radio, or media playback. Do NOT use for 3D model animations (see animations-tweens).
Turn a 2-minute unedited screen recording into 1080p polished edited clips just by typing what you need. Whether it's editing raw footage into shareable videos without desktop software or quick social content, drop your raw video clips and describe the result you want. No timeline dragging, no export settings — 1-2 minutes from upload to download.
Blender 5.x scene setup, render engines (Cycles/EEVEE), output formats, import/export (FBX/glTF/OBJ/USD/Alembic), linking/appending, color management (AgX/Filmic), view layers, viewport config, and world/environment setup via Python (bpy). Includes 5.1 changes (AVIF, HTJ2K, OpenColorIO 2.5, Light Path in World).
Create or operate a portable, auditable Chinese book-review short-video workflow from a clean local workspace. Use when starting a book-video factory, choosing between the original 3:4 bilingual editorial style and the new 9:16 VOX-style book-video workflow, importing dbs-content-system source documents and QST/CON/OPI/CAS/SOL content units, linking script claims to evidence and scenes, using approved Gemini API or Google Flow assets, collecting rights-aware media, recording run cost, or preparing a local master for optional ChatCut fine editing.
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
Get captioned video files ready to post, without touching a single slider. Upload your video clips (MP4, MOV, AVI, WebM, up to 500MB), say something like "generate accurate captions and export as a captioned video ready for Final Cut", and download 1080p MP4 when it's done. Built for video editors and content creators who move fast and need captions added quickly without manual transcription in Final Cut.
Remote-control Cavalry (Scene Group''s 2D motion-design app) by script: build scenes procedurally, animate with keyframes and magic easing, do per-letter text animation, load image/JSON assets, and render PNG frames or full videos. Use whenever the user wants to create or edit a Cavalry scene (.cv file), a motion-graphics sting, logo animation, animated title, countdown, lower third, or particle-style burst in Cavalry — or says ''Cavalry'', ''logo sting'', ''make an animation in Cavalry'', ''intro animation'', ''render from Cavalry'' — even if they don''t mention scripting. Also use when a video project needs an animated overlay that DaVinci Resolve or ffmpeg alone can''t produce.
Da Vinci's thinking framework and creative methods. Based on deep research into 30+ sources including the Da Vinci Notebooks, Vasari's Lives of the Artists, Walter Isaacson's Leonardo da Vinci, Martin Kemp's Leonardo, and Fritjof Capra's The Science of Leonardo, distilling 5 core mental models, 7 life heuristics, and a complete expression DNA. Purpose: as a thinking advisor, analyze creativity, interdisciplinary thinking, observation methods, project management and other issues from Da Vinci's perspective. Use when the user mentions "Da Vinci's perspective", "what would Da Vinci think", "Da Vinci mode", or "davinci perspective". Also applies to: interdisciplinary integration, creative methods, observation training, curiosity-driven learning, and the combination of art and science. Even if the user only says "how to cultivate creativity", "how to think across disciplines", "observation training", or "curiosity", it can trigger. Do not trigger when the user is only asking general questions like "is this decision sound" or "help me think" — activate only when Da Vinci's core methodologies such as creativity, observation methods, interdisciplinary thinking, or curiosity-driven learning are involved.
Use when writing or reviewing Python code in this repo that calls Deepgram Speech-to-Text v1 (`/v1/listen`) for prerecorded or live audio transcription. Covers `client.listen.v1.media.transcribe_url` / `transcribe_file` (REST) and `client.listen.v1.connect` (WebSocket). Use this skill for basic ASR; use `deepgram-python-audio-intelligence` for summarize/sentiment/topics/diarize overlays, `deepgram-python-conversational-stt` for turn-taking v2/Flux, and `deepgram-python-voice-agent` for full-duplex assistants. Triggers include "transcribe", "live transcription", "speech to text", "STT", "listen endpoint", "nova-3", "listen.v1".
Chinese-language fan fiction writing and copyright compliance checks. Use when a user wants to write fan fiction derived from film, TV, anime, novels, or game IP; asks whether a fan work can be commercialized or signed; wants a fan-fiction copyright risk check; or needs a safe rewrite to avoid infringement. Provides creative approaches and compliance checks based on each platform’s fan-work policies.
edit video clips into royalty-free videos with this skill. Works with MP4, MOV, AVI, WebM files up to 500MB. makers, DIY creators, hobbyists use it for preparing videos cleared for maker and DIY content distribution — processing takes 30-60 seconds on cloud GPUs and you get 1080p MP4 files.
Skip the learning curve of professional editing software. Describe what you want — generate a 10-second cinematic video clip from my text prompt — and get AI generated videos back in 1-3 minutes. Upload MP4, MOV, WebM, GIF files up to 500MB, and the AI handles AI video creation automatically. Ideal for content creators who want to create videos without cameras or editing software.
generate text prompts into AI generated videos with this skill. Works with MP4, MOV, WebM, AVI files up to 500MB. content creators use it for generating videos from text prompts using AI for free — processing takes 1-2 minutes on cloud GPUs and you get 1080p MP4 files.
Skip the learning curve of professional editing software. Describe what you want — turn these images into a video with music and transitions — and get free video files back in 30-60 seconds. Upload MP4, MOV, JPG, PNG files up to 200MB, and the AI handles free video creation automatically. Ideal for students, social media users, bloggers who want to create videos from images without paying for software.
Creates memes using the meme CLI with 298 templates. Generates, previews, searches, and lists meme templates. Use when user asks to make memes, create memes, generate memes, or mentions specific meme names like petpet, slap, hug, rub, etc.
Design cheat abilities (外挂/系统) for Chinese web novels. Use when the user wants to design core concepts such as system-based, check-in, pocket-space, simulator, reincarnation-with-foreknowledge, or hiding one’s strength, or give the protagonist a way to grow stronger. Produces a cheat ability concept with prerequisites, a growth curve, costs, and ties to the main plot.
Long-form writing for WeChat official accounts (1500–4000 characters). First diagnose what the author already has (an idea / a pile of material / half a draft / an outline / a finished draft they are unhappy with), then route to one of six corresponding writing approaches, produce a finished draft and run it through a quality check specific to WeChat official accounts. Triggers when the user says "write a WeChat official account post", "help me write an article", "how should I write about this topic", "I have a pile of material but don't know how to organize it", "help me expand this", "revise this piece", "I'm stuck", "long-form article", "in-depth article".
Turn a script into MiniMax H3 shot lists with working emotional performance — beat tables, shot counts, expression direction, and the acting techniques that actually render. Use when breaking a script or scene into H3 shots, writing beat timings, directing a character's face or emotion, fixing flat/wooden performance, deciding shot length or how many beats a shot can hold, or writing prompts for episodic narrative work. Complements the minimax-h3 skill, which covers prompt syntax and ComfyUI setup but not performance or shot breakdown.
Use when users ask for a hand-drawn or illustrated image prompt, name one of the repository's 22 numbered styles or the 3.1 stable variant, or mention triggers such as 亲子手绘、家庭蜡笔画、蜡笔、吉卜力、水墨、像素、淡彩速写、动画概念、水粉、北欧绘本、纸雕、软胶潮玩、墨线绘本、暖色扁平绘本、圆头红线、暖黄墨线、family-crayon-card、warm-flat-storybook、roundhead-redline、warm-yellow-ink-story、朱墨写意、朱墨水墨漫画、vermilion-ink-wash、ink-comic-transfer、皮影、皮影彩染、shadow-puppet、backlit-puppet. Produces prompt text or a formal reference-bearing call bundle and does not generate images.
Generate images from text descriptions using each::sense AI. Create photorealistic photos, illustrations, concept art, digital paintings, logos, and any visual from a text prompt. Supports all styles from hyperrealism to anime, abstract to architectural. 7 specialized models including flux-2-max, gemini-imagen-4, and seedream-v4-5. Use for: concept art, illustrations, marketing visuals, social media images, product shots, storyboarding, creative exploration. Triggers: generate image, create image, text to image, ai image, image generation, txt2img, ai art, generate picture, create visual, image from text, ai illustration, make image, draw, render
Get animated video clips ready to post, without touching a single slider. Upload your still images (JPG, PNG, WEBP, HEIC, up to 200MB), say something like "turn these photos into a 15-second video with smooth transitions", and download 1080p MP4 when it's done. Built for social media creators who move fast and want to make videos from photos without editing software.
Skip the learning curve of professional editing software. Describe what you want — animate this image into a smooth 5-second video clip — and get animated video clips back in 30-60 seconds. Upload JPG, PNG, WEBP, HEIC files up to 200MB, and the AI handles AI video creation automatically. Ideal for social media creators who want to bring static images to life without manual animation skills.
Remote-control a running Krita (the open-source digital painting app) by Python script through a small local bridge — build documents, paint real brush strokes with the current preset or push QPainter pixels, stack and blend layers, add vector/SVG text, run filters and masks, animate frames, and export PNG/JPEG/TIFF/.kra or batch-convert whole folders. Use whenever the user wants to create or edit a Krita document (.kra), composite or retouch a raster image, batch-export layers or files, script or automate Krita, render an animation frame sequence, or says "Krita", "paint layer", "krita script", "batch export from Krita", "open this .kra" — even if they don't mention scripting. Also covers Hungarian: "csinálj egy képet Kritában", "vezéreld a Kritát", "rétegek", "exportáld PNG-be", "kötegelt export". Not for natural-media painting simulation (use rebelle), vector/layout design (use affinity), or keyframed motion graphics (use cavalry).
Download videos and audio from 1500+ websites including YouTube, Bilibili, TikTok, Twitter/X, Instagram, Vimeo, and more using yt-dlp. Use when the user wants to download videos, save media from social platforms, download with specific resolution (720p/1080p/4K), get subtitles, or download entire playlists. Triggers on requests like 'download this video', 'save this YouTube video', 'download in 1080p', 'download with subtitles', 'download this playlist'.
Multimodal content generation (images, videos). Use this skill when the user needs to generate images, create images, generate videos, AI painting, AI drawing, draw a picture, make a video, text-to-image, or text-to-video. Automatically calls multimodal-agent for generation.
Build premium, consistent App Store screenshot campaigns with Nano Banana. Use when Codex needs to analyze an app codebase for brand, style, and claims, decide which screens should be captured, direct the user to take specific screenshots, turn those screenshots into advertisement-first App Store slides, keep a consistent style anchor across the set, and normalize the final exports to App Store portrait sizes.
Generate images with Google Gemini native image models via inference.sh CLI. Models: Gemini 3 Pro Image, Gemini 2.5 Flash Image. Capabilities: text-to-image, image editing, multi-image input. Triggers: nano banana, gemini image, gemini 3 pro image, gemini 2.5 flash image, google image generation, native image generation, gemini native image
Use when creating any quest, mission, or story content — enforces the 5-step narrative coherence check: lore validation, conflict detection, quest registry, and contradiction prevention. Triggers: coherence check, lore validation, quest registry, narrative consistency.
Neta API skill for browsing spaces and worldviews — browse worldview settings, subspaces, and gameplay content by space/tag. Use this skill when the user mentions worldview/space/universe/scene settings, or wants to browse characters and gameplay based on space and activity structure; it does not handle specific image/video/song creation (handled by neta-creative).
Turn a research paper, a paper2assets package, or an existing PPT deck into a narrated MP4 video by fully delegating slide authoring to the installed ppt-master skill and fully delegating rendering, subtitles, timeline assembly, and strict media QA to the installed pptx2video skill and its public CLI. Resolves one explicit animation-trigger decision (on-click or after-previous) and hands it to both child skills so the delivered PPTX and the delivered MP4 never disagree, then audits the final PPTX's native p:timing tree to prove the handoff held. Use when the user wants a paper turned into a video, wants /paper2video, or wants a narrated MP4 plus editable PPTX from a paper2assets bundle.
Turn a voiceover script, a single opinion line, or a complete topic into an editorial-metaphor collage-style video (black-and-white halftone cutouts + flat color fields + stop-motion assembly from an empty stage piece by piece). Two modes: single-line 5-second B-roll (single or batch), and beat map-driven 45–60 second full explainer videos (with voiceover TTS, content-aware speed changes, subtitles and assembly). Use when the user says "拼贴 b-roll", "纸拼贴视频", "vox 那种风格的视频", "半调拼贴动画", "给这句口播配画面", "把这个选题做成拼贴讲解视频"; it also handles downstream video-ization needs after ray-kb / ray-writer / ray-cover output. Not for: cases requiring precise layer and timeline control (use HyperFrames), prompt-only without a finished video, on-camera talking heads, or live-action product ads.
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.