Global-AI-Group-Inc
OrganizationMira AI content generation skills: genre playbooks and prompting knowledge for AI agents that generate video and images through the Mira MCP server
Categories
Indexed Skills (14)
mira-3d
3D models on Mira AI: a textured mesh (GLB, FBX, OBJ, USDZ) from a text prompt or from one to four photos, optionally rigged as a humanoid with animation clips. Use it for "3D model", "3д модель", "сделай меш", "GLB", "для Blender", "для Unity", "for a game", "3D print", "AR product", "turn this photo into 3D", "rig this character". Pass skill="3d" to generate_3d, or call rig_3d on an existing model. Do NOT use for 2D renders that merely look three-dimensional (mira-toon3d) or for product photos (mira-product).
mira-ads
Short paid creative on Mira AI: a bold ad clip or a banner with a hook in the first beat, an offer and a clean closing frame. Use it for "ad", "commercial", "promo", "sale", "banner", "рекламный ролик", "промо", "баннер", "скидка", Meta or TikTok ads, launch teasers. Pass skill="ads" to generate_video or generate_image. Do NOT use for authentic creator clips (mira-ugc), quiet catalogue packshots (mira-product) or slow film mood (mira-cinematic).
mira-anime
Hand-drawn anime on Mira AI: cel-shaded characters, painted backgrounds, drawn camera, not footage. Use it for "anime", "аниме", "manga style", "cel shading", "make it a cartoon in the Japanese style", turning a photo or a product into an anime scene. Pass skill="anime" to generate_video or generate_image. Do NOT use for Western illustration or storybook (mira-illustration), 3D animation (mira-toon3d) or pixel art (mira-pixel).
mira-cinematic
Film-grade mood pieces on Mira AI: one strong image, motivated light, real optics, a grade. Use it for "cinematic", "film look", "brand film", "hero shot", "mood video", "кино", "как в фильме", "атмосферно", teasers and key visuals. Pass skill="cinematic" to generate_video or generate_image. Do NOT use for phone-shot creator content (mira-ugc), catalogue packshots (mira-product) or fast paid cuts (mira-ads).
mira-explainer
Clear demonstration clips on Mira AI: show how a product or service works in plain light and plain framing so the value is obvious without words. Use it for "explainer", "demo", "how it works", "tutorial", "show the steps", "объясняющее видео", "покажи как работает", "инструкция". Video only. Pass skill="explainer" to generate_video. Do NOT use for creator testimonials (mira-ugc), paid ads (mira-ads) or drawn motion graphics (mira-illustration).
mira-generate
Generate images and video on Mira AI through its MCP server: connect, pick a model, attach the user's avatar, location or product, write the prompt, pass a playbook skill, wait for the result, extend or upscale a clip. Use it whenever the user wants to "generate", "make a video", "make an image", "animate this photo", "create an ad", "сгенерируй", "сделай видео", "сделай картинку" and a Mira MCP server is connected or can be. Chain with mira-video-prompting and mira-image-prompting for what to write, and with the mira-* playbooks for the genre. NOT for prompting theory on its own.
mira-illustration
Drawn and painted artwork in motion on Mira AI: editorial illustration, storybook, comic panel, flat vector, watercolour or gouache brought to life. Use it for "illustration", "illustrated video", "motion graphics", "storybook", "watercolour", "иллюстрация", "нарисованный ролик", "как в детской книге". Video only. Pass skill="illustration" to generate_video. Do NOT use for Japanese anime (mira-anime), 3D animation (mira-toon3d) or pixel art (mira-pixel).
mira-image-prompting
How to write stills for Mira AI's image models: GPT Image 2, Nano Banana Pro, Seedream 4 and 4K, Flux. Which model holds text, which keeps a product identical across a series, how the craft banks for light, optics, composition, grade and materials are used, and the words that make an image worse. Use it before any generate_image call on Mira, or when the user says "image prompt", "промпт для картинки", "нарисуй", "сгенерируй картинку", poster, packshot, banner, cover. NOT for video (mira-video-prompting).
mira-pixel
Pixel art on Mira AI: sprites on a visible grid, a limited palette, stair-stepped edges, motion in held frames. Use it for "pixel art", "8-bit", "16-bit", "retro game style", "sprite", "пиксель-арт", "как в старой игре", "пиксельный". Pass skill="pixel" to generate_video or generate_image. Do NOT use for smooth cartoon animation (mira-toon3d), anime (mira-anime) or flat vector illustration (mira-illustration).
mira-product
Product-as-hero visuals on Mira AI: studio packshots, lifestyle scenes with the product in use, hands holding it, marketplace cards. Use it for "product shot", "packshot", "product video", "товар на белом", "карточка товара", "предметная съёмка", "show my product", e-commerce, catalogue, Amazon or Wildberries style. Pass skill="product" to generate_video or generate_image. Do NOT use for creator-style phone clips (mira-ugc), loud paid creative with a headline (mira-ads) or film mood pieces (mira-cinematic).
mira-toon3d
Stylised 3D animation and CGI key visuals on Mira AI: the look of a modern animated feature, appealing simplified shapes, designed studio light, bouncy timing. Use it for "3D animation", "Pixar-like", "3D cartoon", "CGI character", "3D render of my product", "3D мультфильм", "мультяшный 3D", "рендер". Pass skill="toon3d" to generate_video or generate_image. Do NOT use for hand-drawn anime (mira-anime), flat illustration (mira-illustration) or photoreal product renders (mira-product).
mira-ugc
Creator-style clips and photos on Mira AI: phone-shot, handheld, someone talking to the camera, a review, an unboxing, a how-to, a testimonial. Use it when the user says UGC, "shot on a phone", "like a customer filmed it", "creator video", "TikTok ad", "influencer style", "отзыв", "распаковка", "как снято на телефон". Pass skill="ugc" to generate_video or generate_image on Mira. Do NOT use for glossy product hero shots (mira-product), brand films (mira-cinematic) or anything drawn (mira-anime, mira-toon3d, mira-pixel).
mira-video-prompting
Which of Mira's thirteen video models to pick and how each one treats a prompt: Seedance 2.5, Runway Gen-4.5, Kling 3.0, Veo 3.1 (Fast, Lite, Quality), Gemini Omni Flash, MiniMax H3, HappyHorse, Wan 2.7 and 3.0, Grok Imagine. Use it before any generate_video call on Mira, when the user asks "which model", "how long can it be", "does it have sound", "промпт для видео", or pastes a video prompt to improve. NOT for stills (mira-image-prompting) or for the camera and light banks themselves (mira-craft).
mira-craft
The camera, light, look, rhythm, time and continuity banks Mira's prompt pipeline is built on, generated from the live registry: 58 camera moves, 36 lighting schemes, film stocks, grades, lenses, hooks, cut patterns, the continuity doctrine. Use it when you write a clip prompt for Mira yourself and want a camera move, a light or a look to be YOUR decision rather than the pipeline's: pick from the bank, write the description in words. Also answers "what camera moves exist", "lighting scheme for", "движение камеры", "схема света". NOT a prompting workflow (mira-video-prompting) and never a list of keys to paste.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.