Video & Animation

Turns Claude Code or Codex into an AI film studio with the MiniCut CLI. Idea or script to story, shot sheet, character and location pictures, video takes, voice lines, music and an edited cut in the MiniCut editor, on Seedance, Kling, Wan and other models. Checks every step and stops before every paid run with the price. Use when the user wants to make an AI short film, AI drama, AI series, trailer, ad, music video or multi-shot video, or says "make a film", "make an episode", "storyboard this", "make a short drama".

找出并剪除口播、课程录像和屏幕讲解中的重复讲述、重录残留及未完成起句，同时核对声音、课件和操作画面的衔接，提供带时间点的建议、可核对预览或保留原片的完整剪辑版。适用于“口播没剪干净”“找重复段”“去重剪辑”；纯文字清理、摘要压缩和宣传片制作不使用本 Skill。

Turns one long video, podcast, talk or article into a week of native pieces. Scores a transcript for the best 20 to 60 second windows on opening hook, self-containment, density and payoff, writes ready-to-run ffmpeg commands for 9:16 cuts with matching caption files, then adapts each piece for each platform with a new first frame, platform captions and no foreign watermarks, plus text and carousel spin-offs. Use when someone has long content and asks for clips, Shorts, Reels, a content week or "how do I get more out of this video".

Turns a video and its transcript into an edit plan. Reads an SRT or VTT file to report speaking pace, dead air to cut and filler words with timestamps, re-chunks subtitles into short readable lines for vertical video, and writes a cut list, b-roll and on-screen text notes, and export settings. Use when someone asks how to edit a video, wants captions or subtitles, wants to remove pauses and ums, or says their edit feels slow. Produces instructions and a caption file to apply in CapCut, Premiere, DaVinci, Descript or any editor. Nothing edits the video itself.

Turn one or more reference videos into a reusable style, written either as a STYLE.md file or as an installable agent skill that makes new videos in that style. Use when asked to capture, extract, document or package a video's style, make a recipe, template or skill from a video, or "make more videos like these".

Writes and times scripts for short vertical video and long YouTube videos. Structures the hook, the promise, the beats with open loops, the payoff and the loop back, writes for the ear in the creator's voice, then times it and flags a hook that runs long, beats that sit still, filler runs, an early call to action and a missing loop. Use when someone needs a script, a talking-points outline, a voiceover, a faceless video, or asks "how long will this run" or "why do people leave my videos".

Transcreve vídeo ou áudio (mp4, mov, mkv, mp3, wav, m4a etc.) com Whisper, rodando localmente no computador ou pela API gratuita da Groq, e entrega texto corrido (.txt), legenda (.srt) e um .md com timestamps. Use quando o usuário pedir para transcrever, legendar, tirar o texto ou decupar um vídeo ou áudio.

Use when the user wants a video/clip (giới thiệu, hướng dẫn, explainer, walkthrough) built from a website or interactive web page, with an AI voice host and on-screen effects synced to the narration — e.g. "làm clip giới thiệu hệ thống", "dựng video từ trang web", "clip có giọng đọc AI", "/web2clip". Also when resuming any phase: setup, kịch bản, giọng đọc, quay hình, ghép clip tổng.

Guía maestra del usuario para producción visual y motion design en CUALQUIER proyecto — MOTION.md como constitución visual por proyecto, brief y storyboard antes de animar, la música como reloj editorial, motion determinista y editable (HyperFrames para piezas de video, After Effects por MCP solo si hay .aep), y el ciclo de QA de frames y render. Usar antes de diseñar, animar, generar, editar o renderizar cualquier pieza visual o de movimiento (videos de producto, demos, lanzamientos, reels, animaciones de interfaz, videos de ayuda), al preparar un repositorio como "MOTION-READY", o cuando el usuario mencione MOTION.md, HyperFrames, motion design o After Effects.

Producir un corto animado completo (historia, personajes, cámara, partículas, voz en español, lip-sync, música, mezcla) 100 % con código usando Remotion y herramientas locales, sin APIs de pago.

Agent-directed, music-reactive VFX clips from an FX score. WebGL2 shader templates (psychedelic, spectrum, scope, impact, light, glitch, neo-brutalist collage and lattice), optional Blender background plates, a flash audit on every render, silent ping-pong loops, and a web export for live use in apps and sites. Use when someone asks for a VFX clip, a visualizer, a festival or stage loop, a music-reactive background, or a live shader effect for a web page.

Rebuild any video, or its style, as an editable video project. Measure the reference (cuts, shots, camera, captions, sound), write a beat map, build it (HyperFrames by default), then check the render against the reference frame by frame. Use when asked to replicate, recreate, copy, clone or match a video, or to make one "like this".

Turn a one-line topic into a finished, voiced, captioned, animated vertical reel (1080x1920 MP4) with reelkit. Use when the user asks to make a reel, short, TikTok, explainer video, or animated video about something, or gives feedback on a reel ("make the hook punchier", "slow down scene 3").

Use when setting up scheduled publishing of an app's marketing content to Instagram (Reels, carousels, Stories), Threads, X and TikTok through official APIs - self-hosting Postiz in Docker behind a Cloudflare Tunnel, creating the Meta app with the newer use-case flow (business portfolio, Facebook Page linked to the Instagram professional account, Threads tester invite), X developer pay-per-use credits and spend cap, TikTok and YouTube audit limits, safe OAuth account selection when one browser holds personal and brand accounts, resource limits, and phasing a posting calendar around real launch events.

Art direction, real assets and a visual check for 3D websites made with three.js, React Three Fiber or WebGL, such as immersive scroll-driven sites, portfolios, product launches, brand and place stories, and 3D heroes. A script deals a researched direction (mood, light, palette, type, finish, a shot per scene), so builds don't converge on the generated look (glowing orb, starfield, dotted globe, grey object in a void, the same safe layout everywhere). A starter brings an award-grade pipeline (HDRI light, ambient occlusion, bloom, tone mapping, smooth scroll, text reveals, intro, site chrome), and a second script fetches CC0 models, textures and HDRIs for the world around the subject. The skill renders the site at desktop and phone sizes, films the scroll, checks usability, and fixes what's broken. Use when building or redesigning any 3D or WebGL website, section or hero.

Create short-form promo videos with Monclers from any AI agent. Use when the user wants to find viral or trending TikTok/short-form videos, track competitors (TikTok Spy), import and analyze reference videos, write or remix hooks and scripts, keep Brand memory, generate Hook + Demo, Text on Screen or Talking Head (AI avatar) videos, batch-render videos with presets, edit in the Monclers video editor, or download finished videos — or when they mention Monclers, UGC videos, video hooks, or remixing a viral video for their product.

Conductor for growing a channel on Instagram, YouTube, TikTok, Facebook, LinkedIn, X or Threads. Use when someone wants to start, grow, fix or plan social content, asks what to post or where to post, wants a content strategy, calendar or weekly routine, or mentions views, followers, reach, Reels, Shorts, carousels or building a creator business. First asks what they want to make, for whom and where, recommends a hub platform and spokes sized to their real weekly hours, then runs playbooks that chain the sr-* skills with approval gates. It writes and plans. It never posts.

把任意选题做成「图片在讲故事」的竖屏短视频——生成式线稿逐笔描出 + 代码叠台词气泡 + 单口配音 + 大字幕。声音是主线：念白本身必须是一条听得懂的故事。适用于漫画风格解说、历史与知识类短视频、贱萌吐槽向科普，或用户要求「像混子哥那样讲」「图片讲故事」「漫画分镜视频」时。触发词：漫画讲故事、混子哥风格、图片讲故事、漫画分镜视频、贱萌科普、历史短视频、comic storytelling、mixige。

Plan and generate short product and e-commerce videos with Makernice, such as product showcases, ad clips and marketplace listing videos. Covers choosing a mode, writing the prompt, picking aspect ratio and resolution, checking the price and running the job.

Turn someone's GitHub year into a short, postable year-in-review video (4:5, about 45 s, made for LinkedIn) using HyperFrames. Use when someone says "/github-year-in-review", "/year-in-review", "make my GitHub wrapped", "my year in code", "GitHub recap video", or wants to share what they shipped this year. Pulls real data with the gh CLI; no screenshots or uploads.

Edit videos and create polished reels, shorts, tutorials, podcasts, explainers, motion graphics and multi-platform exports using local editing tools.

Design, create, edit, or review static social media visuals, including quote posts, carousels, covers, thumbnails, and coordinated post sets. Use for visual direction, typography, composition, and adapting approved designs across social formats. Video production belongs to video-editor; copy and calendars belong to social-content; project research and channel strategy belong to social-marketer when available.

Create, edit, or review videos, including reels, animated quotes, visual explainers, talking-head edits with B-roll, and audio-to-video or long-form projects. Own visual direction, story structure, pacing, captions, sound, animation, and verified exports. Also use for video production pipelines and timecoded edit feedback. Static posts and carousels belong to social-designer when available.

Generate professional Seedance video storyboard prompts (10-second segments) for AI short dramas, 剧情视频, and commercial video generation. This skill should be used when: (1) user provides novel text, script, chapter content, or plot material and asks to split into storyboard shots; (2) user requests "分镜", "分镜提示词", "导演指令", "Seedance分镜", "拆镜头", "写镜头脚本"; (3) user needs to generate video prompts for Seedance / Minimax H3 / Runway / Kling etc. with precise camera language; (4) user is making AI短剧, 甜宠短