Video & Animation

Build ready-to-upload subtitle files (.srt) in Thai, English and Simplified Chinese (or any language set) for a YouTube Short, TikTok or Reel. Takes a script, a transcript with timestamps, or an existing SRT, translates line by line in natural spoken style, keeps the three files in perfect sync, wraps lines for a vertical 9:16 screen and runs a readability check. Use this whenever the user wants subtitles, captions, ซับ, ซับไตเติล, คำบรรยาย, 字幕, an .srt file, "translate my captions", "add English/Chinese subs", or is preparing a short video for viewers in more than one language — even if they only say "make subs for this clip".

Generate a branded YouTube thumbnail from a video title. Uses a reference photo of the creator, high-CTR thumbnail principles, and brand colours to produce a ready-to-generate image prompt for Gemini. Use this skill whenever the user says "thumbnail", "youtube thumbnail", "build me a thumbnail", or wants a video cover image before writing the script. The thumbnail-first workflow mirrors the graphic-first approach for LinkedIn: sells the video before anyone hears a word of the script.

Consult the private preferences shared by a human and their agent and find reusable animation, short-video, motion-design, charts, design and generative-art references on 1human before building a relevant visual task. Save useful sources, attribute remixes and contribute only within the owner's existing permissions. Use for 1human participation; skip unrelated coding tasks.

Edita videos crudos de Futuros Residentes / Doc Juanes (una persona hablando a cámara, guiones grabados) y los convierte en Reels verticales 9:16 dinámicos con Remotion. Corta claquetas, tomas falsas, repeticiones y silencios, limpia el audio, pone subtítulos palabra por palabra con énfasis de color que nunca tapan la cara, cambia de plano en cada corte y, si se pide, agrega fotos superpuestas (incluso rasgándose), emojis/stickers con efectos de sonido, destellos de luz en las transiciones y música libre de derechos. Funciona en Mac y en Windows. Úsalo siempre que alguien pase o mencione un video crudo, un "guion N", una grabación de Doc Juanes o Futuros Residentes, o pida editar, cortar, subtitular o dejar listo un video para Instagram/TikTok/Reels/Shorts, aunque no diga "Remotion" ni "skill".

Turn a long talk, panel, podcast or interview recording into vertical 9:16 reels with word-by-word build-up captions and Instagram-grid covers, in two caption styles. Also re-captions already-edited vertical videos, including iPhone HDR footage. Use when someone wants shorts, reels or clips cut from a long video, burned-in captions, or reel covers. Triggers include "cut clips from this", "make reels from this panel", "turn this into shorts", "caption this video", "make covers for these reels".

Consult the private preferences shared by a human and their agent and find reusable animation, short-video, motion-design, charts, design and generative-art references on 1human before building a relevant visual task. Save useful sources, attribute remixes and contribute only within the owner's existing permissions. Use for 1human participation; skip unrelated coding tasks.

>- 토킹헤드 릴스(세로 1080×1920) 편집. 촬영본 1개 + 화면녹화 B롤 → 무음·버벅임 공격적 컷 → 1.05배속 → 조선굴림체 흰 박스 자막(입술 아래) → B롤은 자막 아래 카드 → 리모션 애니메이션(줌 펀치·키워드 스티커·예시 작업물 상단 팝업·마지막 CTA 인포그래픽) → 효과음은 대사 주요 포인트에만. 트리거 예 — "릴스 편집해줘", "이 영상 릴스로 편집", "방금 찍은 거 편집해줘", "B롤 넣어서 편집해줘", "자막 넣고 무음 잘라줘".

Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.

Execute the implementation plan by processing and executing all tasks defined in tasks.md

Create or update the feature specification from a natural language feature description.

Edita reels verticales 9:16 a partir de tomas grabadas con el móvil (limpiar audio e imagen, transcribir, cortar silencios y repeticiones, subtitular, montar en CapCut y revisar volumen y zona segura) y aprende el estilo de edición del usuario a partir de sus reels terminados y de reels de referencia (cuenta fantasma). Úsala cuando el usuario diga "edita este reel", "monta el reel", "corta esta toma", "ponle subtítulos", "revisa el volumen", "quita de X a Y", "aprende de mis reels", "aprende cómo edito", "analiza esta cuenta", "cuenta fantasma", "quiero editar como este reel" o pase un vídeo .mp4 para editar.

Turn a GitHub repository, website, PDF, Word file, brief, or other readable product source into a short original motion video with source-checked text and numbers. Use when asked to make a cinematic project demo, product teaser, or animated explainer from source material.

Create or update the project constitution from interactive or provided principle inputs.

Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.

Generate a custom checklist for the current feature based on user requirements.

Burns word-by-word karaoke subtitles into an English-language video. Each word turns from white to green and briefly scales up as it is spoken. Optionally adds short inline Simplified Chinese glosses, in blue, for technical terms, hard words, phrasal verbs and idioms, pitched at Chinese learners around the CET-6 level (China's College English Test Band 6, upper-intermediate). Use when the user gives an English video file or URL (YouTube, X, or any site yt-dlp supports) and wants word-synced karaoke subtitles, highlighted captions, or English subtitles with Chinese glosses. Needs an Alibaba Cloud Model Studio (DashScope) API key; no storage bucket is needed.

Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.

当用户提供自媒体账号链接并要求‘账号分析’、账号内容盘点或完整账号诊断时，采集最近50条作品，统计主题占比与平均点赞，转写点赞前5条，并基于证据分析人设、受众、产品及卖点，保存到本地桌面。

把任何一份文稿（工程纪实、报告、论文、说明书、科普资料）变成一条 3:4 竖版 科普/宣传短视频（1080×1440，60–150 秒）。纯代码渲染：单文件 HTML 确定性时间轴 → Playwright 逐帧截图 → ffmpeg 编码合成。无需剪辑软件、无需 AI 视频生成 API、 全程本地零成本、逐帧可复现。适用于：已有文稿要做视频；数据叙事/知识科普短视频； 需要批量、可审计、可复现的视频生产；模型（任何编程能力强的 LLM）直接执行生产。

Record real product tasks, author directed product films with the existing motion kit, or edit the included HTML/SVG animation study through Taskfilm and HyperFrames. Use for feature lessons, motion promos and source-attributed OSS demos. Provider-generated media and repository sandbox builds are outside this alpha.

Turn a real web app into polished how-to / tutorial videos — Playwright records the actual UI with a visible cursor, then a Hyperframes edit adds an intro card, step captions (any language, Thai included), zoom + highlight ring on the control to press, click sounds, music and optional TTS narration, rendered to 1080p MP4. Use this whenever someone wants a tutorial video, how-to video, training video, onboarding video, walkthrough, user guide video or "วิดีโอสอนใช้งาน / คลิปสอน / วิดีโอแนะนำการใช้งานระบบ" of a website or web app, wants to replace live user training with downloadable videos, or wants to re-record such videos after the UI changed — even if they don't say "Playwright" or "Hyperframes".

한국어 모션그래픽 영상(쇼릴·홍보 영상·프로필 영상·티저·브랜드 필름·행사 홍보·제품 소개·교육 영상·메이킹 필름)을 기획 브리프부터 납품까지 만드는 스킬. 사용자에게 주제·분위기·길이(15초·30초·60초·100초·5분)·이미지 생성 여부·나레이션 여부를 물어 방향을 정한 뒤, 조사 → 원고 → ElevenLabs 나레이션(기본 Marcus 바리톤) → 음악·효과음 → codex-image 이미지 → HTML 모션 엔진 렌더 → 믹스 → 자동 검수까지 끝낸다. '쇼릴', '모션그래픽', '애니메이션 영상 만들어줘', '홍보 영상', '소개 영상', '인물 소개 영상', '1분 영상', 'N초 영상', '이력서용 쇼릴', '놀라운 모션 그래픽 디자이너', '전력을 다해요', '키네틱 타이포', '나레이션 넣은 영상', '티저 영상', '하네스가 어떻게 동작하는지 영상으로' 같은 요청이면 영상이라는 말이 없어도 이 스킬을 쓴다. 실사 촬영본 컷 편집, 파일 자르기·변환만 하는 작업, Sora·Veo 같은 생성형 비디오 모델 호출, 슬라이드·PDF만 만드는 작업은 범위가 아니다.

Mandatory entry point: read this first for any request to make, create, edit, animate, or render a video, animation, or motion graphic, including a promo, explainer, captioned clip, title card, overlay, slideshow or interactive deck, Remotion port, or any HyperFrames HTML composition. Also use it to inspect, diagnose, validate, preview, publish, or batch-render an existing HyperFrames project. Inputs may be a website URL, GitHub PR, Figma design or URL, text or brief, existing footage, or music. It resumes project state, captures intent when applicable, selects and installs the owning workflow, and routes domain capabilities. HyperFrames is the default output framework unless the user explicitly chooses another framework for the deliverable or asks only to record a browser session.

A short, design-led motion graphic where motion is the message — kinetic typography, stat count-up, chart/data-viz hit, logo sting / brand lockup, lower-third / callout / social overlay, animated map (highlight regions, connect places, zoom to a location), animated tweet / news-article / headline, webpage / UI animation (scroll, cursor, callouts), or fusing a real image's geometry into a chart. Usually under 10s (up to ~30s), no narration or live-action subject; renders to MP4 or transparent overlay. Longer / narrated / multi-scene → /general-video. Unclear → /hyperframes.