동영상·이미지·음성 스킬

Generate and edit transparent PNG ornaments, game sprites, emblems, and interface graphics with built-in Codex image generation. Includes transparency checks, saved prompts, and optional integration into an existing project with verified asset copies.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create transparent PNG decorations for game interfaces
• Generate standalone sprites and emblems
• Check PNG transparency and gaps within artwork

Extract timestamped text from a YouTube video's transcript panel and turn it into summaries, chapter outlines, X threads, blog articles, or notable quotes. Use existing captions to create readable material from video content.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing a video's main points through a summary
• Creating timestamped chapter outlines
• Turning video content into a blog article or X thread

Extract a YouTube video’s full transcript and metadata, meaning details such as its title, channel, and like count, through the BrowserAct API. Use the results as source material for summaries, content research, or knowledge bases.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Collecting transcripts as source material for video summaries
• Gathering video text for content research
• Adding video transcripts to an internal knowledge base

Extract details from TikTok video URLs, including captions, author profiles, view and engagement counts, music, and hashtags. Process individual posts or a list of URLs, with image links available for slideshow posts.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check views and likes for a specific video
• Archive TikTok post metadata
• Collect details from multiple video URLs

Inspect images and videos you generated or edited for AI watermarks and embedded origin information, then remove selected signals. The skill guides a command-line tool and reports completed operations without treating missing signals as proof of human authorship.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Inspecting files for AI origin signals
• Removing visible AI labels from your own media
• Removing embedded AI metadata

Generate images, edit reference images, or redraw selected areas using GPT Image 2 or 2.5 through a packaged command-line tool. Resolve the model, image size, and quality settings, with reference examples available to guide the request.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating posters and images with text
• Editing an existing image using references
• Redrawing a selected area with a mask

Create HTML stories where page progress controls a continuous camera journey. The workflow covers research, chapter planning, consistent AI images, Seedance scene and transition clips, interface design, media preparation, and browser checks.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create an immersive journey through connected scenes
• Present a timeline as a continuous camera journey
• Build a visual product story

Find how to retrieve audio and video metadata with Mediabunny, a library for handling media in the browser. The skill points to focused guides for audio duration, video duration, and video width and height.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding an audio file's duration in seconds
• Finding a video file's duration in seconds
• Checking a video file's width and height

Guide an agent to the right Remotion instructions for creating videos, adding captions or maps, exporting files, and building applications. The workflow emphasizes checking an interactive preview as the video takes shape.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create a video while reviewing its preview
• Find guidance for captions and animated maps
• Export a finished video

Start a new Remotion video by setting up a project when needed and opening Studio before building scenes. Covers folder selection, React video structure, multiple scenes, and timelines with individually editable clips.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Set up a new Remotion video project
• Add a new video to an existing project
• Create a video with multiple scenes

Create and display captions for Remotion videos, with guidance for transcribing audio or video, importing SRT files, and animating captions. Keep caption text and timing in a shared JSON format.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Generate captions from video or audio
• Display and animate captions in a video
• Import existing SRT subtitles

Export Remotion compositions as videos or still images using command-line tools. Extract several selected frames as images in one call, with references for additional export options and videos with transparent backgrounds.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Export a finished Remotion video
• Save a still image from a composition
• Export multiple selected frames as PNG images

Structure Remotion code so elements can be selected and edited visually in Remotion Studio. Covers reusable scenes, editable text and styles, timeline organization, and keyframes, which define how properties change over time.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Make text, colors, and positions editable in Studio
• Edit scene and clip timing independently
• Adjust animation keyframes and easing

Launch Remotion Studio to preview a video in a browser while it is being created or edited. Keep the preview open to review changes, and choose browser behavior, server ports, or logging options.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preview a video early in production
• Review changes while editing
• Open Studio in an in-app browser

Choose a technique for adding maps to Remotion videos, from satellite images with animated overlays to globe views, geographic annotations, and terrain flythroughs. Compare approaches based on the intended shot and service requirements.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Animate overlays on a satellite image
• Show a globe or 3D buildings with Mapbox
• Use MapLibre without an API key

Build Remotion video scenes with animation, media, and visual effects. Follow React markup patterns that keep timing and individual elements editable in Studio, with guidance for reusable scenes and frame-based motion.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create a title fade-in
• Add an editable lower third over a video
• Organize multiple scenes into editable timelines

Extract one still image from a local video using FFmpeg. Choose the first frame, a timestamp, or a frame number, then save a JPG for sharing or a PNG for clear interface details.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Extract the first frame to inspect a video
• Save a still image from a specified timestamp
• Extract a frame by its exact frame number

Create a draft PeonPing notification sound pack with a consistent theme. It generates wordless effects or spoken lines for all seven notification categories, along with configuration files, then directs you to review and approve the draft.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating a notification pack with a consistent mood
• Drafting wordless notification effects
• Drafting spoken notifications with one voice

Regenerate sounds in a draft PeonPing pack based on feedback. This internal workflow revises sound prompts or speech text, preserves the pack's style and voice, renders replacement audio, and records each successful change.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Soften a sound based on review feedback
• Apply a correction across an entire sound pack
• Create a fresh variation of an existing sound

Create short films entirely in code, using styles such as oil painting or Ukiyo-e. The skill guides style selection and production, including science and product explainers built from real source materials.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create a short film in an oil painting or Ukiyo-e style
• Make science explainers using satellite imagery
• Explain product structures using CAD files

Plan where each character sits or stands at the start of an AI short drama scene. An interactive overhead layout lets you adjust positions and facing directions, export the data, and produce opening placement descriptions for storyboarding.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Plan seating and positions for ensemble scenes
• Adjust opening positions on an interactive layout
• Distinguish present characters from later arrivals

Turn an AI short drama script into timed segments and shots, with frame prompts and video prompts for MiniMax H3 and Seedance. Validate dialogue coverage and timing, then produce review reports, generation batches, and voice alignment lists.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Breaking a short drama script into timed shots
• Preparing MiniMax H3 or Seedance video prompts
• Checking dialogue coverage and shot duration

Generate character reference images from a short description, including full-body, face, side, and back views. Use one reference image to guide the set, regenerate individual views, and track versions and images that need updating.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create reference images for an original character
• Prepare character references for video models
• Regenerate a specific outfit detail

Analyze reference animations and create art animations or narrated explainer videos with code. The skill covers storyboards, visual styles, rendering, and quality checks, with optional workflows for recorded narration, generated voices, and character images.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Analyze motion and transitions in a reference animation
• Create an animation with a consistent artistic style
• Produce explainer clips timed to narration