동영상·이미지·음성 스킬

Plan video production and combine tools for footage search, capture, generation, audio, analysis, and captions. Select tools for each task based on quality, budget, available credentials, and offline needs, with guidance for source rights and review.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Turning a video concept into a script and storyboard
• Finding footage and music while recording usage rights
• Planning narration, music, and sound effects

Create and edit Shotcut video projects through commands. Arrange and trim clips, adjust audio, add effects and transitions, then export a video. Preview files let agents review cuts, pacing, and visual changes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Arrange clips at specified times
• Lower background audio during selected sections
• Add transitions and picture-in-picture

Build and edit OBS Studio scene collections from the command line. Arrange visual sources, adjust filters and audio, configure transitions and output settings, and save the setup as JSON with undo and redo support.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create or duplicate streaming scenes
• Adjust source positions and cropping
• Configure audio volume and mute settings

Turn video speech into subtitles, refine and translate the text, and embed subtitles in the video. Review tools compare subtitles with an approved script and generate a preview frame before final export.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Transcribe speech from a video into subtitles
• Translate subtitles for another language audience
• Export a video with embedded subtitles

Compress screen recordings on Apple Silicon Macs using dedicated video hardware. Choose quality settings for sharing or archiving, inspect video properties, and check the resulting file size and storage savings.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Shrink screen recordings for chat or email
• Keep text legible in shared tutorial recordings
• Choose higher quality for archived recordings

Create and edit images from the command line using Pillow, an image processing library. Combine layers, add text and rectangles, resize or crop images, apply filters, and export compositions while saving editable project state.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Combine images and text into a poster
• Resize or crop an image
• Adjust layer opacity and filters

Prepare OBS Studio scene collections through commands. Add scenes and sources, adjust layout and audio, configure transitions and output settings, and save the project as JSON with undo and redo support.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create and duplicate scenes for a broadcast
• Adjust source position, size, and cropping
• Set audio volume, mute, and monitoring

Build Blender 3D scenes through text commands, adjusting objects, materials, lights, cameras, and animation keyframes. Render the scene or generate preview images to check its appearance, with scene state saved in JSON for later editing.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build a 3D scene from basic shapes
• Adjust materials, lighting, and camera settings
• Set animation keyframes and frame ranges

Manage ComfyUI image generation from the command line. Validate workflows, which define generation steps, submit them for execution, monitor queued jobs, inspect available models, and download images from completed runs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Validating and submitting image generation workflows
• Checking or interrupting queued generation jobs
• Listing available models and node types

Build video edits through commands: import media, arrange and trim clips, and add effects or transitions. Save project state as JSON and generate Kdenlive/MLT XML, with undo and redo support during editing.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Arrange imported clips across timeline tracks
• Trim and split clips at specified points
• Configure effects and transitions

Compress screen recordings on Apple Silicon Macs using dedicated HEVC video encoding hardware. Choose quality presets for sharing or archiving, inspect source files, and review file size savings through command output.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Shrink screen recordings for chat or email
• Compress tutorial recordings while preserving visual quality
• Reduce recording sizes for archiving

Automate Krita image workflows through commands for project setup, layer management, filters, canvas resizing, and export. Use it for repeatable editing tasks, batch image processing, and structured results that AI agents can read.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Prepare layer structures for illustrations
• Adjust layer opacity, visibility, and blending modes
• Apply image filters and resize the canvas

Build and edit audio projects through an Audacity command-line interface: arrange and trim clips, adjust tracks, configure effects, add labels, and render audio files while retaining project state and undo history.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Trim, split, and arrange audio clips
• Adjust track volume, pan, mute, and solo
• Configure effects and add timeline labels

Inspect and edit Live2D Cubism model files from the command line. Check referenced assets, adjust motion and expression settings, compare versions, process multiple models, and prepare model files for distribution without opening Live2D Editor.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check for missing assets and unused files
• Adjust motion fade times across multiple models
• Compare model versions

Edit screen recordings from the command line with zoom effects, speed changes, cuts, cropping, and text annotations. Adjust backgrounds and framing, review rendered previews, and export the finished video as MP4 or GIF.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create a demo video from a screen recording
• Zoom in on important steps
• Cut or speed up waiting time

Process musical scores through MuseScore 4 from the command line. Transpose music, extract individual parts, add or remove instruments, inspect score differences, and export sheet music, audio, MIDI, MusicXML, or Braille files.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Transpose a score to another key or pitch
• Extract individual parts from a full score
• Export scores as PDF, audio, or MIDI

Generate photos, illustrations, logos, and presentation visuals through the OpenRouter Image API. Edit or combine reference images, choose among supported models, and check available settings such as resolution, output format, and transparency before generation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating illustrations and visuals for slides or posters
• Editing colors or styles in existing images
• Combining multiple reference images

Generate images from written instructions and edit saved or uploaded images using them as references. Continue refining the latest image in a conversation, adjusting details such as brightness, background, or colors while specifying what to preserve.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating an image from a written description
• Editing an uploaded image
• Refining the latest generated image

Turns casual selfies into professional headshots using the paid Beatra service. Supports portraits with changed backgrounds, business attire, and studio lighting for resumes, company websites, career profiles, and social media.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create a headshot for a resume
• Prepare a portrait for a company website
• Update a career profile photo

Use Azure's Python transcription client to turn audio files into text and review timestamped results. Covers authentication, installed SDK options, and error handling, while clarifying when streaming or asynchronous batch work needs a different Speech API.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Transcribe a local recording with consent
• Review timestamped transcription output
• Check authentication and installed SDK options

Turn audio or video recordings into Markdown documents with transcripts and summaries. Use it for meeting notes, speaker identification, subtitle files, or batch transcription when several recordings need to become readable documentation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create meeting notes from recordings
• Summarize long lectures or talks
• Identify speakers in recorded conversations

Generate images and videos through Atlas Cloud by checking each model’s input requirements before submission. Guides the agent through sending a request, checking progress within a time limit, and downloading and validating the resulting media.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Generate an image from a text prompt with Atlas Cloud
• Generate a short video from a scene description
• Check model-specific inputs before submitting a request

Turn article ideas into hand-drawn, 16:9 illustrations featuring Grav, a floating character. Plan image placement and visual metaphors, then generate white-background sketches with sparse English labels and review their consistency.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Plan illustrations for a blog post
• Explain an abstract concept through a visual metaphor
• Keep illustration styles consistent across articles

Create multilingual voice-over audio from scripts supplied for each language using the paid Beatra service. Guides voice selection for each market, pronunciation and timing pilots, and delivery organized by language and segment for review.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Produce voice-overs from scripts prepared for each language
• Choose voices suited to each target market
• Review pronunciation and timing with pilot audio