Images, video, audio and generative media.
Generates or edits bitmap images such as photos, sprites and transparent cutouts.
Writes detailed prompts for the loaded image or video model.
Reveals a headline as leaves sweep across the frame, in a 12 second HyperFrames block.
Generates, reconstructs and checks 3D assets for OpenMontage worlds.
Routes to the right Remotion skill for building videos in React.
Make a verified presenter video from a script and an image.
Generates or edits images from text prompts for illustrations, icons, and posters.
Produces 3Blue1Brown-style math and technical animations with Manim.
Directs and produces videos from briefs and references using generated media.
Finds where an article needs visuals and generates matching illustrations.
Generates jingles, music beds, voiceovers and sound effects as one MP3 or WAV file.
Queries AIHOT live for recent Chinese AI news, model releases, and industry events.
Turns a project website into a short shareable launch video with Hyperframes.
Downloads a video, extracts frames and transcript, and answers questions about it.
Sets the rules for placing captions as an overlay on top of HyperFrames videos.
Generates background music, vocal tracks and stems for video with ACE-Step.
Transcribes, displays, and animates captions in Remotion videos.
Transcribes, translates, and burns styled subtitles into videos.
Creates cinematic product videos from real page captures with Remotion and sound design.
Generates original images, product visuals, and diagrams with the desktop image provider.
Adds speech-to-text dictation to a composer and transcribes recorded audio with Grok.
Runs the KrillinAI CLI for subtitles, dubbing, rendering, covers, and voices.
Plans and generates a stylized 3D animated short from story to final review.
Installs, configures and runs the Horizon news radar with profiles and daily digests.
Generates local speech, transcribes audio and runs dubbing through VoiceStudio's API.
Directs a short film made entirely in code in a named Lemo-Opuscar style.
Downloads WeChat official account articles as HTML, PDF, Word, Markdown or MHTML.
Plays, pauses, seeks and searches NetEase Music through the musicbox CLI.
Downloads videos from m3u8 streams, Bilibili and direct URLs with MediaGo.
Makes lip-synced avatar videos from a portrait and audio, then merges segments.
Turns a weekly changelog markdown file into a branded, captioned changelog video.
Calls a running Modly app from the terminal to make image-to-3D assets.
Writes and troubleshoots Seedance 2.0 video prompts across many surfaces.
Aligns audio stems with duration mismatch handling and pre-mix checks.
Creates a new Remotion video project.
Transcribes, cuts, grades and subtitles video by plain conversation.
Generates game images, 3D models, voices and sound effects locally or via APIs.
Summarizes posts from top AI builders on X and YouTube podcasts.
Creates educational comics with panel layouts and batch image generation.
Removes and identifies AI watermarks and provenance marks in images and video the user...
Creates storyboarded HTML motion films with synced sound and seekable playback.
Generates and edits images with GPT Image models, including posters and inpainting.
Breaks down and recreates animation styles, and renders narrated motion clips.
Removes visible Gemini watermarks from local images using the project CLI.
Turns SRT subtitles into hand-drawn whiteboard animation videos with a preview step.
Flips a tiled headline surface cell by cell to reveal the headline behind it.
Generates videos from text or a reference image using several video providers.
Writes prompts for Seedance 2.0 video generation using text, image and audio references.
