Image & Video

Turns a frontend project or webpage into a cinematic product promo with Remotion, real page captures, 124 shot cards, beat sync and sound design.

A full production skill for making art-style and explainer animations in code — shot list, lint, per-shot render, QA, and a delivery gate that blocks weak films.

Turns audio or video into speaker-labeled, timestamped transcripts — locally with MLX/whisper.cpp on Apple Silicon or through a remote ASR endpoint.

A director-grade skill that builds launch films, explainers and motion graphics as editable HTML + GSAP code and renders them to MP4/GIF.

Turns textbook PDFs, stories and ideas into narrated SVG animated web books, documentaries, vertical shorts and explorable maps.

Generates stills, films, 3D motion graphics and web animations entirely in code across 32 styles, complete with composed scores, narration and subtitles.

Builds stills, animations and 3D motion graphics entirely in code across 32 styles, with composed scores, narration and subtitles.

Directs, builds and renders premium product launch films, UI walkthroughs and logo stings from code using Remotion or HyperFrames, with automated quality gates.

Turns AI-generated or existing video and frame sequences into scroll-, pointer-, drag- or audio-driven web animations, end to end.

Measures and dissects reference short dramas, extracts transferable craft mechanisms, and benchmarks your own plan or cut against them on the same ruler.

Assembles already-generated short-drama shots into a finished film by recording every cut decision in an edit sheet, then rendering with subtitles, sound and delivery specs.

A production rigging pipeline for Blender: Rigify metarig setup, robust skinning, weight rules, and engine-ready game skeletons.

Handles Blender 5.x keyframing, mocap retargeting, and baking/exporting game-ready animation clips.

An orchestrator that turns a raw video into a finished narrated recap by chaining video understanding, scripting, cutting, AI voiceover and assembly.

Executes an Agent's already-decided clip selections: validates the plan, snaps boundaries to sentence ends and the frame grid, and renders a single constant-frame-rate edited_source.mp4.

Builds 1–3 minute, 16:9 finance/tech explainer films in the 'Xiao Lin Shuo' visual language — from topic and script all the way to a mixed 1080p render.

Generates an AI creator speaking an approved script as multiple takes with one consistent face, room and voice, then joins them into a single continuous track.

Generate or edit images with any FAL image model, routed through the GooseWorks proxy so calls are billed to the Ads agent.

Generates WeChat Official Account cover images and in-article illustrations by matching the article's title and content to reusable style presets.

Breaks a finished video into measured cut rhythm, loudness and section structure, then exports a production_reference.json containing only reusable methods — no original names or dialogue.