Image & Video

Final-stage assembly skill that lays narration audio over the source video, ducks the original sound, generates and burns subtitles, and normalizes loudness into a finished recap.

Executes an agent-authored clip plan: validates clip_plan.json, snaps cut boundaries safely, and concatenates the selected ranges into edited_source.mp4.

Builds 2–5 minute, 16:9, voiceover-free knowledge films where one line of subtitle is literally acted out on screen, rendered frame-by-frame with Canvas + Playwright + ffmpeg.

Turns a timestamped narration.json into per-segment TTS audio that fits each time window, plus placement metadata for downstream mixing.

Turns an already-analyzed video into a director-level story plan, A/V board, and timestamped narration JSON — then validates it before TTS.

Turns one knowledge point into a narrated 45-second-to-5-minute short film with sourced facts, styled visuals, BGM, and OCR quality control.

Turns a single topic into a full lesson-video series — research, narration, TTS, scene choreography, 1080p rendering and publishing — through one scripted pipeline.

A local ffmpeg skill that composites a generated creator track over a product layer beat by beat for split-screen and creator-over-product ad reels.

Transcribes your raw footage, cuts retakes and dead air, and builds a finished first-pass timeline inside your open DaVinci Resolve project.

Final-stage video mixing skill that lays narration over source footage, ducks the original audio, burns subtitles, and loudness-normalizes the delivered recap.

Generate, review and retake short GIF shots, then assemble them into a short MP4 film via a public CLI.

Generates a complete 30-40s vertical "A vs B" explainer video project with Vietnamese TTS voiceover and audio-accurate caption timing.

Generates a complete 30-40s vertical "A vs B" comparison video project with fixed 3-zone layout and Vietnamese TTS voiceover.

A 9-step pipeline that pulls a Zoom recording, adds intro/outro, builds timecodes and a thumbnail, uploads to YouTube, and files it in a playlist.

Turns a single baseline character image into an identity-locked, transparent 14-frame game animation sequence.