Agent skill · creative production · pika-labs
4k-vfx
Use when the user asks for 4k vfx or a task matching the examples below. Turn a plain video clip into a cinematic 4K AI-VFX shot. Give Claude a video and the change you want; it reads EVERY frame via local contact sheets and understands the audio, writes a Seedance-faithful prompt that locks your face, gestures, and camera move, then re-renders the same shot with the VFX baked in via Seedance 4K reference-to-video.
Why this skill is useful
Adds a detailed workflow for generating 4K VFX shots using Seedance, including frame extraction and prompt generation that the AI cannot infer on its own.
What it needs
Requires ffmpeg installed locally. About 10k tokens when loaded. Last updated 2026-07-20. 38 stars on the source repository.
What this skill does
4k-vfx Maps a video-to-video VFX move onto the Pika MCP's Seedance 4K reference-to-video. The user hands you a clip + the change they want; you read EVERY frame (locally extracted with ffmpeg and tiled into contact sheets) and understand the audio (speech + music + SFX + ambience), author a Seedance-faithful prompt that locks the original (face, gestures, camera move) and time-codes the change to the right beat, then re-render the same shot in 4K with the VFX baked in. One run produces one 4K clip for one requested change. How it works — why reading EVERY frame (and the audio) is the mechanism (do not skip the reading pass) Seedance treats the reference video as a motion/style anchor, NOT a pixel-locked base — it does not copy the input frame-for-frame, it re-generates the shot guided by your prompt. So fidelity comes from the PROMPT: the more exhaustively the prompt describes the original (subject identity, exact gestures, camera move, framing, lighting, palette, wardrobe) and the audio (dialogue + lip-sync, music/SFX beats), the more the 4K output reads as the same shot with the change layered on. Reading EVERY frame — not a sample — is how you build that exhaustive description: you locally extract all frames with ffmpeg, tile them 25-to-a-contact-sheet (5×5), and analyze every sheet so the prompt is built from the entire timeline rather than a handful of stills. Skip the read (or read only a sample) and the output drifts — a different face, a different camera move, a different room, a missed motion beat. The reading pass — all frames + the audio — IS the skill. Prerequisites pika MCP available, and local ffmpeg in the run environment (used to extract every frame and build the contact sheets). Two inputs from the user: (1) a video clip (a local file or a public URL) and (2) the VFX change they want made to it. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills pika-labs/4k-vfx