Menu
Skills in this repository
SkillsMP has collected 169 skills from gooseworks-ai/gooseworks-ads-skills. Open a skill to review its source and details.
gooseworks-ai/gooseworks-ads-skillsShowing 9 of 169 collected skills.
Use when creating a programmatic, voiceless or VO-optional, full-bleed 9:16 paid-social motion ad from brand assets and a brief — produces a deterministic Hyperframes render, procedural audio bed, FFmpeg-muxed MP4, and review-frame QA. Stops before any…
Produce a 9:16 split-screen creator ad — a two-zone vertical layout with a product/demo clip on top (contain-fit, blurred-fill, no black bars) and an AI-creator talking head lip-synced to the voiceover on the bottom, joined by a thin brand divider, with…
Produce a UGC-style talking-head ad with an AI avatar reviewing 1-N products. NB2 generates the avatar portrait; Seedance 2.0 reference-to-video on FAL renders each per-product scene with native lip-synced dialogue. Per-product scenes are stitched with a hook…
create a ugc ad with talking-head footage and product clips.
Produce a premium, viral 9:16 "Goose vs [tool]" head-to-head for the @goose.ai.tools account, in the agency / done-for-you angle. A warm cream editorial canvas (Fraunces type, film grain, depth) with a BIG floating circular "Loom-bubble" of the real felt…
Produce a 4–6s vertical iOS lockscreen "notification avalanche" clip — N notification banners from one brand cascade onto the lockscreen, faster than the screen can hold them, with a procedural CSS-only tear/glitch overlay at the climax. Output is the…
re-edit an existing video (a pipeline output, a flat talking-head take, or any external clip) so it follows CREATOR_GRAMMAR.md — reorder hook-first, jump-cut the breaths, snap cuts to beats, restyle captions, add silence beats and SFX. This is the…
Produce a 9:16 fast-paced explainer video starring a felt-puppet mascot (default Goose) lip-synced in a creator-aesthetic apartment, with a clean two-zone overlay layout (big sample-or-text card on top, mascot PIP on bottom — never overlapping), per-tip pop…
Watch a video (URL or local path). Downloads with yt-dlp, extracts auto-scaled frames with ffmpeg, pulls the transcript from captions (or Whisper API fallback), and hands the result to Claude so it can answer questions about what's in the video.