gooseworks-ai/gooseworks-ads-skills - Page 3

toggle-pill-slide

motion-graphic primitive — UI segmented-control active state animates as a sliding pill between options. small UI-mock idiom that says "this is a real product, not a placeholder". used for "Annual / Monthly" toggles in pricing scenes and for any 2-3 option…

ui-panel-float-z

motion-graphic primitive — realistic UI mock card drifting on a fake Z-axis with subtle 3D tilt and parallax. signature sp-f product-demo mechanic. composes scale + tilt + shadow + blur-halo + continuous parallax drift. renderer = hyperframe-gsap preferred.

create-music-elevenlabs

create custom music beds with the elevenlabs music api — prompt, composition plan, or video-matched scoring.

find-music

find, generate, or select a music bed that fits a video brief and edit timing.

render-video-overlay-track

Render premium, reusable video overlay components from declarative JSON specs for social videos, ads, product videos, UI callouts, notifications, proof cards, charts, product screenshots, iMessages, stickers, and animated text overlays. Use when Codex needs…

analyze-reference-grammar

watch a reference or existing video, measure its creator-grammar profile (cut points, pacing curve, audio mode, speech transcript, beat grid), and classify it into one of the 8 editorial archetypes defined in CREATOR_GRAMMAR.md. Use when you need to…

create-motion-graphics-storyboard

build a frame-by-frame motion graphics storyboard as a single html page. each scene row specifies copy, on-screen text, animation primitive (pop-in, scale-bounce, kinetic-typography, camera-pan, slide, data-viz reveal), duration, easing, and music cue.…

create-shot-list

Produce a structured scene manifest (text-based, no images) for a multi-scene video ad. One row per scene with duration, script line, setting, wardrobe, framing, lighting, sub-beats, on-screen ratio, product refs, and continuity links. The pre-render approval…

create-storyboard-html

assemble <video_folder>/storyboard.html as the single review surface for a video project. Reads per-state JSON fragments from _state/ and templates them into one collated, browsable page with TOC + state sections.

create-video-implementation-workflow

create an exact scene-by-scene build workflow for a programmatic video, including tools, source assets, render steps, QA checks, and output paths.

generate-edit-decision-list

turn a creator-grammar archetype + script/transcript + scene table into a validated edl.json — the machine-readable timeline that render-edl executes. supports generative mode (clips to be created) and conform mode (recut of existing footage). use whenever…

create-product-images-higgsfield-ms

compatibility scaffold for higgsfield marketing studio product image generation; prefer create-product-images-higgsfield-marketing-studio.

create-product-images-higgsfield-product-photoshoot

create brand-faithful product stills using higgsfield product photoshoot workflows.

edit-image-nano-banana

edit images via fal-hosted nano banana / gemini 2.5 flash image — fast prompt-driven edits, multi-subject consistency, photorealism.

compare-with-reference-video

Side-by-side comparison of a target master video against a reference video that exemplifies the style you're aiming for. Extracts aligned frame samples from both, builds an HTML comparison grid, computes mechanical metrics (cuts/min, motion magnitude,…

review-video-for-ad-quality

review a video for ad quality: clarity, pacing, cta, captions, proof, and visual artifacts.

review-video-pacing-rhythm

Detect cut points (ffmpeg scene-detect) and music beats (librosa via the beat-sync-reel skill); flag cuts > 100 ms off the nearest beat and scenes > 4 s with no internal motion change. Emits a pacing-report.md with a waveform overlay PNG.

watch

Watch a rendered video (whole file or specific ranges) at a chosen fidelity and emit a timestamp-keyed observation report. Observation only — no edits, no verdicts.

source-brand-assets

scrape a company's visual brand assets (logos + hero/product reference photos) from the public web into a structured `brand-assets/` folder. Use when starting creative work for a new brand and you need real reference imagery before generating product photos,…

source-company-existing-ads

find and inventory a companys existing ads for downstream video analysis and planning.

split-audio-by-words

Slice a long-form audio file (podcast, interview, talk) into per-scene mp3 splits using Whisper word-level timestamps so cuts land on clean word boundaries, never mid-syllable. Accepts explicit timestamp markers OR auto-detects scene breaks from long pauses.…

create-ugc-heygen

generate a ugc talking-head video using heygen when credentials and provider details are available.

create-video-kling

create dialogue-heavy or multi-shot narrative video clips using kling 3.0 via the higgsfield mcp. use for talking-head scenes with multi-character lip-sync, character-driven story beats, and anime/stylized motion. cheapest of the frontier engines, supports…

create-video-seedance-2-fal

Generate a single 4-15s vertical video clip with ByteDance Seedance 2.0 reference-to-video via fal.ai. Multi-image reference (avatar + product + setting), native lip-synced VO + ambient audio via `generate_audio: true`, internal multi-cut handling within one…

create-video-seedance-fal

Generate a reference-driven video clip with ByteDance Seedance 2.0 via fal.ai's direct API. Use when you have 1-9 reference images (a locked character, a product still, a world plate) and you want the output clip to faithfully reproduce them inside a motion…

create-video-seedance

create reference-driven product video clips using bytedance seedance 2.0 via the higgsfield mcp. use for product demos with complex camera moves, multi-sku consistency, image+audio reference inputs, and clips up to 15s. tops the leaderboards on…

create-video-veo3

create cinematic product videos using google veo 3.1 via the higgsfield mcp. use as the default workhorse for ads, talking-head with native synced dialogue, vertical social, and any clip where prompt adherence and audio quality matter more than raw motion…

create-voiceover-elevenlabs

create elevenlabs voiceover audio with timing data and pronunciation checks.

format-script-to-style

transform an unformatted script (already in the calling agent's conversation context) into a v3-tagged script that matches an approved delivery style at a target duration. use when an agent has just brainstormed a script and needs to apply a specific…

generate-voiceover-elevenlabs-v3

generate a voiceover mp3 using ElevenLabs eleven_v3 TTS from a v3-tagged script, interactively confirming which approved voice from VOICES.md to use, then applying ffmpeg atempo post-process to hit the target duration (v3 ignores the speed voice_setting).

create-hybrid-ad

Produce a Hybrid H-CARD ad (Common Thread Co taxonomy): a 22-second 9:16 video where a motion layer (NB2-generated avatars, Pexels stock b-roll, HTML phone mockups, NB2 product composites) runs underneath kinetic typography banner cards animated word-by-word…

create-product-hypermotion-with-specs

Produce a Product Hypermotion + Kinetic Typography intercut ad (Common Thread Co "Product Specs" format × Higgsfield "Hyper Motion" treatment). Single Seedance i2v hypermotion clip cut into 5-6 segments, intercut with 5-7 PIL-rendered kinetic typography text…

create-value-prop-ad

Produce a Value Prop ad (Common Thread Co taxonomy): 3-5 short noun-phrase benefits revealed sequentially over per-SKU product visuals. Default 17s 9:16 vertical for Reels/Stories/TikTok/Meta. Autonomously scrapes value props from brand homepage + PDPs and…

create-vignette-ad

Produce a Vignette ad (Common Thread Co taxonomy): real-time kinetic background video (sourced from Pexels stock OR generated via T2V) composited with product cutouts, cold-open text card, and annotated end card. 9-12s, 1:1 or 9:16, music-led, no VO.…

build-brand-clip-library

build a reusable, indexed clip library from a brand's own videos — download N brand-owned videos, watch each, cut semantically-named clips, and write a searchable clip index. use when a brand has its own footage (launch films, product demos, explainers,…

research-new-brand

kickoff prep for a new brand — web research, existing-ad analysis, sourced + AI-generated brand assets, and an ad concept brief. use when starting work on a brand the repo hasn't touched before (e.g. `amex`, `klarify`, `ramp`). Emits the control-plane…

create-broll-narrative-essay

produce a 25-45s lyrical b-roll narrative essay — a VO-driven travel/lifestyle/brand essay over evocative b-roll, structured in two acts joined by a 0.25-0.6s structural-silence pivot. Use when you need a creator-native essay format that builds lyrical…

create-how-we-made-this-hook

Produce a 9:16 "proof-then-recipe" social hook reel — open on the most jaw-dropping seconds of a finished brand film (the flex), hard-cut on a record-scratch, then a felt-Goose mascot reveals the exact AI tool-stack that made it (the recipe) with fast cuts,…

create-pause-and-click-explainer

Produce a 9:16 short pause-and-annotate explainer over an existing live-action or AI-generated base clip. Overlays a Windows-style pixel cursor that flies in from off-screen and snaps to N (typically 2-6) product/scene elements, freezing the underlying clip…

create-vo-anchored-beat-video

Produce a VO-driven 9:16 / 1:1 / 16:9 shortform explainer video where every visual moment is snapped to a VO word boundary. Renders the voiceover first, extracts Whisper word-timestamps, decomposes the script into N "beats" (one HTML hyperframe per visual…