Claude Code: Video & Audio Production Skills

Overlays silent b-roll cutaway clips onto a finished base video — the base audio keeps running underneath while the picture cuts away and returns, and the final duration always equals the base duration. Use when the user asks to add b-roll, add cutaways, or overlay clips on a video: "add b-roll to this", "cut away to a product shot here", "overlay these clips on my UGC ad". Entered from an approved base video plus its transcript, which comes from POST /v1/transcripts and needs no local install; it never generates the base itself and it never extends a video.

Burn timed, styled captions into a finished video on the local machine, without re-rendering the source. This is the manual fallback to the API's captioning endpoint, POST /v1/captions, which stays the default path: come here when the style the user wants is outside the API's presets, when the wording has to be hand-corrected before it is burned into the pixels, or when the source was rendered with audio disabled and the API refuses it. Transcribes the audio with Whisper, groups words into reading phrases, renders the captions in a real browser via HyperFrames, and composites them over the source with ffmpeg using a real alpha channel. Use when the user has an MP4 with narration, dialogue or voiceover and asks to add captions, subtitles, burned-in text, TikTok-style captions or word-by-word text to it and the API path has been ruled out. Runs out of band, so it costs no credits and works on any video file whoever generated it. Not for generating video (use the video skills) and not for a separate .srt/.vtt sidecar file.

Generate one or more standalone Meta image-ad creatives via ChatGPT Image 2 (gpt-image-2) through the Novoads API. Locks the model, auto-strips platform chrome, enforces edge-safe layouts and glyph-safety inside body text. Use when the user asks for a "gpt-image-2 ad", "ChatGPT Image ad", "Image 2 ad creative", "make a static image ad with GPT", or anchors on a need for typography-heavy / dense-text / UI-mimicry ad creatives (chat threads, comparison tables, fake search results, iOS dialogs, Slack snapshots, ChatGPT-conversation ads, Apple Notes lists). Does NOT trigger on Nano Banana cues — use nano-banana-image-ad for those.

Clones a VIDEO ad end to end for a different product or offer, on the Novoads API. The deliverable is a finished rendered MP4 — the WHOLE ad, not its opening, and not a template. Reads the source's style, pacing, camera work, dialogue and tone, adapts it into a Seedance 2.0 prompt, prices it, renders it, files the source beside the clones and diffs each clip's transcript against the approved script. Use when asked to "clone this ad", "clone this video ad", "make this ad but for my product", "recreate this video for my brand", or when handed a video ad plus a product photo with a request for something similar. Two neighbours it is NOT: a STATIC IMAGE ad is image-ad-clone, and rebuilding only the first few seconds — where the hook ends and why it works — is a hook skill, not this one. If the source does not move, this is the wrong skill.

Generate high-CTR YouTube thumbnails using Nano Banana Pro via the Novoads API. Handles reference image upload, character likeness alignment, proven CTR-tested prompt formulas, and bounded batch generation. Use when the user asks to create a YouTube thumbnail, video thumbnail, A/B test thumbnail variations, or refers to thumbnail design with their face, brand assets, or product photos.

Clones a STATIC IMAGE ad into a reusable prompt TEMPLATE. The deliverable is a parameterized library entry — placeholders, variables and per-model notes, appended to the shared image-ad library — not a finished ad. Reads the frame structurally, round-trips the draft prompt through gpt-image-2, nano-banana-pro or reve-2.1 until it reproduces, then replaces every brand-specific with a {placeholder} and proves the generalized version still renders on a different brand. Use when asked to "clone this ad as a template", "reverse engineer this ad", "turn this ad into a prompt", "extract a template", "make this ad reusable", "add this to my prompt library", or "study this ad and make a template". Two neighbours it is NOT: generating a finished image ad from a brief or an existing template is chatgpt-image-ad or nano-banana-image-ad, and cloning a VIDEO ad is clone-ad. If the source is a still and the user wants one finished picture rather than something reusable, they do not want this skill.

Publish finished creatives as live Meta (Facebook/Instagram) ads via the Meta Marketing API, plus research and ad-copy support. Uploads an image or video, builds a multi-variant creative (5 bodies / 5 titles / 3 descriptions in an asset feed), and creates a PAUSED ad in an existing ad set. Also pulls top-performing ads (ranked by ROAS) and competitor ads from the Ad Library to inform copy. Use when the user asks to deploy / publish / launch a creative as a Meta or Facebook ad, build a Meta ad, push a video or image into an ad set, pull their top ads, or research competitor ads. Not for generating creative (use the image/video skills) and not for writing AdTable/Airtable rows (use adtable-light).

Lays a music bed under a finished video — the music is trimmed and faded to the video's exact length and ducks beneath the voice, while the video stream is copied untouched. Use when the user asks to add music, add a background track, add a music bed or soundtrack, or asks for something like "make a lofi mix of this": "put music under this ad", "add a background track", "give me a couple of music versions". Entered from a finished cut — captions already burned is the preferred input, not a problem. It never edits the picture and never changes the video's length.

Generate one or more standalone Meta image-ad creatives via Nano Banana Pro through the Novoads API. Locks the model, auto-strips platform chrome, enforces edge-safe layouts. Use when the user asks for a "Nano Banana ad", "Gemini image ad", "nano-banana-pro ad creative", "make a static image ad with Gemini", or anchors on a need for photoreal / lifestyle / multi-reference / handheld-object / clay-texture ad creatives (sticky-note flatlays, held-whiteboard signs, lifestyle portraits, ingredient collages, OOH photography). Does NOT trigger on ChatGPT Image cues — use chatgpt-image-ad for those.

Generate AI video ads and image ads through the Novoads REST API (api.novoads.ai). Use when the user wants a UGC video, a product video, a talking-head ad, an AI actor holding a product, a TikTok or Reels or Shorts ad, a static image ad, or asks to "make me an ad", "generate a video", "animate this photo", or names a model (Seedance, Seedance 2.5, Seedance Mini, Omni Flash, Veo 3.1, Sora 2, GPT Image 2, Nano Banana Pro, Reve). Handles upload, dialogue approval, cost confirmation, generation, polling, QA, and download. Not for editing an existing video file and not for publishing to an ad platform.

Builds a hand-sculpted stop-motion CLAY ad on the Novoads REST API as a STORYBOARD: five to eight beats, each rendered from its own key frame, a storyteller narration laid into the gaps, a music bed, captions burned on, assembled locally with ffmpeg. Carries the genre's arc (named protagonist, inciting moment, social beat, quiet despair, sculpted clay infographic, discovery, transformation, resolution card), and also recreates a found clay ad by reading the reference video locally with ffmpeg and Whisper. Use for ANY clay or stop-motion ask at ANY length: "claymation ad", "stop-motion ad", "clay ad", "a quick clay ad", "plasticine characters", "make an ad like this clay one", or a reference video with sculpted clay characters in it. There is no one-call tier here, so ffmpeg is required. Not for the smooth 3D animated look (use novoads-pixar-ad, which covers every Pixar-style length), talking-head UGC (novoads-api), or a static image ad.

Builds a stylized 3D animated ad on the Novoads REST API as a STORYBOARD: four to six beats, each rendered from its own key frame, narration laid into the gaps, a music bed, captions burned on, assembled locally with ffmpeg. Carries the genre's beat formulas (anthropomorphized problem character, protagonist reveal, mascot mechanism scene, composited end card) and produces a product read, cast sheet, beat board, per-beat still and clip, and the exact curl calls. Use for ANY Pixar-style, Disney-style, 3D animated or animated-film-look ad at ANY length: "Pixar style ad", "3D animated ad", "animated movie look", "cute 3D character ad", "a quick animated ad", "15 second animated ad", "30 second animated ad", "storyboard ad", "several scenes", "animated ad with a voice-over", "little mascots", or a product URL or photo for an emotional animated spot. No one-call tier, so ffmpeg is required. Not for stop-motion clay (use novoads-claymation-ad), talking-head UGC (novoads-api), video cloning, or static image ads.

Downloads a competitor's live ad creatives — the actual MP4s and JPEGs — from the Meta Ad Library into a local swipe folder, through the Novoads API. One sweep per competitor, priced by a live estimate before anything is charged, media pulled the moment the response lands because the CDN links expire, and every ad carried with its permanent Ad Library URL, the page running it, and how many audiences the creative is running against. Use when asked to spy on competitors, find what ads a brand is running, pull a competitor's video or static creatives, build or refresh a swipe file, check who is outspending you on Meta, or source a reference ad to recreate. It finds and files ads; it does not rebuild them — cloning a competitor VIDEO ad for your own product is clone-ad, and turning a static ad into a reusable parameterized template is image-ad-clone. It writes no analysis and no creative brief. A sweep that finds nothing is reported as a result, never apologised for.