Assemble a narrated-UGC "stitch reply" ad from a config: one voiceover carries a verbatim testimonial while about 30 short clips (one creator across about 5 outfits and 3 settings, plus product B-roll) are trimmed to windows cut from the voiceover's word timings and joined. The voiceover sits over a ducked music bed, word-by-word captions run throughout, a landing-page scroll is animated from a screenshot, and the brand's real end card closes it (never AI-rendered text). Free, deterministic assembly using the shared stitch-videos-ffmpeg helper; the voiceover, creator stills and clips come from create-vo-elevenlabs, create-image-gpt-image-fal, create-image-fal and create-video-fal. Use for the narrated-ugc-wardrobe-stitch format.
Install gooseworks: https://gooseworks.ai/creative-agent/install.md # then, in Claude Code, Cursor, or Codex: /gooseworks use the render-narrated-ugc-wardrobe-stitch skill
Assemble a narrated-UGC "stitch reply" ad from a config: a fast-cut vertical testimonial where a single spoken VO carries a verbatim ~13-sentence testimonial over ONE creator across ~5 wardrobe changes in ~3 micro-worlds, interspersed with product B-roll (e.g. product macro, unboxing, a landing-page scroll), ~30 hard cuts on the VO cadence, closing on a brand end card. This capability is the FREE, deterministic assembly — trim-to-EDL, hard-concat, the VO+music mix, the word-by-word caption burn, the landing-page zoompan, and the end-card append.
scripts/config.example.json is one worked example (the fictional Sunnook "Don't buy Sunnook Tan Mousse" demo, ~37s
1080×1920 9:16, ~30 body cuts + a ~2s end card) — its creator, voice, hook, worlds and music are
that demo's answers, not defaults; scripts/PIPELINE.md maps every config block to
its source step and scripts/README.md documents the free assembly.
The creative calls are made upstream by the user (the recipe's choices) and arrive in the config;
this assembly never picks them.
character.descriptor / character.name. The demo used a
31-year-old curly-haired woman.vo.voice_id / vo.settings. The demo used an excited voice
matched to its creator.vo.hook_line / vo.script_md / vo.payoff_line. The
demo used a "Don't buy <brand>" reversal.worlds.briefs. The demo used bedroom / bathroom / balcony.audio_mix.music_brief. With "no music", skip the bed
and mix the VO alone.This is the FREE, deterministic assembly stage — it spends nothing. The paid inputs are
separate capabilities — the spoken VO (create-vo-elevenlabs) Whisper-aligned so the WORD
BOUNDARIES set the cut grid; one locked creator (create-image-gpt-image-fal anchor + ~5 wardrobe
edits chained off the anchor) + 3 world wides + per-cut start-frames (create-image-fal product
composites); and one Veo/Seedance i2v clip per cut (create-video-fal). Given the VO +
vo-final.words.json + edl.json + one clip per cut + a Playwright landing-page PNG + the brand
end-card PNG, render-narrated-ugc-wardrobe-stitch trims each clip to its EDL window, hard-concats
on the VO cadence, mixes the VO over the ducked bed, burns the word-by-word captions, appends the
end card → the master. Re-cuts reuse the existing VO / start-frames / clips and spend nothing.
The assembly runs on a shared helper. montage.py lives in the shared stitch-videos-ffmpeg
atom, which this package lists in requires_skills, so it installs alongside. After
gooseworks fetch render-narrated-ugc-wardrobe-stitch it is at
/tmp/gooseworks-scripts/stitch-videos-ffmpeg/scripts/montage.py. Write a montage.json from the
config (field mapping in scripts/README.md), then:
M=/tmp/gooseworks-scripts/stitch-videos-ffmpeg/scripts/montage.py
python3 $M edl --spec montage.json --out edits/edl.json # check every clip + window first
python3 $M run --spec montage.json --out edits/master-final.mp4 --workdir edits/workrun builds the EDL from the VO word boundaries (word_range), trims and hard-cuts every clip
with the filter_complex concat filter, renders the landing-page scroll as a zoom/pan over the PNG,
holds the end-card PNG, burns word-by-word captions (one word at a time in one colour, with
respell; no active-word highlight), mixes the VO over the
ducked bed, and masters to -14 LUFS. It writes edits/work/manifest.json. This package ships no
scripts of its own.
hook, feature,
reaction-insert, payoff-hold, b-roll-insert, landing-page); snap every cut window to the
word boundaries. The payoff line gets a HELD payoff-hold beat (~3× mean shot length).filter_complex concat, not the demuxer. Trim each clip to its EDL window and
hard-concat with filter_complex concat — the -f concat demuxer drops the audio when a
drawtext/scale step shaves a clip a few ms below its window. No dissolves.vo-final.words.json (VEED
Whisper preset, bold yellow), on every word; re-spell brand tokens Whisper mishears against the
locked script (Sunnook demo: "Sunnook" over "Sunook"; kept "I'ma" verbatim) — never edit the script to
match Whisper. Captions are suppressed over the end card. If VEED mis-captions a brand token,
hand-patch that sentence with local ASS karaoke.filter_complex concat, VO+music mix,
caption burn, landing-page zoompan, end-card append, loudnorm I=-14 → a 1080×1920 h264+aac
master as long as the VO plus the end card (~37 s in the demo). No paid calls, no keys.character.descriptor / character.name. The demo used avo.voice_id / vo.settings. The demo used an excited voicevo.hook_line / vo.script_md / vo.payoff_line. Theworlds.briefs. The demo used bedroom / bathroom / balcony.audio_mix.music_brief. With "no music", skip the bedResearch supported advertising promises from a specific buyer's context, current product facts, customer language and observed ads. Turn them into static, video or copy ideas; match video ideas to actual recipes and save a product-scoped angle bank for write-video-ad-script. Product-led discovery can use verified facts without reviews. Reference persistence and reach are observations, not proof of performance.
Analyze ad campaign performance data (Google, Meta, LinkedIn) to identify what's working, what's wasting budget, and specific cut/scale/test recommendations. Runs statistical analysis, funnel diagnostics, and multi-channel budget reallocation with specific dollar-amount shift recommendations and scenario modeling.
For paid lead-gen and participant-recruitment ads, replaces vanity CPA with true CAC per qualified lead by joining ad-platform data with downstream funnel events, surfaces tracking gaps, and classifies every creative into Scale / Keep / Investigate / Cut.