Turn a winning video ad into a structured set of new concepts and hook variations. The workflow creates or swaps video and voice clips, rebuilds captions, and prepares filenames and a testing plan for Meta or TikTok campaigns.
Turns one winning video ad into 20 ad variants that Meta's Andromeda and TikTok treat as different creatives: tag the winner with varg video_analyze, plan two layers (about 7 new concepts that each change message, visual execution or format, plus about 13 single-variable iterations, mostly new hooks), generate the new openers and concepts on varg (Seedance 2.5, Kling 4, Nano Banana, ElevenLabs), swap hooks onto the winner with a tested FFmpeg script (word-boundary cut, normalised parts, 20 ms fade, manifest), re-caption every variant, and export names and a test plan. Use when a seller asks for ad variations, more creatives, hook variants, "scale my winning ad", "make 20 versions of this ad", creative testing volume for Meta or TikTok, or new hooks for an ad that is fatiguing. Not for the testing strategy alone (ad-creative-testing), finding winners from competitors (varg-ad-library-remix), or a brand-new single ad.
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
Since Meta's Andromeda update, ads that look alike are grouped and compete as one ("Entity ID" in agency talk): a new caption, colour or music track is not a new creative. Sellers now test 20–40 creatives a week at about $20/day each and refresh every 2–3 weeks (theoptimizer, segwise). The "suppressed above 60% similarity" thresholds are repeated by agencies but not published by Meta.
video_analyze on the winner (about 5 credits; prompt in varg-ad-library-remix) → hook, angle, format, emotional driver, persona, proof, CTA. You scale the mechanism behind the ad, not the file.
Layer A, ~7 new concepts. Each must pass the three-question check (two "no" answers = the same Entity): Is the message different? Is the visual execution different, not just the text? Is the format different? Moves: same script with a new persona (female → male → couple → parent), same structure with a new script, same concept in a new format (UGC → unboxing → demo → mascot song → problem/solution), same script with new b-roll.
Layer B, ~13 iterations, one variable each. Mostly new hooks (3–5 per concept, ≤3 s), then new CTAs or offers. If two fields change between variants, the plan is wrong (Pixis).
Write the plan as JSON before generating; name every file {angle}_{offer}_{product}_{format}_{hook}_v{n}, e.g. safety_fullprice_gloves_tutorial_povmandoline_v1, with a closed list of 8–10 angles.
varg-product-hook archetypes, varg-unboxing-video) plus its spoken line on eleven_v4 in the same voice as the winner (1 credit per line).ai-ugc-ad-video, varg-mascot-jingle-ad, varg-dropship-reel …).POST /v2/estimate / estimate_cost.Keep a clean master of the winner without burned captions. Find the cut: the first word of the body in its word timings (Whisper, or hook from varg-dropship-reel's guide-edl.mjs). Then:
node scripts/hook-swap.mjs --body master_clean.mp4 --cut 7.34 --out variants/ \
clips/mandoline.mp4+lines/pov-mandoline.mp3 \
clips/knife.mp4+lines/knife-test.mp3
Each hook is a clip, or clip+line.mp3 to lay a new spoken line over it (the hook lasts as long as the line + 0.3 s). Every part is normalised to 1080×1920 / 30 fps / 48 kHz before the join, with a 20 ms fade at the cut (no click), and variants/manifest.json records hook, line, cut and lengths. Then re-caption each variant: transcribe it, captions.mjs, burn with ffmpeg (libass).
ABO, one creative per ad set, broad targeting, $20–50/day per ad set; kill under 1% CTR or at $10–30 spent without a result; judge after 7–14 days and 1,000+ impressions; move winners to CBO/Advantage+; refresh every 2 weeks. On TikTok, post hook variants as separate ads, not as duplicates of one post (duplicates get buried).
2026-10-28 on the cut-resistant gloves reel (59 s). Two new spoken hooks on eleven_v4 (1 credit each) over the reel's own clips, swapped in with hook-swap.mjs in seconds, then re-captioned:
Both cut cleanly into "They can be purchased for…" with no click or jump. These are Layer B iterations; Layer A concepts need new footage.
ad-creative-testing (why an ad won, the test plan), varg-ad-library-remix (new angles from competitors), varg-product-hook and varg-unboxing-video (new openers), varg-dropship-reel (captions.mjs, guide-edl.mjs), ai-ad-compliance-check.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Plan worthwhile local tasks by checking dependencies, effects, resources, and platform boundaries, then execute the exact approved plan. It can use safe parallel work or suitable Apple-silicon backends when the project exposes them.
Turn a winning TikTok or Meta ad into a structured creative test plan. Identify what made it work, plan distinct concepts, set test budgets and review timing, and use funnel metrics to decide whether to stop, iterate, or scale each ad.
Record deferred engineering decisions and temporary workarounds in a debt registry, with context such as effort, ongoing cost, affected area, and payoff trigger. Entries receive short labels so they can be reviewed or dropped later.
Generate or compare AI agent code for LangChain, EINO, AutoGen, AgentScope, and CrewAI using framework-specific templates, API mappings, conventions, and project structures. Reference files include verification dates to help identify potentially outdated guidance.
Investigate a reproducible bug, test failure, or unexpected page behavior, then make a narrowly scoped fix. The workflow calls for a regression test before changing code, verifies the fix, and reports remaining risks and evidence while avoiding unrelated refactoring or feature work.
Build an AI agent project through six collaborative stages, from requirements and architecture to tools, prompts, code generation, and verification. Start framework-independent, then generate a runnable project for frameworks such as LangChain, EINO, AutoGen, AgentScope, or CrewAI.