Back Office · office.temerarii.xyz
One asset, all the way in — composition, the wireframe + storyboard, the output format stack, and the template, all read from the SAME content-index record. The expected output matches what /media surfaces for this post.
post social-W33-Tue-2kind threadweek W33date 2026-08-18campaign thread · Tuepillar performancebeat Tueasset videoduration 61.4sground whitescenes 9

Checklist the per-video bar — engine/sim

86.6/100
plain languagevo coverageno dead airuniquenesscaption fitcompletenesscleanliness
quantitative quality · weights learn from your reviews (engine.sim.memory review social-W33-Tue-2 good|bad)
⚠ 3 flag(s) — not yet ship-ready: copy_genericdup_sequence_across_assetsdup_set_across_assets · see docs/strategy/VIDEO-CHECKLIST.md

Composition comp · template family · expected output

composition SceneReelfamily / template SignalFieldReel
9:16 Reelpending1:1 Squarepending16:9 Widepending9:16 4Kpending1:1 4Kpending16:9 4KpendingGIF (SMS)pending
render pending — silent master not yet on disk
expected output: 0/7 rendered — same matrix the /media preview surfaces for this asset.

Composition layer × scene 9 scenes · 61.4s · comp_id + rendered still + tier + the script

#Layer (comp_id · still · tier)BeatTimecodeMotionLogoAudioVO / on-screen / caption
1s1
matches intent
shared field
signature-3d		open0–7.3sspatial-parallaxicon·3d-extrude♪ bed_in
We are close to marketplace listings that answer a shopper's question right there, before they ever leave the page.
on-screen: Soon your listing answers buyers
expected on screen: white ground · dodeca hero in the shared Signal Field · Mensor leads · node-graph · spatial-parallax · icon·3d-extrude logo · caption bottom-left
spec (the prompt): comp_id shared Signal Fieldvisual node-graphshape dodecaground whitetreatment 3d-extrudemotion spatial-parallaxpower summoninstrument summon→Soon your listing answers buyers
2s2
matches intent
shared field
signature-3d		hook7.3–14.6skinetic-buildicon·wireframe♪ node_lock
Old way, you posted a flat listing, set a price, and waited for the algorithm to maybe notice you.
on-screen: The old way: list and wait
expected on screen: white ground · dodeca hero in the shared Signal Field · Mensor leads · mark · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id shared Signal Fieldvisual markshape dodecaground whitetreatment wireframemotion kinetic-buildpower laser-lockinstrument laser-trace→The old way: list and wait
3s3
matches intent
NumberedList
template		teach14.6–22.7skinetic-buildicon·wireframe♪ node_lock
Here is the move: pull your reviews through a model and find the exact words buyers use to describe the win.
on-screen: Mine reviews for the real words
expected on screen: white ground · a NumberedList panel over a dimmed Signal Field · Mensor leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id NumberedListvisual node-graphshape dodecaground whitetreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→Mine reviews for the real wordscurate items, nodes
4s4
matches intent
ComparisonTable
template		proof22.7–29.7sreceipts-counticon·wireframe♪ node_lock
Rewrite your title and bullets in those words, so the listing matches the search living in their head.
on-screen: Rewrite the listing in their words
expected on screen: white ground · a ComparisonTable panel over a dimmed Signal Field · Mensor leads · receipts · receipts-count · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id ComparisonTablevisual receiptsshape dodecaground whitetreatment wireframemotion receipts-countpower receiptsinstrument spotlight→Rewrite the listing in their wordscurate colA, colB, rows, statsLabels
5s5
matches intent
LogStream
template		diff29.7–36.3scrossfade-8ficon·wireframe♪ node_lock
A listing written in your words gets skimmed. One written in the buyer's words gets the click.
on-screen: Speak their words, win the click
expected on screen: white ground · a LogStream panel over a dimmed Signal Field · Mensor leads · code · crossfade-8f · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id LogStreamvisual codeshape dodecaground whitetreatment wireframemotion crossfade-8fpower morphinstrument morph→Speak their words, win the clickcurate codeLines, rows
6s6
matches intent
ChecklistCard
template		teach36.3–42.9skinetic-buildicon·wireframe♪ node_lock
Now add a question block built from the real questions people keep asking, answered plainly up front.
on-screen: Add a Q-and-A from real questions
expected on screen: white ground · a ChecklistCard panel over a dimmed Signal Field · Mensor leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id ChecklistCardvisual node-graphshape dodecaground whitetreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→Add a Q-and-A from real questionscurate items, nodes
7s7
matches intent
KpiGrid
template		proof42.9–49.199999999999996sreceipts-counticon·wireframe♪ node_lock
Answer the doubt before purchase and the return rate falls, because nobody bought the wrong thing.
on-screen: Doubts answered, returns drop
expected on screen: white ground · a KpiGrid panel over a dimmed Signal Field · Mensor leads · receipts · receipts-count · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id KpiGridvisual receiptsshape dodecaground whitetreatment wireframemotion receipts-countpower receiptsinstrument spotlight→Doubts answered, returns dropcurate kpis, statsLabels
8s8
matches intent
WireframeMock
template		step49.2–55.1skinetic-buildicon·wireframe♪ node_lock
Three steps: mine the reviews for real words, rewrite the listing, pre-answer the common doubts.
on-screen: Step: mine, rewrite, pre-answer
expected on screen: white ground · a WireframeMock panel over a dimmed Signal Field · Mensor leads · pipeline · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id WireframeMockvisual pipelineshape dodecaground whitetreatment wireframemotion kinetic-buildpower throwinstrument laser-trace→Step: mine, rewrite, pre-answercurate stages, steps
9s9
matches intent
shared field
signature-3d		resolve55.1–61.4scoalescenceicon·3d-extrude♪ bed_out
Stop waiting on the algorithm. Make the listing itself do the convincing, and the ranking follows.
on-screen: Let the listing do the selling
expected on screen: white ground · dodeca hero in the shared Signal Field · Mensor leads · coalescence · coalescence · icon·3d-extrude logo · caption bottom-left
spec (the prompt): comp_id shared Signal Fieldvisual coalescenceshape dodecaground whitetreatment 3d-extrudemotion coalescencepower coalescenceinstrument coalescence→Let the listing do the selling

Format stack 3 aspects · same scenes[], re-cropped

9:16
1080×1920
Stories · TikTok · YouTube Shorts · Reels
1:1
1080×1080
LinkedIn · Facebook · Instagram
16:9
1920×1080
X/Twitter · YouTube · LinkedIn video

Channels 9 destinations

LinkedInX/TwitterYouTubeInstagramFacebookThreadsTikTokPinterestBluesky

Social captions supplemental published copy · per channel (comp_id level)

tiktokSoon your marketplace listing answers buyers before they leave the page. (AI-assisted) The move: run your reviews through a model to find the EXACT words buyers use, rewrite your title and bullets in those words, then pre-answer common doubts. Returns drop when nobody buys the wrong thing.
instagramWrite the listing in the buyer's words, not yours. Mine reviews for the real language. Rewrite title and bullets. Pre-answer the common doubts. #marketplace #ecommerce #amazonseller #listings #conversion
linkedinWe're close to marketplace listings that answer a shopper's question right on the page, before they leave. The move: pull your reviews through a model and find the exact words buyers use to describe the win. Rewrite your title and bullets in those words, so the listing matches the search living in their head. Then add a question block built from the real questions people keep asking, answered plainly up front. A listing in your words gets skimmed. One in the buyer's words gets the click. Answer the doubt before purchase and returns fall, because nobody bought the wrong thing.
xSoon your listing answers buyers before they leave. Mine reviews for the EXACT words buyers use. Rewrite title and bullets in them. Pre-answer the common doubts. Returns drop when nobody buys the wrong thing. temerarii.com
facebookMarketplace move: run your reviews through a model to find the exact words buyers use, rewrite your title and bullets in those words, then pre-answer the common doubts on the page. A listing in the buyer's words gets the click, and returns drop when nobody buys the wrong thing. temerarii.com
threadsSoon your listing answers buyers before they leave the page. Mine reviews for the EXACT words buyers use, rewrite title and bullets in them, pre-answer the common doubts. Returns drop when nobody buys the wrong thing.
pinterestMarketplace listing optimization: mine reviews for the exact words buyers use, rewrite titles and bullets in their language, and pre-answer common questions on the page. Ecommerce listing copy, review mining, conversion optimization, lower return rate.
blueskySoon your listing answers buyers before they leave. Mine reviews for the exact buyer words, rewrite title and bullets in them, pre-answer the common doubts. Returns drop when nobody buys the wrong thing. temerarii.com
youtubeMarketplace Listings: Write in the Buyer's Words We're close to marketplace listings that answer a shopper's question right on the page. This short shows the move: pull your reviews through a model to find the exact words buyers use to describe the win, rewrite your title and bullets in those words so the listing matches the search in their head, then add a question block built from the real questions people keep asking. A listing in your words gets skimmed. One in the buyer's words gets the click. Pre-answer doubts and returns fall. #marketplace #ecommerce #listings

Cross-links every lens is a view on this one record

→ Wireframe · scenes→ Calendar week→ Media (audience preview)→ Storyboard hub→ Day view→ Channel view