Checklist the per-video bar — engine/sim
84.5/100
quantitative quality · weights learn from your reviews (
engine.sim.memory review social-W33-Thu-3 good|bad)⚠ 4 flag(s) — not yet ship-ready: copy_generictoo_complexdup_sequence_across_assetsdup_set_across_assets · see docs/strategy/VIDEO-CHECKLIST.md
Composition comp · template family · expected output
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 · 63.5s · comp_id + rendered still + tier + the script
| # | Layer (comp_id · still · tier) | Beat | Timecode | Motion | Logo | Audio | VO / on-screen / caption |
|---|---|---|---|---|---|---|---|
| 1 |  matches intent shared field signature-3d | open | 0–8.1s | spatial-parallax | icon·white-knockout | ♪ bed_in | We are close to where one strong idea fans out to every platform, each in its own native voice, in minutes. on-screen: Soon one idea fans out everywhere |
expected on screen: red ground · octa hero in the shared Signal Field · Lumen leads · node-graph · spatial-parallax · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual node-graphshape octaground redtreatment white-knockoutmotion spatial-parallaxpower summoninstrument summon→Soon one idea fans out everywhere | |||||||
| 2 |  matches intent shared field signature-3d | hook | 8.1–15.399999999999999s | kinetic-build | icon·white-knockout | ♪ node_lock | Old way, you pasted the exact same post on every app and acted surprised it landed flat on most. on-screen: The old way: same post everywhere |
expected on screen: red ground · octa hero in the shared Signal Field · Lumen leads · mark · kinetic-build · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual markshape octaground redtreatment white-knockoutmotion kinetic-buildpower laser-lockinstrument laser-trace→The old way: same post everywhere | |||||||
| 3 |  matches intent NumberedList template | teach | 15.4–22.7s | kinetic-build | icon·liquid-chrome | ♪ node_lock | Here is the move: write the one core idea cleanly, the single point you would defend in a room. on-screen: Write the core idea once |
expected on screen: red ground · a NumberedList panel over a dimmed Signal Field · Lumen leads · node-graph · kinetic-build · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id NumberedListvisual node-graphshape octaground redtreatment liquid-chromemotion kinetic-buildpower morphinstrument morph+laser→Write the core idea oncecurate items, nodes | |||||||
| 4 |  matches intent ComparisonTable template | proof | 22.7–29.7s | receipts-count | icon·white-knockout | ♪ node_lock | Then let a model recast that one idea into each platform's voice, punchy on one, plainspoken on another. on-screen: Let AI translate the voice per app |
expected on screen: red ground · a ComparisonTable panel over a dimmed Signal Field · Lumen leads · receipts · receipts-count · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id ComparisonTablevisual receiptsshape octaground redtreatment white-knockoutmotion receipts-countpower receiptsinstrument spotlight→Let AI translate the voice per appcurate colA, colB, rows, statsLabels | |||||||
| 5 |  matches intent JsonDiff template | diff | 29.7–36.0s | crossfade-8f | icon·liquid-chrome | ♪ node_lock | Spamming the same words is lazy. One idea spoken in each room's real language is respect. on-screen: One idea, many true voices |
expected on screen: red ground · a JsonDiff panel over a dimmed Signal Field · Lumen leads · code · crossfade-8f · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id JsonDiffvisual codeshape octaground redtreatment liquid-chromemotion crossfade-8fpower morphinstrument morph→One idea, many true voicescurate codeLines, fileName, lines | |||||||
| 6 |  matches intent ChecklistCard template | teach | 36.0–42.6s | kinetic-build | icon·white-knockout | ♪ node_lock | Now read every version yourself before it ships, because a model can drift off-brand without you noticing. on-screen: Keep a human edit at the end |
expected on screen: red ground · a ChecklistCard panel over a dimmed Signal Field · Lumen leads · node-graph · kinetic-build · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id ChecklistCardvisual node-graphshape octaground redtreatment white-knockoutmotion kinetic-buildpower morphinstrument morph+laser→Keep a human edit at the endcurate items, nodes | |||||||
| 7 |  matches intent KpiGrid template | proof | 42.6–49.9s | receipts-count | icon·liquid-chrome | ♪ node_lock | The model drafts nine versions fast, you fix the two that sound wrong, and the whole thing stays yours. on-screen: Machine drafts, you sign off |
expected on screen: red ground · a KpiGrid panel over a dimmed Signal Field · Lumen leads · receipts · receipts-count · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id KpiGridvisual receiptsshape octaground redtreatment liquid-chromemotion receipts-countpower receiptsinstrument spotlight→Machine drafts, you sign offcurate kpis, statsLabels | |||||||
| 8 |  matches intent NodeGraphCard template | step | 49.9–56.9s | kinetic-build | icon·white-knockout | ♪ node_lock | Three steps: write the one idea, let the model translate per platform, give every version a human edit. on-screen: Step: one idea, translate, human edit |
expected on screen: red ground · a NodeGraphCard panel over a dimmed Signal Field · Lumen leads · pipeline · kinetic-build · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id NodeGraphCardvisual pipelineshape octaground redtreatment white-knockoutmotion kinetic-buildpower throwinstrument laser-trace→Step: one idea, translate, human editcurate hub, nodes, stages, steps | |||||||
| 9 |  matches intent shared field signature-3d | resolve | 56.9–63.5s | coalescence | icon·white-knockout | ♪ bed_out | Strategy was never about posting more. It is having one idea worth translating in the first place. on-screen: Strategy is the idea, not the volume |
expected on screen: red ground · octa hero in the shared Signal Field · Lumen leads · coalescence · coalescence · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual coalescenceshape octaground redtreatment white-knockoutmotion coalescencepower coalescenceinstrument coalescence→Strategy is the idea, not the volume | |||||||
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 one idea fans out to every platform in its own voice. (AI-assisted) The move: write the ONE core idea cleanly, then let a model recast it into each platform's voice. But read every version yourself before it ships. One idea in each room's real language is respect. Spamming is lazy.
instagramOne idea, many true voices.
Write the core idea once.
Let AI translate per platform.
Give every version a human edit.
#socialmediastrategy #contentstrategy #socialmedia #marketing #aitools
linkedinWe're close to where one strong idea fans out to every platform, each in its own native voice, in minutes.
The move: write the one core idea cleanly, the single point you'd defend in a room. Then let a model recast that idea into each platform's voice, punchy on one, plainspoken on another. But read every version yourself before it ships, because a model can drift off-brand without you noticing. It drafts nine versions fast; you fix the two that sound wrong, and the whole thing stays yours.
Strategy was never about posting more. It's having one idea worth translating in the first place.
xSoon one idea fans out to every platform in its own voice.
Write the ONE core idea cleanly, let a model recast it per platform, then read every version before it ships.
Strategy is the idea, not the volume.
temerarii.com
facebookSoon one strong idea fans out to every platform in its own voice. Write the one core idea cleanly, let a model recast it per platform, then read every version yourself before it ships. One idea in each room's real language is respect; spamming the same words is lazy. temerarii.com
threadsSoon one idea fans out to every platform in its own voice.
Write the ONE core idea cleanly, let a model recast it per platform, then read every version before it ships.
Strategy is the idea, not the volume.
pinterestSocial strategy with AI: write one core idea, let a model translate it into each platform's native voice, then human-edit every version before posting. Content repurposing, platform-native voice, social media strategy, cross-platform posting, content workflow.
blueskySoon one idea fans out to every platform in its own voice. Write the ONE core idea cleanly, let a model recast it per platform, then read every version before it ships. Strategy is the idea, not the volume. temerarii.com
youtubeSocial Strategy: One Idea, Many Native Voices
We're close to where one strong idea fans out to every platform, each in its own native voice, in minutes. This short shows the move: write the one core idea cleanly, the single point you'd defend in a room, then let a model recast it into each platform's voice. But read every version yourself before it ships, because a model can drift off-brand. It drafts fast; you fix the two that sound wrong.
Strategy was never about posting more. It's having one idea worth translating.
#socialmediastrategy #contentstrategy #marketing