Checklist the per-video bar — engine/sim
86.6/100
quantitative quality · weights learn from your reviews (
engine.sim.memory review social-W36-Thu-4 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
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 · 47.1s · 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 | 0–5.0s | spatial-parallax | icon·liquid-chrome | ♪ bed_in | An interview used to be one recording, posted once, then forgotten forever. on-screen: Interviews used to be one and done |
expected on screen: red ground · octa hero in the shared Signal Field · Lumen leads · node-graph · spatial-parallax · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual node-graphshape octaground redtreatment liquid-chromemotion spatial-parallaxpower summoninstrument summon→Interviews used to be one and done | |||||||
| 2 |  matches intent shared field signature-3d | hook | 5.0–10.5s | kinetic-build | icon·white-knockout | ♪ node_lock | An hour of sharp talk got used exactly one time and then gathered dust. on-screen: All that talk, used a single time |
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→All that talk, used a single time | |||||||
| 3 |  matches intent NumberedList template | teach | 10.5–16.0s | kinetic-build | icon·liquid-chrome | ♪ node_lock | Now we transcribe it and ask a model to find every standalone idea inside. on-screen: Transcribe, then mine for threads |
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→Transcribe, then mine for threadscurate items, nodes | |||||||
| 4 |  matches intent RankList template | proof | 16.0–21.2s | receipts-count | icon·white-knockout | ♪ node_lock | One conversation quietly becomes a dozen posts, each built on a single idea. on-screen: One talk becomes a dozen posts |
expected on screen: red ground · a RankList panel over a dimmed Signal Field · Lumen leads · receipts · receipts-count · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id RankListvisual receiptsshape octaground redtreatment white-knockoutmotion receipts-countpower receiptsinstrument spotlight→One talk becomes a dozen postscurate rows, statsLabels | |||||||
| 5 |  matches intent DiffCard template | diff | 21.2–26.4s | crossfade-8f | icon·liquid-chrome | ♪ node_lock | But chopping the talk blindly loses the meaning and the guest sounds odd. on-screen: Chopping blindly loses the meaning |
expected on screen: red ground · a DiffCard panel over a dimmed Signal Field · Lumen leads · code · crossfade-8f · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id DiffCardvisual codeshape octaground redtreatment liquid-chromemotion crossfade-8fpower morphinstrument morph→Chopping blindly loses the meaningcurate codeLines, lines | |||||||
| 6 |  matches intent ChecklistCard template | teach | 26.4–31.599999999999998s | kinetic-build | icon·white-knockout | ♪ node_lock | So you tell the model each clip must hold one complete, honest thought. on-screen: Keep each clip a whole thought |
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 each clip a whole thoughtcurate items, nodes | |||||||
| 7 |  matches intent StatScoreboard template | proof | 31.6–37.1s | receipts-count | icon·liquid-chrome | ♪ node_lock | Now every channel gets its own angle from the same hour of real talk. on-screen: Every channel gets its own angle |
expected on screen: red ground · a StatScoreboard panel over a dimmed Signal Field · Lumen leads · receipts · receipts-count · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id StatScoreboardvisual receiptsshape octaground redtreatment liquid-chromemotion receipts-countpower receiptsinstrument spotlight→Every channel gets its own anglecurate pillar, stats, statsLabels | |||||||
| 8 |  matches intent PipelineMap template | step | 37.1–42.1s | kinetic-build | icon·white-knockout | ♪ node_lock | Try it: transcribe one interview and ask for ten standalone, complete ideas. on-screen: Mine one talk for ten ideas |
expected on screen: red ground · a PipelineMap panel over a dimmed Signal Field · Lumen leads · pipeline · kinetic-build · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id PipelineMapvisual pipelineshape octaground redtreatment white-knockoutmotion kinetic-buildpower throwinstrument laser-trace→Mine one talk for ten ideascurate stages, steps | |||||||
| 9 |  matches intent shared field signature-3d | resolve | 42.1–47.1s | coalescence | icon·liquid-chrome | ♪ bed_out | Soon a single conversation quietly feeds your whole week of content. on-screen: Soon one talk feeds the week |
expected on screen: red ground · octa hero in the shared Signal Field · Lumen leads · coalescence · coalescence · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual coalescenceshape octaground redtreatment liquid-chromemotion coalescencepower coalescenceinstrument coalescence→Soon one talk feeds the week | |||||||
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)
tiktokOne interview should not be posted once and forgotten. Here is the move (AI-assisted): transcribe it, then ask a model to find every standalone idea, where each clip holds ONE complete thought. One talk becomes a dozen posts. #podcasting #repurposing #aitools
instagramOne interview, posted once? No.
Transcribe it.
Mine for standalone ideas.
Each clip = one whole thought.
One talk feeds the week.
#interview #podcasting #contentrepurposing #aitools #creators
linkedinAn interview used to be one recording, posted once, then forgotten. The method: transcribe it and ask a model to find every standalone idea, with one rule, each clip must hold one complete thought. The takeaway: chopping blindly loses meaning, but done right, a single hour of real talk feeds a dozen posts across channels.
xInterview move: transcribe it, ask AI to find every standalone idea, each clip holding one complete thought. One talk becomes a dozen posts. temerarii.com
facebookAn interview used to be posted once and forgotten. The method: transcribe it, ask a model to find every standalone idea, and require each clip to hold one complete thought. One talk becomes a dozen posts. See it at temerarii.com.
threadsOne interview, posted once and forgotten? No. Transcribe it, ask AI to find every standalone idea, each clip holding one complete thought. One talk becomes a dozen posts.
pinterestAI content repurposing: how one interview becomes a dozen posts. Transcribe the talk, ask a model to find standalone ideas, and keep each clip a complete thought. Evergreen guide to repurposing, podcast clips, and multi-channel content.
blueskyInterview move: transcribe it, ask AI to find every standalone idea, each clip holding one complete thought. One talk becomes a dozen posts. temerarii.com
youtubeAI Repurposing: Turn One Interview Into A Dozen Posts
An interview used to be one recording, posted once, then forgotten, with an hour of sharp talk used exactly once. The real method: transcribe it and ask a model to find every standalone idea inside, with one strict rule, each clip must hold one complete, honest thought. Chopping blindly loses meaning and the guest sounds odd. Done right, a single conversation feeds your whole week. More at temerarii.com.