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 longform-W31-Satkind longformweek W31date 2026-08-08campaign longform-youtubepillar brandbeat asset videoduration 108.9sground redscenes 6

Checklist the per-video bar — engine/sim

100.0/100
plain languagevo coverageno dead airuniquenesscaption fitcompletenesscleanliness
quantitative quality · weights learn from your reviews (engine.sim.memory review longform-W31-Sat good|bad)
✓ all static checks pass — one-focal/scene · tier-by-beat · one-track caption · colorway · cast+shape correct · no banned/fabricated. (audio + visual tiers verify on the rendered finals — Phase 2)

Composition comp · template family · expected output

composition LongFormChaptersfamily / template LongFormChapters
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 6 scenes · 108.9s · comp_id + rendered still + tier + the script

#Layer (comp_id · still · tier)BeatTimecodeMotionLogoAudioVO / on-screen / caption
1s1
matches intent
shared field
signature-3d
open0–20.5sspatial-parallaxicon·white-knockout♪ bed_in
Cut busywork, keep revenue. We close the week with strategy, which sounds grand but is really just deciding what not to do. Most plans are long lists of everything. We are going to show you how to use a model to find the one move that matters and let the rest go. The skill is subtraction.
on-screen: Strategy is choosing what to skip
expected on screen: red ground · icosa hero in the shared Signal Field · Signum leads · node-graph · spatial-parallax · icon·white-knockout logo · caption bottom-left
spec (the prompt): comp_id shared Signal Fieldvisual node-graphshape icosaground redtreatment white-knockoutmotion spatial-parallaxpower summoninstrument summon→Strategy is choosing what to skip
2s2
matches intent
NumberedList
template
teach20.5–38.5skinetic-buildicon·white-knockout♪ node_lock
Step one. Write down every marketing thing you currently do, every channel, every weekly task. Be honest, the whole pile. Hand that list to Claude Code. You cannot cut busywork until you can see all of it in one place, and most teams never write the full list down.
on-screen: List every channel honestly
expected on screen: red ground · a NumberedList panel over a dimmed Signal Field · Signum leads · node-graph · kinetic-build · icon·white-knockout logo · caption bottom-left
spec (the prompt): comp_id NumberedListvisual node-graphshape icosaground redtreatment white-knockoutmotion kinetic-buildpower morphinstrument morph+laser→List every channel honestlycurate items, nodes
3s3
matches intent
ChecklistCard
template
teach38.5–56.5skinetic-buildicon·liquid-chrome♪ node_lock
Step two. Pair that list with your revenue-by-source data from earlier this week and ask the model a hard question. Which of these actually drives money, and which just feels productive. The model has no attachment to the task someone built two years ago. It answers from the numbers.
on-screen: Ask which one drives revenue
expected on screen: red ground · a ChecklistCard panel over a dimmed Signal Field · Signum leads · node-graph · kinetic-build · icon·liquid-chrome logo · caption bottom-left
spec (the prompt): comp_id ChecklistCardvisual node-graphshape icosaground redtreatment liquid-chromemotion kinetic-buildpower morphinstrument morph+laser→Ask which one drives revenuecurate items, nodes
4s4
matches intent
AnnotatedDiagram
template
teach56.5–73.1skinetic-buildicon·white-knockout♪ node_lock
Step three. Tell the model to name the single highest-return activity and a short list to stop entirely. A real strategy fits on one line. The model forces the choice you have been avoiding, because doing everything a little is how revenue quietly leaks away.
on-screen: Pick one move, drop the rest
expected on screen: red ground · a AnnotatedDiagram panel over a dimmed Signal Field · Signum leads · node-graph · kinetic-build · icon·white-knockout logo · caption bottom-left
spec (the prompt): comp_id AnnotatedDiagramvisual node-graphshape icosaground redtreatment white-knockoutmotion kinetic-buildpower morphinstrument morph+laser→Pick one move, drop the restcurate callouts, nodes
5s5
matches intent
ComparisonTable
template
proof73.1–91.89999999999999sreceipts-counticon·liquid-chrome♪ node_lock
We ran our own studio through this exact subtraction. We stopped a pile of work that only looked busy and kept the few moves that pay. We are not selling a framework we skipped. The whole calendar you are watching came from one source file, on purpose, after cutting the rest.
on-screen: We cut our own list first
expected on screen: red ground · a ComparisonTable panel over a dimmed Signal Field · Signum leads · receipts · receipts-count · icon·liquid-chrome logo · caption bottom-left
spec (the prompt): comp_id ComparisonTablevisual receiptsshape icosaground redtreatment liquid-chromemotion receipts-countpower receiptsinstrument spotlight→We cut our own list firstcurate colA, colB, rows, statsLabels
6s6
matches intent
shared field
signature-3d
resolve91.9–108.9scoalescenceicon·white-knockout♪ bed_out
So the takeaway for the whole week. Strategy is not adding more, it is choosing the few things that keep revenue and letting a model help you drop the busywork without flinching. Go see the focused version running in public at office dot temerarii dot xyz.
on-screen: See the focused studio live
expected on screen: red ground · icosa hero in the shared Signal Field · Signum leads · coalescence · coalescence · icon·white-knockout logo · caption bottom-left
spec (the prompt): comp_id shared Signal Fieldvisual coalescenceshape icosaground redtreatment white-knockoutmotion coalescencepower coalescenceinstrument coalescence→See the focused studio live

Format stack 1 aspects · same scenes[], re-cropped

16:9
1920×1080
X/Twitter · YouTube · LinkedIn video

Channels 2 destinations

YouTubeBlog

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

youtubeMarketing Strategy Is Choosing What to Skip: List It All, Find What Drives Revenue, Cut the Rest Strategy sounds grand but is really just deciding what not to do. Most plans are long lists of everything. This walkthrough shows how to use a model to find the one move that matters and drop the busywork without flinching. The method: - List every channel honestly. Write down every marketing thing you currently do, every channel, every weekly task, the whole pile. Hand that list to a coding agent. You cannot cut busywork until you can see all of it in one place, and most teams never do. - Ask which one drives revenue. Pair that list with your revenue-by-source data and ask the model a hard question, which of these actually drives money and which just feels productive. The model has no attachment to the task someone built their week around. - Pick one move, drop the rest. Tell the model to name the single highest-return activity and a short list to stop entirely. A real strategy fits on one line. The model forces the choice you have been avoiding, because doing everything a little is how revenue leaks. We ran our own studio through this exact subtraction. We stopped a pile of work that only looked busy and kept the few moves that pay. The whole calendar you are watching came from one source file. Strategy is not adding more, it is choosing the few things that keep revenue and letting a model help you drop the rest. See the focused studio at office.temerarii.xyz. Keywords: marketing strategy, prioritization, revenue attribution, cut busywork, channel focus, small business marketing.

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