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 topic-x-creative-workflowskind topicweek —date —campaign multimedia-pillarpillar multimediabeat —asset videoduration 122.7sground blackscenes 19

Checklist the per-video bar — engine/sim

96.5/100
plain languagevo coverageno dead airuniquenesscaption fitcompletenesscleanliness
quantitative quality · weights learn from your reviews (engine.sim.memory review topic-x-creative-workflows good|bad)
⚠ 2 flag(s) — not yet ship-ready: copy_generictoo_complex · see docs/strategy/VIDEO-CHECKLIST.md

Composition comp · template family · expected output

composition SceneReelfamily / template SceneReel
9:16 Reelrendered1:1 Squarepending16:9 Widepending9:16 4Kpending1:1 4Kpending16:9 4KpendingGIF (SMS)pending
▶ open rendered mp4
expected output: 1/7 rendered — same matrix the /media preview surfaces for this asset.

Composition layer × scene 19 scenes · 122.7s · comp_id + rendered still + tier + the script

#Layer (comp_id · still · tier)BeatTimecodeMotionLogoAudioVO / on-screen / caption
1s1
matches intent
shared field
signature-3d		open0–6.4sspatial-parallaxicon·wireframe♪ —
One idea has to become a reel, a thread, a carousel, an email. What if that whole spread built itself?
on-screen: One idea, every channel
expected on screen: black ground · octa hero in the shared Signal Field · Lumen leads · node-graph · spatial-parallax · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id shared Signal Fieldvisual node-graphshape octaground blacktreatment wireframemotion spatial-parallaxpower summoninstrument summon→three-mark
2s2
matches intent
ListCard
template		legacy6.4–13.100000000000001scrossfade-8ficon·wireframe♪ —
The old way was a person at midnight resizing the same post for the fifth platform, slowly losing their mind.
on-screen: The content treadmill
expected on screen: black ground · a ListCard panel over a dimmed Signal Field · Lumen leads · crossfade-8f · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id ListCardshape octaground blacktreatment wireframemotion crossfade-8fpower morphinstrument decay→three-symboliccurate items
3s3
matches intent
NumberedList
template		teach13.1–19.4skinetic-buildicon·wireframe♪ —
We start with a single content file, the idea written once, that every downstream asset reads from.
on-screen: Step 1: one source of truth
expected on screen: black ground · a NumberedList panel over a dimmed Signal Field · Lumen leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id NumberedListvisual node-graphshape octaground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→html-in-canvas-panelcurate items, nodes
4s4
matches intent
ChecklistCard
template		teach19.4–25.2skinetic-buildicon·wireframe♪ —
An agent pulls the trend and the receipts first, so the piece stands on something real, not a hunch.
on-screen: Step 2: research the angle
expected on screen: black ground · a ChecklistCard panel over a dimmed Signal Field · Lumen leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id ChecklistCardvisual node-graphshape octaground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→three-diagramcurate items, nodes
5s5
matches intent
NodeGraphCard
template		teach25.2–33.2skinetic-buildicon·wireframe♪ —
The agent drafts a structured script, an opening, a teach, a turn, so the content has a spine, not just vibes.
on-screen: Step 3: write the script
expected on screen: black ground · a NodeGraphCard panel over a dimmed Signal Field · Lumen leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id NodeGraphCardvisual node-graphshape octaground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→html-in-canvas-codecurate hub, nodes
6s6
matches intent
LogStream
template		teach33.2–39.6skinetic-buildicon·wireframe♪ —
We send the script to a text-to-speech model, so the voiceover is generated, not recorded at 2am.
on-screen: Step 4: voice from the script
expected on screen: black ground · a LogStream panel over a dimmed Signal Field · Lumen leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id LogStreamvisual node-graphshape octaground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→three-flowcurate nodes, rows
7s7
matches intent
AnnotatedDiagram
template		teach39.6–46.300000000000004skinetic-buildicon·wireframe♪ —
The motion is built on a fixed visual system, so every clip looks like the same brand without a designer per post.
on-screen: Step 5: visuals on a system
expected on screen: black ground · a AnnotatedDiagram panel over a dimmed Signal Field · Lumen leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id AnnotatedDiagramvisual node-graphshape octaground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→html-in-canvas-panelcurate callouts, nodes
8s8
matches intent
WireframeMock
template		teach46.3–52.9skinetic-buildicon·wireframe♪ —
We render the video programmatically, so the same script outputs square, vertical, and wide from one build.
on-screen: Step 6: render in code
expected on screen: black ground · a WireframeMock panel over a dimmed Signal Field · Lumen leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id WireframeMockvisual node-graphshape octaground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→three-diagramcurate nodes
9s9
matches intent
BuildLog
template		teach52.9–59.4skinetic-buildicon·wireframe♪ —
Captions and safe zones get baked per platform, so nothing important hides behind the TikTok interface.
on-screen: Step 7: caption-burn per platform
expected on screen: black ground · a BuildLog panel over a dimmed Signal Field · Lumen leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id BuildLogvisual node-graphshape octaground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→html-in-canvas-codecurate lines, nodes
10s10
matches intent
JsonDiff
template		teach59.4–64.9skinetic-buildicon·wireframe♪ —
The long video gets sliced into the strongest moments, so one shoot feeds a week of shorts.
on-screen: Step 8: cut the long into shorts
expected on screen: black ground · a JsonDiff panel over a dimmed Signal Field · Lumen leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id JsonDiffvisual node-graphshape octaground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→three-flowcurate fileName, lines, nodes
11s11
matches intent
CodeWindow
template		teach64.9–70.30000000000001skinetic-buildicon·wireframe♪ —
The same source spins out a written thread, so the people who do not watch video still get the
on-screen: Step 9: thread from the same idea
expected on screen: black ground · a CodeWindow panel over a dimmed Signal Field · Lumen leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id CodeWindowvisual node-graphshape octaground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→html-in-canvas-panelcurate codeLines, nodes, windowTitle
12s12
matches intent
DiffCard
template		teach70.3–77.7skinetic-buildicon·wireframe♪ —
Before anything posts, a gate checks brand rules, banned words, and the logo, so nothing off-brand slips out.
on-screen: Step 10: QA the batch
expected on screen: black ground · a DiffCard panel over a dimmed Signal Field · Lumen leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id DiffCardvisual node-graphshape octaground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→three-diagramcurate lines, nodes
13s13
matches intent
TerminalRun
template		teach77.7–84.60000000000001skinetic-buildicon·wireframe♪ —
Approved assets get scheduled across every account at once, so distribution is a click, not a calendar puzzle.
on-screen: Step 11: schedule across accounts
expected on screen: black ground · a TerminalRun panel over a dimmed Signal Field · Lumen leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id TerminalRunvisual node-graphshape octaground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→html-in-canvas-codecurate nodes
14s14
matches intent
PipelineMap
template		teach84.6–90.8skinetic-buildicon·wireframe♪ —
Every published asset logs itself to a library, so you always know what ran where and how it did.
on-screen: Step 12: log to the library
expected on screen: black ground · a PipelineMap panel over a dimmed Signal Field · Lumen leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id PipelineMapvisual node-graphshape octaground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→three-flowcurate nodes, stages
15s15
matches intent
StackTrace
template		teach90.8–97.0skinetic-buildicon·wireframe♪ —
A person still approves the batch, because the engine handles volume but taste is not automatable.
on-screen: Step 13: keep the human taste
expected on screen: black ground · a StackTrace panel over a dimmed Signal Field · Lumen leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id StackTracevisual node-graphshape octaground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→html-in-canvas-panelcurate errMsg, errType, fix, frames, nodes
16s16
matches intent
CheatSheet
template		teach97.0–103.1skinetic-buildicon·wireframe♪ —
What performs gets read back into the next idea, so the engine sharpens instead of just spinning.
on-screen: Step 14: measure, then feed back
expected on screen: black ground · a CheatSheet panel over a dimmed Signal Field · Lumen leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id CheatSheetvisual node-graphshape octaground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→three-diagramcurate nodes, points, uses
17s17
matches intent
RankList
template		proof103.1–111.1sreceipts-counticon·wireframe♪ —
That is a single idea turned into research, script, voice, video, thread, and schedule, with a human on taste.
on-screen: One idea. A full week.
expected on screen: black ground · a RankList panel over a dimmed Signal Field · Lumen leads · receipts · receipts-count · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id RankListvisual receiptsshape octaground blacktreatment wireframemotion receipts-countpower receiptsinstrument spotlight→html-in-canvas-receiptscurate rows, statsLabels
18s18
matches intent
shared field
signature-3d		futurist111.1–116.5sspatial-parallaxicon·wireframe♪ —
When production stops being the bottleneck, the only limit left is how good your ideas are.
on-screen: What this unlocks
expected on screen: black ground · octa hero in the shared Signal Field · Lumen leads · spatial-parallax · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id shared Signal Fieldshape octaground blacktreatment wireframemotion spatial-parallaxpower spatial-parallaxinstrument laser-fire→three-forward
19s19
matches intent
shared field
signature-3d		resolve116.5–122.7scoalescenceicon·wireframe♪ swell
Bring one idea and we will show you the engine turn it into a week of content. temerarii.xyz.
on-screen: Bring one idea
expected on screen: black ground · octa hero in the shared Signal Field · Lumen leads · coalescence · coalescence · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id shared Signal Fieldvisual coalescenceshape octaground blacktreatment wireframemotion coalescencepower coalescenceinstrument coalescence→three-coalescence

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 12 destinations

LinkedInX/TwitterYouTubeInstagramFacebookThreadsTikTokPinterestBlueskyEmailSMSBlog

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

tiktokOne idea has to become a reel, a thread, a carousel, an email. What if that whole spread built itself? (AI-assisted) Start with one content file, the idea written once, that every asset reads from. An agent pulls the trend and the receipts first. It drafts a structured script with an opening, a teach, a turn. Send the script to text-to-speech for the voiceover. Render the video in code, so one build outputs square, vertical, and wide. A gate checks brand rules, banned words, and the logo before anything posts. A person still approves the batch, because volume is automatable but taste is not.
instagramOne idea. A reel, a thread, a carousel, an email. What if it built itself? Write the idea once, one source file Agent researches, then scripts it Text-to-speech does the voiceover Render in code: square, vertical, wide A gate checks brand rules before posting Volume automates. Taste does not. #ContentOps #Remotion #AItools #Repurposing #Temerarii
linkedinOne idea has to become a reel, a thread, a carousel, an email. What if that whole spread built itself? Here is the engine, given away. The old way was a person at midnight resizing the same post for the fifth platform, slowly losing their mind. The method: 1. Start with a single content file, the idea written once, that every downstream asset reads from. 2. An agent pulls the trend and the receipts first, so the piece stands on something real. 3. It drafts a structured script, an opening, a teach, a turn, so the content has a spine. 4. Send the script to a text-to-speech model, so the voiceover is generated, not recorded at 2am. 5. Render the video in code, so one build outputs square, vertical, and wide. 6. Captions and safe zones get baked per platform, so nothing important hides behind the interface. 7. A gate checks brand rules, banned words, and the logo before anything posts. A person still approves the batch, because the engine handles volume but taste is not automatable. Bring one idea and we will show you the engine turn it into a week of content. temerarii.xyz
xOne idea: a reel, a thread, a carousel, an email. It can build itself. Write the idea once Agent researches, then scripts Text-to-speech voiceover Render in code: square, vertical, wide A gate checks brand before posting Volume automates, taste doesn't. temerarii.xyz
facebookOne idea has to become a reel, a thread, a carousel, an email. What if that whole spread built itself? Start with one content file, the idea written once. An agent researches the angle, then drafts a structured script. Text-to-speech does the voiceover. The video renders in code, so one build outputs square, vertical, and wide. A gate checks brand rules, banned words, and the logo before anything posts. A person still approves the batch, because volume automates but taste does not. Bring one idea: temerarii.xyz
threadsOne idea: a reel, a thread, a carousel, an email. What if it built itself? Write the idea once, one source file. An agent researches, then drafts a structured script. Text-to-speech does the voiceover. Render in code: square, vertical, wide. A gate checks brand rules before posting. Volume automates. Taste does not.
pinterestHow to turn one idea into a week of content across every channel: write the idea once as a source file, let an agent research and script it, generate the voiceover, render the video in code for every aspect ratio, and gate it for brand rules. A plain content repurposing method with a human taste check.
blueskyOne idea: a reel, a thread, a carousel, an email. What if it built itself? Write the idea once. An agent researches, then scripts it. Text-to-speech voiceover. Render in code: square, vertical, wide. A gate checks brand before posting. Volume automates. Taste does not. temerarii.xyz
youtubeOne Idea Into a Week of Content: A Code-Built Creative Pipeline One idea has to become a reel, a thread, a carousel, an email. What if that whole spread built itself? This walks the full engine and gives it away. The old way was a person at midnight resizing the same post for the fifth platform, slowly losing their mind. The method: 1. Start with a single content file, the idea written once, that every downstream asset reads from. 2. An agent pulls the trend and the receipts first, so the piece stands on something real. 3. It drafts a structured script, an opening, a teach, a turn, so the content has a spine. 4. Send the script to a text-to-speech model, so the voiceover is generated, not recorded at 2am. 5. The motion is built on a fixed visual system, so every clip looks like the same brand. 6. Render the video in code, so one build outputs square, vertical, and wide. 7. Captions and safe zones get baked per platform. The long video gets sliced into shorts. 8. A gate checks brand rules, banned words, and the logo before anything posts. A person still approves the batch, because the engine handles volume but taste is not automatable. Bring one idea and we will show you the engine turn it into a week of content. temerarii.xyz

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

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