Cyber Security — social-W38-Sun-1 — Temerarii Media Back Office

post social-W38-Sun-1kind threadweek W38date 2026-09-20campaign thread · Sunpillar it_devbeat Sunasset videoduration 65.7sground 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-W38-Sun-1 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 · 65.7s · comp_id + rendered still + tier + the script

#	Layer (comp_id · still · tier)	Beat	Timecode	Motion	Logo	Audio	VO / on-screen / caption
1	still pending matches intent shared field signature-3d	open	0–6.6s	spatial-parallax	icon·color	♪ bed_in	Old way: a brand book sat in a drawer and every post drifted off-tone within a month. on-screen: Brand systems used to drift
	expected on screen: white ground · box hero in the shared Signal Field · Faber leads · node-graph · spatial-parallax · icon·color logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual node-graphshape boxground whitetreatment colormotion spatial-parallaxpower summoninstrument summon→Brand systems used to drift
2	still pending matches intent shared field signature-3d	hook	6.6–13.2s	kinetic-build	icon·color	♪ node_lock	Here is the real problem: humans guess the voice instead of measuring it, so the brand wobbles. on-screen: Why your posts feel off
	expected on screen: white ground · box hero in the shared Signal Field · Faber leads · mark · kinetic-build · icon·color logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual markshape boxground whitetreatment colormotion kinetic-buildpower laser-lockinstrument laser-trace→Why your posts feel off
3	still pending matches intent NumberedList template	teach	13.2–20.9s	kinetic-build	icon·color	♪ node_lock	Write a style guide as plain text rules, then paste it into the model as a system prompt every time. on-screen: Pin the voice in a file
	expected on screen: white ground · a NumberedList panel over a dimmed Signal Field · Faber leads · node-graph · kinetic-build · icon·color logo · caption bottom-left spec (the prompt): comp_id NumberedListvisual node-graphshape boxground whitetreatment colormotion kinetic-buildpower morphinstrument morph+laser→Pin the voice in a filecurate items, nodes
4	still pending matches intent RankList template	proof	20.9–28.599999999999998s	receipts-count	icon·color	♪ node_lock	We feed that one prompt to every draft, so the tone holds whether it is a caption or a script. on-screen: Same voice, every channel
	expected on screen: white ground · a RankList panel over a dimmed Signal Field · Faber leads · receipts · receipts-count · icon·color logo · caption bottom-left spec (the prompt): comp_id RankListvisual receiptsshape boxground whitetreatment colormotion receipts-countpower receiptsinstrument spotlight→Same voice, every channelcurate rows, statsLabels
5	still pending matches intent TerminalRun template	diff	28.6–36.7s	crossfade-8f	icon·color	♪ node_lock	A static PDF is a wish. A prompt the model reads on every job is a control you can actually enforce. on-screen: A doc is not a system
	expected on screen: white ground · a TerminalRun panel over a dimmed Signal Field · Faber leads · code · crossfade-8f · icon·color logo · caption bottom-left spec (the prompt): comp_id TerminalRunvisual codeshape boxground whitetreatment colormotion crossfade-8fpower morphinstrument morph→A doc is not a systemcurate codeLines
6	still pending matches intent ChecklistCard template	teach	36.7–43.300000000000004s	kinetic-build	icon·color	♪ node_lock	Teach staff to run each draft back through a checker that flags banned words and off-brand lines. on-screen: Score drafts against rules
	expected on screen: white ground · a ChecklistCard panel over a dimmed Signal Field · Faber leads · node-graph · kinetic-build · icon·color logo · caption bottom-left spec (the prompt): comp_id ChecklistCardvisual node-graphshape boxground whitetreatment colormotion kinetic-buildpower morphinstrument morph+laser→Score drafts against rulescurate items, nodes
7	still pending matches intent StatScoreboard template	proof	43.3–51.0s	receipts-count	icon·color	♪ node_lock	When a line breaks a rule, the model rewrites it before a person ever sees it. Fewer arguments, less drift. on-screen: The check catches the drift
	expected on screen: white ground · a StatScoreboard panel over a dimmed Signal Field · Faber leads · receipts · receipts-count · icon·color logo · caption bottom-left spec (the prompt): comp_id StatScoreboardvisual receiptsshape boxground whitetreatment colormotion receipts-countpower receiptsinstrument spotlight→The check catches the driftcurate pillar, stats, statsLabels
8	still pending matches intent SchematicCard template	step	51.0–57.6s	kinetic-build	icon·color	♪ node_lock	Your step: list ten voice rules, name ten banned words, save them as one reusable prompt today. on-screen: Turn rules into a prompt
	expected on screen: white ground · a SchematicCard panel over a dimmed Signal Field · Faber leads · pipeline · kinetic-build · icon·color logo · caption bottom-left spec (the prompt): comp_id SchematicCardvisual pipelineshape boxground whitetreatment colormotion kinetic-buildpower throwinstrument laser-trace→Turn rules into a promptcurate nodes, stages, steps
9	still pending matches intent shared field signature-3d	resolve	57.6–65.7s	coalescence	icon·color	♪ bed_out	Now the brand is living code, not a dusty file. The Big T-M keeps it tight while the team moves fast. on-screen: Brand as living code
	expected on screen: white ground · box hero in the shared Signal Field · Faber leads · coalescence · coalescence · icon·color logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual coalescenceshape boxground whitetreatment colormotion coalescencepower coalescenceinstrument coalescence→Brand as living code

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)

tiktokYour brand voice drifts because it lives in a PDF nobody reads. Move it into a system prompt the model checks on every post. (AI-assisted) #brandsystems #contentops #marketingtips

instagramBrand voice in a drawer = brand voice in the wind. Move your rules into a prompt the model reads every time. Drift dies. Tone holds. #brand #contentstrategy #socialmedia #aimarketing #brandvoice

linkedinMost brand books fail for one boring reason: they are static. A PDF cannot enforce anything. The fix we teach staff: turn your voice rules and banned-word list into a system prompt the model reads on every draft, then run each draft back through a checker. Off-brand lines get rewritten before a human sees them. The brand stops being a wish and starts being code. Want the checklist? Comment below.

xYour brand book is a PDF nobody opens. Turn the rules into a system prompt the model checks on every post. Drift dies. Here is the method:

facebookBrand voice drifts because it lives in a document nobody reads. Move your rules and banned words into a prompt the model checks on every draft. Comment for the free checklist.

threadsA brand book in a drawer cannot stop your posts from drifting. Put the rules in a prompt the model reads every time, run drafts through a checker, and the voice holds across every channel. That is the whole trick.

pinterestBrand voice consistency system: how to turn your brand style guide and banned-word list into a reusable AI system prompt that keeps tone consistent across every social channel. Content operations, brand management, marketing workflow tips.

blueskyYour brand book is a PDF nobody reads. Move the rules into a prompt the model checks on every draft. Drift dies, tone holds. Here is the method:

youtubeBrand Voice as Code: Stop Your Content From Drifting Off-Brand Most brand books fail because they are static files. This walks through turning your voice rules and banned-word list into a reusable system prompt the model checks on every draft, then scoring drafts against the rules so off-brand lines get rewritten automatically. Brand systems, content operations, and a workflow your whole team can run. AI-assisted production.

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

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