Checklist the per-video bar — engine/sim
84.7/100
quantitative quality · weights learn from your reviews (
engine.sim.memory review thread-the-stack-W38-Tue good|bad)⚠ 5 flag(s) — not yet ship-ready: low_vo_coveragedead_airgeneric_scene · see docs/strategy/VIDEO-CHECKLIST.md
Composition comp · template family · expected output
9:16 Reelrendered1:1 Squarepending16:9 Widepending9:16 4Kpending1:1 4Kpending16:9 4KpendingGIF (SMS)pending
expected output: 1/7 rendered — same matrix the /media preview surfaces for this asset.
Composition layer × scene 6 scenes · 34.1s · 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 | hook | 0–5.0s | kinetic-build | icon·liquid-chrome | ♪ node_lock | The tool is Google Sheets. Every project starts there. Then the file hits a hundred thousand rows and stalls. on-screen: Sheets dies at 100k rows |
expected on screen: red ground · cone hero in the shared Signal Field · Augur leads · mark · kinetic-build · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual markshape coneground redtreatment liquid-chromemotion kinetic-buildpower laser-lockinstrument laser-trace→Sheets dies at 100k rows | |||||||
| 2 |  matches intent ChecklistCard template | teach | 5.0–12.2s | kinetic-build | icon·white-knockout | ♪ node_lock | So we export the sheet to a file and query it with DuckDB, a tiny local engine that chews millions of rows in on-screen: Push to DuckDB locally |
expected on screen: red ground · a ChecklistCard panel over a dimmed Signal Field · Augur leads · node-graph · kinetic-build · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id ChecklistCardvisual node-graphshape coneground redtreatment white-knockoutmotion kinetic-buildpower morphinstrument morph+laser→Push to DuckDB locallycurate items, nodes | |||||||
| 3 |  matches intent StackTrace template | build | 12.2–19.1s | type-on | icon·liquid-chrome | ♪ node_lock | Now the analysis that froze your browser runs in a blink, and you still write plain SQL against your old spreadsheet on-screen: Million-row analysis, instant |
expected on screen: red ground · a StackTrace panel over a dimmed Signal Field · Augur leads · code · type-on · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id StackTracevisual codeshape coneground redtreatment liquid-chromemotion type-onpower summoninstrument draw-on→Million-row analysis, instantcurate codeLines, errMsg, errType, fix, frames | |||||||
| 4 |  matches intent PipelineMap template | proof | 19.1–24.1s | receipts-count | icon·white-knockout | ♪ node_lock | So export your biggest sheet to a CSV and point DuckDB at it. on-screen: Query your CSV with DuckDB |
expected on screen: red ground · a PipelineMap panel over a dimmed Signal Field · Augur leads · receipts · receipts-count · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id PipelineMapvisual receiptsshape coneground redtreatment white-knockoutmotion receipts-countpower receiptsinstrument spotlight→Query your CSV with DuckDBcurate stages, statsLabels | |||||||
| 5 |  first render · fix pending shared field signature-3ddead_airgeneric_scene | futurist | 24.1–29.1s | spatial-parallax | icon·liquid-chrome | ♪ bed | The Stack |
expected on screen: red ground · cone hero in the shared Signal Field · Augur leads · spatial-parallax · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldshape coneground redtreatment liquid-chromemotion spatial-parallaxpower spatial-parallaxinstrument laser-fire→The Stack | |||||||
| 6 |  first render · fix pending shared field signature-3ddead_airgeneric_scene | resolve | 29.1–34.1s | coalescence | icon·liquid-chrome | ♪ bed_out | The Stack |
expected on screen: red ground · cone hero in the shared Signal Field · Augur leads · coalescence · coalescence · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual coalescenceshape coneground redtreatment liquid-chromemotion coalescencepower coalescenceinstrument coalescence→The Stack | |||||||
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)
tiktokThe stack: Google Sheets, until the file hits 100k rows and stalls. Export it to a CSV and point DuckDB at it, a tiny local engine that chews millions of rows in a blink. You still write plain SQL. (AI-assisted)
instagramThe stack:
Sheets dies at 100k rows.
Export to CSV.
Point DuckDB at it.
Million-row analysis, instant.
Still plain SQL.
#dataanalytics #duckdb #sql #datatools #buildinpublic
linkedinThe stack, in plain terms: every project starts in Google Sheets, until the file hits a hundred thousand rows and crawls.
So we export the sheet to a CSV and query it with DuckDB, a tiny local engine that chews through millions of rows in a blink. The analysis that froze your browser now runs instantly, and you still write plain SQL against your old spreadsheet.
Export your biggest sheet to a CSV and point DuckDB at it.
xThe stack: Google Sheets, until it hits 100k rows and stalls.
Export to a CSV and point DuckDB at it. A tiny local engine that chews millions of rows in a blink. Still plain SQL.
temerarii.xyz
facebookThe stack: every project starts in Google Sheets, until the file hits a hundred thousand rows and crawls.
Export it to a CSV and point DuckDB at it, a tiny local engine that chews millions of rows in a blink. You still write plain SQL. Try it: export your biggest sheet at temerarii.xyz.
threadsThe stack: Google Sheets, until the file hits 100k rows and stalls.
Export it to a CSV and point DuckDB at it. A tiny local engine that chews millions of rows in a blink.
You still write plain SQL.
pinterestGoogle Sheets data analysis tip: when a sheet hits a hundred thousand rows it crawls. Export it to a CSV and point DuckDB at it, a tiny free local engine that chews through millions of rows in a blink. You still write plain SQL against your old spreadsheet data.
blueskyThe stack: Google Sheets, until it hits 100k rows and stalls. Export to a CSV and point DuckDB at it. A tiny local engine that chews millions of rows in a blink. Still plain SQL.
youtubeTitle: When Google Sheets Dies, Point DuckDB at Your CSV
Every project starts in Google Sheets, until the file hits a hundred thousand rows and crawls. So we export the sheet to a CSV and query it with DuckDB, a tiny local engine that chews through millions of rows in a blink. The analysis that froze your browser now runs instantly, and you still write plain SQL.