I counted 150 AI video prompts, then built an n8n workflow that posts one a day

A developer built an n8n workflow that automatically posts one AI video prompt per day, complete with the clip it generated, sourced from a public library of 150 Seedance 2 video prompts. The workflow scrapes JSON-LD schema for stability and rotates prompts by day index. Analysis of the 150 prompts found a median length of 152 characters, with 46% specifying camera details and 34% splitting prompts by time ranges, suggesting that concise, structured prompts are more effective than long ones.

Most "prompt of the day" bots are a random line of text in a Slack channel. Nobody reads them, because a prompt with no output next to it is just a sentence. I wanted the opposite: one prompt a day, with the clip that prompt actually produced , and no credentials to set up. It turned into a small n8n workflow and a much more interesting question — what does a prompt that actually works look like, statistically? Six nodes, no API key, no account: sitemap.xml . day % total . h1 , the pre blocks, and the JSON-LD script tags. VideoObject schema, assemble a Slack-flavoured message. The source is a public library of Seedance 2 video prompts https://emaki.ai/prompt?ref=devto — 150 of them, each with the clip it generated. Rotate, don't randomize. Math.floor Date.now / 86400000 % urls.length gives you one prompt per day that is stable across re-runs. Math.random gives you duplicates within a week and a different result every time you debug. js const urls = ...xml.matchAll /<loc ^< + <\/loc /g .map m = m 1 .trim .filter u = u.includes '/prompt/' .filter u = u.includes '/prompt/category/' ; const dayIndex = Math.floor Date.now / 86400000 ; const url = urls dayIndex % urls.length ; Read the schema, not the layout. Every prompt page ships a VideoObject in JSON-LD with name , description and contentUrl . That is a stable contract; the rendered markup is not. Scraping the schema means a CSS refactor on their side does not silently break my workflow. js for const raw of item.structuredData || { const parsed = JSON.parse raw ; const blocks = Array.isArray parsed ? parsed : parsed ; const found = blocks.find b = b '@type' === 'VideoObject' ; if found { video = found; break; } } Count your selectors before you trust index 0. Each page has two <pre blocks: the Japanese original and the English version. cssSelector: "pre" with returnArray: false silently gives you the first one — so my first run posted Japanese into an English channel and looked completely fine. Set returnArray: true and choose explicitly. Since I had all 150 in a list, I counted them. Median prompt length is 152 characters . Longest is 215. That is roughly one sentence each for style, place, subject and motion. Every "advanced prompting guide" I have read implies the opposite — that control comes from length. In this corpus, it doesn't exist. Long prompts tend to contain contradicting instructions, and the model drops one of them, non-deterministically. Element frequency across the 150: | Element | Appears in | |---|---| | Camera / lens / framing | 69 / 150 46% | | Duration stated in seconds | 63 / 150 42% | | Lighting | 55 / 150 37% | | Cut structure | 22 / 150 15% | | Audio ambience, SFX, dialogue, ASMR | 22 / 150 15% | | Resolution 4K / 8K | 14 / 150 9% | | Slow motion | 4 / 150 3% | Two readings I'd stand behind: A third of the corpus 34/150 splits the prompt by time range rather than describing one continuous action: 00:00-00:05 intro, camera enters from behind the subject 00:05-00:10 turn, light source switches 00:10-00:15 wide, full scene That form clusters hard: sci-fi 9 , cinematic 7 , people 5 — and it is almost absent from scenery 2 and food 0 . It shows up exactly where order carries meaning . For a single continuous shot, stating total duration is enough. And 32 of 150 need a reference image rather than text alone. The tell is simple: the moment a prompt points at a specific person or a specific frame instead of a kind of thing, text can no longer specify it. That is the line between text-to-video https://emaki.ai/video?ref=devto and image-to-video https://emaki.ai/image-to-video?ref=devto . /slack to the webhook URL — it then accepts the same { "text": ... } payload. That's the whole thing. Everything it reads is public, so there is no credential step and nothing to rotate. The prompts themselves are written against Seedance 2.5 https://emaki.ai/seedance-2-5?ref=devto ; if you have not run one before, the walkthrough https://emaki.ai/how-to-use-seedance?ref=devto is shorter than this post. I wrote the full breakdown of all 150 — element frequency, duration patterns, the reference-image split by category — as a standalone reference https://hanshs474.gitbook.io/seedance-2-prompt-guide/ Japanese . There is also a Japanese write-up of the implementation https://qiita.com/hanshs474/items/9781f2a83abac5f260ae on Qiita if that is your reading language. If you build something similar against another corpus, the transferable part is not the scraping — it is checking whether the thing you are scraping publishes structured data first. It usually does, and it is usually more stable than the HTML around it.