Loading page...Загружаем страницу...正在加载页面...
AtlasRepo

The Hook Factory: 5 Prompt Angles I Automated in n8n (Steal the System)

说明与用途

n8n 工作流自动生成五种不同的 Hook,节省时间并提升内容吸引力。

问题

Content creators spend a disproportionate amount of time crafting the first two lines of a post, the hook, which determines reader engagement.

结果

The workflow produces five hook variants—Curiosity gap, Contrarian take, Specific number, Micro‑story, Direct callout—per post, with a 12‑second run time and under a cent cost per batch. Two hooks outperformed the rest of the series combined on comments.

工作流

  • Set node: input post topic
  • Parallel branches: five LLM calls, each with its own system instruction and two few‑shot examples
  • Merge node: Code node assembles strict JSON output
  • Dedup guard: reject hooks sharing >60% content words, re‑run once
  • Human selection: pick best hook

证据

I tracked it for a month: on a typical 800-word post, I spent 40% of the time on the hook and 60% on everything else.

来源

The workflow runs on my laptop's n8n before I write a single word of the article. Twenty minutes of staring, replaced by a 12-second run and a 2-minute pick-the-best.

来源

Five LLM calls, ~400 tokens each, on GPT-4o-mini: under a cent per batch of five hooks.

来源

  • 记录日期: 2026-10-16T06:41:11.938Z