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

The SEO Blog Engine: A Teardown of the n8n Workflow That Writes My Drafts

说明与用途

n8n 工作流生成 SEO 博客草稿,通过可读性评分、引用来源的提纲和在 Markdown 渲染前的 JSON 模式校验,解决关键词堆砌、虚构提纲和格式漂移问题。

问题

Automated LLM workflow produced drafts with keyword stuffing, invented outlines, and formatting drift, causing unreadable content and CMS import failures.

结果

The workflow now produces SEO‑ready drafts that are readable, source‑referenced, and CMS‑compatible, reducing manual editing time to about 6 minutes per article.

工作流

  • Keyword input → research pass pulls top‑ranking pages’ subheadings
  • Outline node generates H2s citing each subheading
  • Draft node writes sections against a style contract
  • Schema guard validates structured JSON before Markdown rendering
  • Publish‑ready Markdown output

证据

The first drafts read like 2012. The model had absorbed a decade of "SEO writing" and produced sentences like "this n8n automation workflow template helps you automate workflows with automation." Technically keyword-rich. Unreadable.

来源

The fix was a readability penalty in the scoring rubric: every draft gets scored on a 0–10 scale where keyword stuffing and repeated phrases subtract points, and the draft only ships at 7+. The prompt didn’t change much — the judge changed.

来源

The outline must cite its sources line by line. Every H2 carries a reference to a real subheading from the research pass, and the draft node is forbidden from introducing new H2s.

来源

The fix was a schema guard before the Markdown render: the draft is produced as structured JSON (sections, headings, code blocks, tables as typed fields), validated against a schema, and only then rendered to Markdown.

来源

  • 记录日期: 2026-10-16T22:41:15.166Z