/seo-content-blog

name: seo-content-blog
description: "Write blog articles that rank on Google and get cited by AI engines (ChatGPT, Perplexity, AI Overviews). Input: a keyword, topic, or existing draft. Output: a publish-ready article, outline, or brief built on a 12-element answer-first skeleton (question H2s, expert quotes, stats, FAQ, internal links, SERP-benchmarked length). Use when writing, rewriting, refreshing, or auditing a blog post, or when one will not rank or get cited by AI engines."
license: MIT
metadata:
  author: "Sorank (https://sorank.com)"
  version: "1.0.0"

SEO Blog Content That Ranks and Gets Cited

Write or rewrite blog articles on a 12-element skeleton (field methodology from 115+ agency audits, layered with 2024-2026 citation research) so the same article ranks in Google and gets extracted as an answer by ChatGPT, Perplexity, and Google AI Overviews.

Company knowledge first (Obsidian)

If the working environment contains an Obsidian vault or any local knowledge base (a folder of .md notes, often with a .obsidian directory), read the relevant notes before acting: brand and product facts, target keywords, competitors, and the SEO action log of what was already tried. Ground every recommendation in that context instead of asking the user for facts the vault already holds. At the end of the session, append the actions taken to the vault's SEO action log so the next session starts informed. Vault structure, read-first and write-back protocols: the obsidian-brain skill.

When to use

• Writing a new blog article from a keyword, topic, or brief.
• Rewriting or refreshing a published post that decayed or never ranked.
• Reviewing a human-written or AI-generated draft before publication.
• Producing an outline or content brief for a writer.
• Planning publication cadence for a blog launch or an established site.

Route adjacent jobs to their own skills:

• Choosing the target keyword, mapping intent, splitting overlapping topics: seo-keyword-research.
• Product, service, or collection page copy: seo-content-product-page, seo-content-service-page, seo-content-collection-page.
• Site-level link routing and silos: seo-internal-linking. Full site diagnosis: seo-geo-audit.

Workflow

Step 1. Lock the target

Confirm before writing:

• Primary keyword and the intent behind it (informational or commercial investigation).
• Language and market: a French SERP and a US SERP rarely reward the same article.
• The commercial pages this article must support with internal links.
• Whether an existing article already covers this intent. If yes, rewrite it instead of creating a new one.

Enforce one angle = one article: two articles on the same intent cannibalize each other and split clicks, links, and signals (merge test in seo-keyword-research).

Step 2. Read the SERP before writing a single line

Fetch the top 3-5 Google results for the keyword and record:

| Per competitor | Why it matters | |---|---| | Word count | Sets the length floor; never come in under the median | | H2 structure and questions answered | The subtopics Google already rewards; this is the coverage checklist | | Tables, images, videos used | The formats the query expects | | Publication and update dates | The freshness bar; an aging SERP is an opening | | People Also Ask questions | Raw material for the FAQ and the question H2s |

For on-page fact collection, run the bundled audit script from the seo-geo-audit skill (scripts/seo_audit.py). Why this step exists: the SERP is the specification. Google is showing what it already considers a satisfying answer for this query; writing blind produces a worse copy of it.

Step 3. Set the length from the benchmark

Target the median of the ranking pages or above (thresholds table below). Never plan a rewrite shorter than the page it replaces: replacing long ranking content with shorter content is one of the most common self-inflicted ranking losses observed in audits.

Step 4. Define the information gain

Name at least one element the current top 5 do not have:

• Original data: your numbers, a small survey, aggregated anonymized client results.
• First-hand experience: you ran the process, with outcomes and photos.
• An expert quote collected for this article.
• A comparison table no competitor built.
• A fresher statistic, with its source linked.

Why: Google holds a patent on scoring pages by information gain (US 11,354,342, "Contextual estimation of link information gain"; a patent signals research direction, not confirmed production use); a page that restates the SERP gives the index no reason to rank it and gives AI engines no reason to cite it. This step is also what makes AI-assisted drafting safe (rules below).

Step 5. Draft on the 12-element skeleton

Next section. Write the body first; write the title and meta description last, they are sharper once the article exists.

Step 6. Layer the GEO elements

• Answer-first block at the top.
• Self-contained H2 sections (chunk autonomy).
• At least one expert quote and at least two statistics with sources cited inline.

These are the interventions with measured visibility gains in generative engines (see GEO layer).

Step 7. Place the links

• 3-5 external authority sources, the first inside the intro.
• 3-5 internal links to commercial pages, styled visibly.

Anchor rules and site-level architecture: seo-internal-linking.

Step 8. Finalize assets and metadata

• 3 images (1 cover + 2 in body), alt text on all, WebP, 200 KB max each.
• FAQ built from 3 real People Also Ask questions.
• Title 30-60 characters, meta description 120-160 characters.
• Natural-language slug containing the keyword (measured citation gap in the GEO layer).

Step 9. Verify

Run the pre-publish checklist (Output format section), then sweep the Common mistakes list.

The 12-element article skeleton

Apply every element. Each one exists because its absence showed up as a recurring loss across 115+ agency a