Every blog post Claude Blog generates gets a score from 0 to 100. That score is not a single number. It is the weighted sum of 5 categories, each measuring a different dimension of content quality. Understanding how scoring works helps you write better content, whether you use Claude Blog or not.

Run /blog analyze on any Markdown or HTML file to get your score. The analysis takes under 10 seconds and outputs category breakdowns, specific issues, and improvement recommendations. You can explore the full skill documentation at /skills/blog-analyze.

The 5 scoring categories

Each category has a fixed weight that determines its contribution to the final score. Here is the breakdown:

CategoryWeightWhat it measures
Content Quality30%Depth, accuracy, readability, structure, word count
SEO25%Title tags, meta descriptions, headings, keywords, internal links
E-E-A-T15%Experience, expertise, authoritativeness, trustworthiness
Technical15%Schema markup, canonical URLs, OG tags, sitemap inclusion
AI Citation15%Passage citability, structural readability, GEO readiness
Scoring Category Breakdown - 100 Point System 100 POINTS Content Quality 30% SEO 25% E-E-A-T 15% Technical 15% AI Citation 15%
The 5 scoring categories and their weights in the 100-point system

Content Quality (30%)

This is the heaviest category because content quality is the foundation everything else builds on. It evaluates:

  • Word count: Does the article meet the target length for its template type?
  • Heading structure: Clean H1 to H2 to H3 hierarchy with no skipped levels
  • Paragraph length: Short paragraphs (2-4 sentences) for readability
  • Readability score: Flesch-Kincaid grade level appropriate for the target audience
  • Content depth: Presence of data, examples, statistics, and actionable advice
  • Introduction quality: Does the opening paragraph clearly state what the reader will learn?

SEO (25%)

The SEO category checks whether your content follows on-page SEO best practices:

  • Title tag: Under 60 characters, includes primary keyword
  • Meta description: 120-160 characters, compelling and keyword-relevant
  • H1 tag: Exactly one per page, includes primary keyword
  • Keyword distribution: Natural placement in headings, first paragraph, and body
  • Internal links: At least 2-3 links to related content
  • External links: References to authoritative sources
  • Image alt text: Descriptive alt attributes on all images

E-E-A-T (15%)

Google's E-E-A-T framework (Experience, Expertise, Authoritativeness, Trustworthiness) is critical for content credibility. The scoring checks:

  • Author attribution: Named author with credentials or bio link
  • Publication date: Visible date with datetime attribute
  • Source citations: Claims backed by data, studies, or documentation
  • First-person experience: Evidence of hands-on knowledge, not just summarized research
  • Trust signals: HTTPS, privacy policy link, contact information

Technical (15%)

Technical quality ensures your content is properly formatted for search engines and social platforms:

  • Schema markup: BlogPosting or Article JSON-LD present and valid
  • Canonical URL: Properly set to prevent duplicate content issues
  • Open Graph tags: Title, description, image, and URL for social sharing
  • Sitemap inclusion: URL present in sitemap.xml
  • Mobile responsiveness: Content renders correctly on mobile viewports

AI Citation (15%)

This category measures how well your content is structured for citation by AI search engines like Google AI Overviews, ChatGPT, and Perplexity:

  • Passage citability: Self-contained answer blocks of 134-167 words
  • Question-answer patterns: Headings phrased as questions with direct answers
  • Data density: Specific statistics, numbers, and facts that AI can extract
  • Structural clarity: Lists, tables, and clear formatting that AI systems parse easily
  • Entity clarity: Brand names, product names, and people clearly identified

Scoring bands

The 0-100 score maps to four quality bands:

ScoreBandMeaning
90-100ExcellentPublication-ready, exceeds standards
80-89GoodPublication-ready, minor improvements possible
60-79Needs WorkTargeted improvements required before publishing
0-59PoorSignificant revision needed
Score Bands - 0 to 100 Quality Scale REWRITE BELOW OK STRONG EXCL. 0 60 70 80 90 100
Score bands from 0 (rewrite) to 100 (exceptional)

The average first-draft score from Claude Blog's 4-agent pipeline is typically 72-85, depending on topic complexity and template. One round of human editing usually pushes scores into the 85-95 range.

AI detection analysis

Claude Blog's scoring includes an AI detection component that helps you identify content that reads as machine-generated. This is not about hiding AI usage. It is about ensuring your content has the variation and specificity that readers expect from quality writing.

Three signals are checked:

Burstiness

Burstiness measures the variation in sentence length throughout your content. Human writing naturally alternates between short, punchy sentences and longer, more complex ones. AI-generated text tends toward uniform sentence lengths. Low burstiness is a red flag.

Fix: Vary your sentence length. Follow a long, detailed sentence with a short one. Break up lists with narrative paragraphs.

Common AI phrase detection

Certain phrases appear far more frequently in AI-generated text than in human writing. Examples include "in today's digital landscape," "it's important to note that," and "dive deep into." The scorer flags these overused patterns.

Fix: Replace flagged phrases with specific, concrete language. Instead of "in today's digital landscape," state the specific context: "Since Google's March 2026 core update."

Type-token ratio (TTR)

TTR measures vocabulary diversity: the ratio of unique words to total words. AI-generated content often has lower TTR because it reuses the same vocabulary patterns. Human writing tends to use a wider range of words.

Fix: Use synonyms intentionally. Replace repeated words with alternatives. Add domain-specific terminology that demonstrates expertise.

How to improve each category

Here are targeted improvements for each scoring category:

  • Content Quality (+5-15 points): Add a data point or statistic to every H2 section. Include at least one real example.
  • SEO (+5-10 points): Add 2-3 internal links. Ensure your title tag is under 60 characters. Write a meta description.
  • E-E-A-T (+5-10 points): Add an author byline with a link to your credentials. Include a publication date. Cite your sources.
  • Technical (+5-10 points): Add BlogPosting schema. Set a canonical URL. Add Open Graph tags.
  • AI Citation (+5-10 points): Restructure one section into a self-contained 150-word answer block. Add a question-based heading.