mcpbeat Sign in

Eeat Audit Agent Skill

Use when auditing a page for E-E-A-T signals. The agent reads the page and scores Experience, Expertise, Authoritativeness, and Trustworthiness — then tells you exactly what to add to each dimension.

19k tokens
context cost
the whole folder, loaded on every use
12
files
instructions only
0
copies elsewhere
how many repositories repackaged it
239
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/inhouseseo/superseo-skills --skill eeat-audit

The instruction itself

18 sections, as written by the author

E-E-A-T Audit

Scores a page on Experience, Expertise, Authoritativeness, and Trustworthiness — the four signals Google's quality raters use to evaluate content. Tells you what's missing and how to add it.

Real E-E-A-T is demonstrated, not declared. An author bio is table stakes. What matters is whether the content *feels* like it was written by someone who has actually done the thing.

Input

URL of the page to audit. If the fetch fails, ask the user to paste the content directly.

Role

You are a senior content quality evaluator with 10+ years reading for Google's quality rater framework. You can tell within 30 seconds of reading whether an author has done the thing they're writing about.

Step 1: Read the Page

Fetch and read the full rendered page. Note everything that could be an E-E-A-T signal:

  • Author name, bio, credentials
  • Byline with publication date
  • First-person language ("I tried...", "we found...", "when I was at...")
  • Specific anecdotes, names, numbers, dates
  • Original photos, screenshots, diagrams
  • Quoted sources, linked references
  • Schema markup (Person, Author, Organization)
  • About page linked from the article
  • External references to the author or publication

Step 2: Score Each Dimension (1-10)

Experience (the most underrated E-E-A-T factor)

What you're looking for: evidence the author has DONE the thing, not just researched it.

Strong signals (8-10):

  • First-person observations with specific details
  • "When I tried this, X happened"
  • Original photos/screenshots from the author's own work
  • Failure stories with specific lessons
  • Details only hands-on experience would know (the "smell test")
  • A story that reveals workflow, not just outcomes

Weak signals (4-6):

  • Generic advice that anyone could write after 30 minutes of research
  • Third-person narration of other people's case studies
  • Examples that feel plucked from Google
  • "According to studies..." without identifying which ones

Absent (1-3):

  • No first-person anywhere
  • No specific stories
  • No details beyond what's already on the top 10 ranking pages

Expertise

What you're looking for: accurate facts and depth beyond surface level.

Strong signals:

  • Every factual claim is accurate and verifiable
  • Numbers cited with primary sources (original research, not "studies show")
  • Technical details correctly used (terminology, processes, edge cases)
  • Willingness to disagree with common advice when the author has a reason
  • Depth beyond what a smart generalist could produce in 30 minutes

Weak signals:

  • Accurate but shallow
  • Secondary sources cited (blog posts citing blog posts)
  • Common advice repeated without critique

Absent:

  • Factual errors
  • Outdated information presented as current
  • Surface-level "what Google says" summary

Authoritativeness

What you're looking for: does this content and author belong in the conversation?

Strong signals:

  • Page is part of a broader topical cluster on the domain
  • Author expertise is verifiable beyond a bio paragraph (LinkedIn, talks, books, citations elsewhere)
  • External sites cite this page or author
  • Clear track record on this specific topic

Weak signals:

  • Isolated page on a broad topic site
  • Generic author with no verifiable specialty
  • No external validation

Absent:

  • Random blog post with no author attribution
  • Site has no topical focus
  • No internal linking cluster

Trustworthiness

What you're looking for: transparency and honesty.

Strong signals:

  • Transparent about limitations ("this didn't work when X")
  • Discloses conflicts of interest (affiliate links, paid placements)
  • Methodology explained
  • Willingness to recommend alternatives, even competitors
  • Factually accurate throughout
  • Recent publish/update date for time-sensitive topics

Weak signals:

  • Feels like an advertorial but doesn't disclose
  • Hides limitations
  • Methodology unclear

Absent (1-3):

  • Factual errors
  • Affiliate-driven content without disclosure
  • Misleading claims
  • Outdated information on a time-sensitive topic

Step 3: Output

E-E-A-T Scorecard

| Signal | Score | Key Gap |

|---|---|---|

| Experience | /10 | |

| Expertise | /10 | |

| Authoritativeness | /10 | |

| Trustworthiness | /10 | |

| Total | /40 | |

What's Working

Specific observations. "The screenshot in Section 3 is clearly from the author's own dashboard — this is a strong Experience signal."

What's Missing

Specific gaps with specific fixes:

  • "No first-person observations in the first 500 words. Add: 'When I first tested this at [company name], the result surprised me — [specific outcome].'"
  • "The claim about 42% improvement isn't sourced. Either cite the primary study or drop the number."
  • "No author bio links to a LinkedIn or profile page. Add: a one-sentence bio with a credential anchor and an external link to the author's profile."

Fastest Wins

Three changes you could make in under 30 minutes that would lift the E-E-A-T score materially. Ordered by impact.

Structural Recommendations

Things that require more work but would fundamentally strengthen E-E-A-T: adding a methodology section, linking to related topical cluster pages, adding Author schema markup, creating an About page for the author.

What to Ignore

  • Generic "add author bio" advice — it's table stakes, not E-E-A-T
  • Schema without substance — marking up a page with Person schema when the content shows no experience is worse than no schema
  • Gaming quality rater signals — the raters aren't fooled, and the algorithm isn't either

Next Step

To apply the fixes: use the improve-content skill with this URL, and paste the gap list as context.

Bundled references

Load from references/ only when the step calls for them.

Scoring and diagnosis:

  • ymyl-scoring-rubric.md — stricter scoring rubric for Your Money Your Life pages (finance, medical, legal) where the E-E-A-T bar is materially higher (Step 2, any YMYL page)
  • experience-detection-playbook.md — how to tell in 30 seconds whether an author has done the thing (Experience dimension, when the page looks ambiguous)
  • fastest-eeat-wins.md — ranked list of the highest-impact E-E-A-T fixes by implementation effort (Step 3, "Fastest Wins" block)
  • eeat-signal-embedding.md — how to surface experience without a bio section or fake credentials (Step 3, "Structural Recommendations")
  • author-schema-templates.md — copy-paste Person / Author / Organization JSON-LD for the schema fix (Step 3)

YMYL content-type templates (references/content-types/) — load when auditing one of these types for the type-specific E-E-A-T bar:

  • thought-leadership.md, product-reviews.md, pricing-pages.md, service-pages.md, case-studies.md, about-pages.md

Other skills for the same job

different authors, same section of the catalogue
Protocolsio Integration
by christophacham
×4

Integration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io functionality into workflows. Applicable for protocol discovery, collaborative protocol development, experiment tracking, lab protocol management, and scientific documentation.

16k tokens
Tailored Resume Generator
by frostant
×4

Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances

3k tokens
Excalidraw Diagram Generator
by github
vendor ×3

Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.

36k tokens scripts
Expo Dev Client
by openai
vendor ×3

Build and distribute Expo development clients locally or via TestFlight

961 tokens
Executing Plans
by ZhanlinCui
×3

Use when you have a written implementation plan to execute in a separate session with review checkpoints

542 tokens
Anndata
by christophacham
×3

Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.

16k tokens
Benchling Integration
by christophacham
×3

Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.

14k tokens
Biopython
by christophacham
×3

Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.

24k tokens

How to use it

Copy the folder

Take inhouseseo/eeat-audit from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.