agentsclimarketplace
Sign in

Seo eeat

Skill Hainrixz/claude-seo-ai/skills/seo-eeat

Audit and strengthen E-E-A-T and trust signals on a page — verify author identity/credentials (Person schema, byline, author page, sameAs), Organization about/contact/policies, visible experience/expertise markers, and transparency (sourcing, disclosures), and generate Person/Organization trust JSON-LD. Module M16. Feeds both the Search SEO and AI Visibility scores.From its SKILL.md

Install
npx -y skills add Hainrixz/claude-seo-ai --skill seo-eeat

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • runs commandsInstructs the agent to run 1 command, including `node ${CLAUDE_SKILL_DIR}/../../scripts/validate-jsonld.mjs --url <u>`.

SKILL.md

3.7 KB, 806 tokens by cl100k_base, as published. Nobody here has run it

seo-eeat (M16)

Experience, Expertise, Authoritativeness, and Trust are how both Google's quality systems and AI answer engines decide whether to rely on a page. Trust is foundational and now applies beyond YMYL. Schema details: references/schema-tier1.md.

Audits

Working from the PageSnapshot (rendered_dom if present, else raw_html):

  1. Author identity & credentials: is there a visible byline? A Person schema with name, jobTitle, knowsAbout, and sameAs[] (LinkedIn/Wikidata)? Does the byline link to an author/bio page? Are credentials/experience stated, not just a name?
  2. Organization trust: discoverable About and Contact pages; an Organization block with name, url, logo, contactPoint, sameAs[]; visible editorial/privacy/returns policies appropriate to the vertical.
  3. Experience & expertise markers: first-hand signals (original photos, "we tested", dates, methodology) and topical depth — not just generic prose.
  4. Transparency: sourcing/citations for claims, author disclosures (affiliate, sponsored, AI-assisted), last-reviewed dates. Defer the sameAs identity-graph detail to M6/seo-entity-linking.

Fixes

  • AUTO (fixable: auto): inject Person (author) and Organization trust JSON-LD built only from confirmed inputs — name, jobTitle, contactPoint, policy URLs the user supplies. The block is a diff for fix.
  • PROPOSED (fixable: proposed): draft a byline link or a sameAs set for per-item accept.
  • ADVISORY (fixable: advisory): writing real author bios, About/contact pages, or editorial policies — the tool never authors these. Never fabricate names, credentials, dates, or identity links — ask the user or leave a clearly-marked TODO placeholder.

Verification

  • Offline: node ${CLAUDE_SKILL_DIR}/../../scripts/validate-jsonld.mjs --url <u> plus dom_assert for visible byline/links/policy pages.
  • When confirming an identity link or a live About/contact page requires a fetch that is unavailable, status is needs_api — never a false pass.

Findings

Emit findings per schema/finding.schema.json. Examples:

  • M16.author.missing_person_schema — editorial page with a byline but no Person schema (status fail, severity 4, fixable: auto, axis both, confidence established).
  • M16.author.no_bio_page — byline does not link to an author/bio page (status warn, severity 3, fixable: proposed, axis both, confidence directional).
  • M16.org.no_contact_page — no discoverable About/Contact or contactPoint (status warn, severity 3, fixable: advisory, axis both, confidence directional). Each finding: evidence.observed quotes what is on the page; verification.reproduce is the runnable command above; expected_impact is banded + confidence-tagged (no naked %).

Honesty

  • E-E-A-T is not a single measurable score Google exposes — it is a quality framing assessed via many signals. Adding a Person block or an "author bio" is not a direct ranking lever; mark such impact directional, never as a guaranteed gain.
  • A fabricated author, invented credentials, or fake review markup is worse than none — it is a trust risk for Search and AI. The tool only emits trust signals the user can substantiate.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most marketing audience skills give in 806 tokens

Counted across 690 of the 894 authors here whose files we hold, read 2026-08-07

  • Apply Poppins font to headingsin 41 of 690, across 6 files
  • Apply Lora font to body textin 41 of 690, across 6 files
  • Use Arial fallback for headingsin 39 of 690, across 4 files
  • Use Georgia fallback for body textin 39 of 690, across 4 files
  • Maintain text hierarchy and formattingin 39 of 690, across 4 files
  • Use accent colors for non-text shapesin 38 of 690, across 3 files
  • Use RGB values for precise color matchingin 38 of 690, across 3 files
  • Use brand colors for primary text and backgroundsin 36 of 690, across 1 file
  • Read product marketing context file before asking questions, starting, or auditingin 35 of 690, across 23 files
  • Use active voice instead of passive voicein 26 of 690, across 10 files
  • Implement or generate appropriate JSON-LD structured datain 24 of 690, across 17 files
  • Prioritize clarity over clevernessin 22 of 690, across 8 files

Said here and by no other author read

  • emit findings per finding schema
  • validate transparency disclosures and review dates
  • inject Person and Organization JSON-LD from confirmed inputs
  • propose byline links or sameAs sets for acceptance

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.