agentsclimarketplace
Sign in

Seo entity linking

Skill Hainrixz/claude-seo-ai/skills/seo-entity-linking

Audit and generate entity & knowledge-graph linkage for a page — verify sameAs identity links (Wikidata/Wikipedia/LinkedIn/Crunchbase/official profiles) on Organization/Person, check NAP/entity consistency for local, confirm a defined primary entity, and measure entity density, then propose ready-to-inject sameAs/about/mentions references. Module M6. Feeds the AI Visibility score.From its SKILL.md

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

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

SKILL.md

3.7 KB, 844 tokens by cl100k_base, as published. Nobody here has run it

seo-entity-linking (M6)

Entity linkage tells search engines and AI systems which real-world thing a page is about and ties it to the Knowledge Graph. Reference: references/schema-tier1.md (the sameAs/@id/Person+Organization rules). This module owns the sameAs detail M5 defers here.

Audits

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

  1. sameAs identity links: for Organization/Person entities, check for sameAs[] resolving to canonical identities — Wikidata QID, Wikipedia, LinkedIn, Crunchbase, official social/company profiles. Wikidata is the strongest Knowledge Graph target.
  2. Primary entity defined: confirm exactly one clear primary entity per page (via @id + mainEntity/mainEntityOfPage), not an ambiguous or missing subject.
  3. Entity consistency (local): for LocalBusiness, verify NAP (name, address, telephone) in schema matches visible on-page NAP and is internally consistent across blocks.
  4. Entity density: count distinct linked/marked entities (@idd nodes, sameAs targets, about/mentions) — flag thin pages with no resolvable entity references.

Fixes

  • AUTO (fixable: auto): inject a sameAs[] array on Organization/Person using only user-confirmed URLs, and add about/mentions entity references to existing schema. Additive, deterministic diffs for fix. Never invent identity links — if a URL is unconfirmed, leave a clearly-marked TODO placeholder the user fills.
  • PROPOSED (fixable: proposed): a candidate Wikidata/LinkedIn match found by lookup — drafted for per-item human accept, never auto-written.
  • ADVISORY (fixable: advisory): "establish a Wikidata entity / claim profiles" when none exist — guidance only, the tool writes nothing.

Verification

  • dom_assert: confirm sameAs/@id/mainEntity present and well-formed in the parsed JSON-LD.
  • Resolve each sameAs URL (Tier 1 Wikidata lookup) to confirm it is live and refers to the asserted entity — a dead or mismatched link is a fail, not a pass.
  • When the live lookup tier is unavailable, status is needs_api, never a false pass.

Findings

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

  • M6.organization.missing_sameas — Organization has no sameAs[] (status fail, severity 4, fixable: proposed, axis ai, confidence directional).
  • M6.person.no_wikidata_link — author Person lacks a Wikidata/LinkedIn identity link (status warn, severity 2, fixable: proposed, axis ai, confidence directional).
  • M6.page.no_primary_entity — no single defined primary entity (@id/mainEntity) on the page (status warn, severity 4, fixable: advisory, axis ai, confidence directional). Each finding: evidence.observed quotes the page (the entity block or its absence); verification.reproduce is a runnable assertion/lookup; expected_impact is banded + confidence-tagged (no naked %).

Honesty

  • A sameAs link does not force entry into the Knowledge Graph and produces no guaranteed ranking lift — it is a disambiguation signal, so impact is directional/ai, not established.
  • Never fabricate, guess, or "best-effort" an identity URL to inflate entity density — a wrong sameAs actively misleads engines. Confirmed-only, or leave it as a TODO.

What ships with it

Read from the repository

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

Gives 0 of the 12 instructions most quality gates skills give in 844 tokens

Counted across 1,524 of the 2,830 authors here whose files we hold, read 2026-09-06

  • Read full output and check exit codein 45 of 1524, across 40 files
  • Verify output confirms the claimin 44 of 1524, across 39 files
  • Identify the command that proves the claimin 43 of 1524, across 39 files
  • Execute the full verification commandin 36 of 1524, across 30 files
  • Produce a verification reportin 34 of 1524, across 18 files
  • Review git diff changesin 30 of 1524, across 16 files
  • Fix build failures immediatelyin 29 of 1524, across 9 files
  • Group findings by severityin 28 of 1524
  • State claim only with evidencein 27 of 1524, across 22 files
  • Verify regression tests with red-green cyclein 26 of 1524, across 22 files
  • Run the full test suitein 26 of 1524, across 25 files
  • Run test suite with coveragein 25 of 1524, across 10 files

Said here and by no other author read

  • Verify sameAs identity links for Organization and Person
  • Confirm exactly one primary entity per page
  • Verify NAP consistency for LocalBusiness
  • Count distinct linked or marked entities
  • Inject sameAs arrays using only confirmed URLs
  • Add about and mentions references to schema

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.