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.
适合你,如果做SEO需要检查实体链接和知识图谱引用
用别的 agent?下载 .zip 解压,把文件夹放进它的技能目录
~/.claude/skills/(项目级 .claude/skills/)~/.codex/skills/npx oh-my-skill add hainrixz/claude-seo-ai/seo-entity-linkingcurl -fsSL https://oh-my-skill.com/install.sh | bash -s -- hainrixz/claude-seo-ai/seo-entity-linkingnpx oh-my-skill verify hainrixz/claude-seo-ai/seo-entity-linking怎么用
技能原文 SKILL.md
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):
- sameAs identity links: for
Organization/Personentities, check forsameAs[]resolving to canonical identities — Wikidata QID, Wikipedia, LinkedIn, Crunchbase, official social/company profiles. Wikidata is the strongest Knowledge Graph target. - Primary entity defined: confirm exactly one clear primary entity per page (via
@id+mainEntity/mainEntityOfPage), not an ambiguous or missing subject. - Entity consistency (local): for
LocalBusiness, verify NAP (name, address, telephone) in schema matches visible on-page NAP and is internally consistent across blocks. - Entity density: count distinct linked/marked entities (
@idd nodes,sameAstargets,about/mentions) — flag thin pages with no resolvable entity references.
Fixes
- AUTO (
fixable: auto): inject asameAs[]array onOrganization/Personusing only user-confirmed URLs, and addabout/mentionsentity references to existing schema. Additive, deterministic diffs forfix. Never invent identity links — if a URL is unconfirmed, leave a clearly-markedTODOplaceholder 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: confirmsameAs/@id/mainEntitypresent and well-formed in the parsed JSON-LD.- Resolve each
sameAsURL (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 falsepass.
Findings
Emit findings per schema/finding.schema.json. Examples:
M6.organization.missing_sameas—Organizationhas nosameAs[](statusfail, severity 4,fixable: proposed, axisai, confidencedirectional).M6.person.no_wikidata_link— authorPersonlacks a Wikidata/LinkedIn identity link (statuswarn, severity 2,fixable: proposed, axisai, confidencedirectional).M6.page.no_primary_entity— no single defined primary entity (@id/mainEntity) on the page (statuswarn, severity 4,fixable: advisory, axisai, confidencedirectional).
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
sameAslink does not force entry into the Knowledge Graph and produces no guaranteed ranking lift — it is a disambiguation signal, so impact isdirectional/ai, notestablished. - Never fabricate, guess, or "best-effort" an identity URL to inflate entity density — a wrong
sameAsactively misleads engines. Confirmed-only, or leave it as a TODO.