Entity Optimizer

Entity Optimizer

Audits, builds, and maintains entity identity across search engines and AI systems. Entities — the people, organizations, products, and concepts that search engines and AI systems recognize as distinct things — are the foundation of how both Google and LLMs decide what a brand is and whether to cite it.

Why entities matter for SEO + GEO:

• SEO: Google's Knowledge Graph powers Knowledge Panels, rich results, and entity-based ranking signals. A well-defined entity earns SERP real estate.
• GEO: AI systems resolve queries to entities before generating answers. If an AI cannot identify an entity, it cannot cite it — no matter how good the content is.

What This Skill Does

Audits entity presence across Knowledge Graph, Wikidata, Wikipedia, and AI systems; maps all 6 signal categories (47 signals); produces a gap analysis, building plan, and disambiguation strategy.

Quick Start

Start with one of these prompts. Finish with a canonical entity profile and a handoff summary using the repository format in Skill Contract.

Entity Audit

Audit entity presence for [brand/person/organization]

How well do search engines and AI systems recognize [entity name]?

Build Entity Presence

Build entity presence for [new brand] in the [industry] space

Establish [person name] as a recognized expert in [topic]

Fix Entity Issues

My Knowledge Panel shows incorrect information — fix entity signals for [entity]

AI systems confuse [my entity] with [other entity] — help me disambiguate

Skill Contract

Expected output: an entity audit, a canonical entity profile, and a short handoff summary ready for memory/entities/.

• Reads: the entity name, primary domain, known profiles, topic associations, and prior brand context.
• Writes: a user-facing entity report plus a reusable profile that can be stored under memory/entities/.
• Promotes: canonical names, sameAs links, disambiguation notes, and entity gaps to memory/hot-cache.md, memory/entities/, and memory/open-loops.md.
• Done when: the 6 signal categories are each scored Pass/Fail/Partial, the AI-resolution test is run (or flagged as user-to-run), and a canonical profile plus top-5 priority actions are produced.

This skill is the sole writer of canonical entity profiles at memory/entities/<name>.md. Other skills write entity candidates to memory/entities/candidates.md only. When 3+ candidates accumulate, this skill should be recommended.

Profile schema: the frontmatter of every canonical entity profile follows the authoritative contract in Entity-GEO Handoff Schema. That schema defines which fields downstream skills (geo-content-optimizer, schema-markup-generator, meta-tags-optimizer, ai-overview-recovery) depend on. Do not omit required fields — the consumers will degrade gracefully to DONE_WITH_CONCERNS and surface an open_loop pointing back here.

• Primary next skill: use the Next Best Skill below once the entity truth is clear.

Handoff Summary

Emit the standard shape from skill-contract.md §Handoff Summary Format.

Data Sources

With tools: query Knowledge Graph API, ~~SEO tool, ~~AI monitor, ~~brand monitor. Without tools: ask the user for entity name/type, domain, profiles, topics, and disambiguation context. See CONNECTORS.md.

Zero-dependency local helper (keyless): python3 "${CLAUDE_PLUGIN_ROOT}/scripts/connectors/kg.py" reconcile "<entity>" resolves the name to a Wikidata QID with a confidence score (does the open KG that feeds Knowledge Panels & AI answers recognize it?); kg.py entity <QID> returns claims + sameAs. See scripts/connectors/README.md.

Decision Gates

Stop and ask the user when:

• No entity name is provided and none is inferable from project context — ask for the entity name and type before auditing.
• The entity is an individual (founder, author, public figure) who may be an EU/EEA/UK resident, before writing to memory/entities/ — prompt: "You are about to create a canonical profile for a person. If this person is or may be an EU/EEA/UK resident, GDPR Art 6 requires a lawful basis: (1) consent, (2) legitimate interest, (3) contract, (4) other. For non-EU subjects, check local regimes (CCPA/CPRA, PIPEDA, LGPD, etc.). If unsure, skip and return NEEDS_INPUT." Only proceed once the user confirms a basis. Advisory only — not legal advice. Reference: Memory Management — GDPR / Privacy Compliance.

Continue silently (never stop for):

• Missing ~~AI monitor or ~~knowledge graph tool access — mark those rows as user-to-run and proceed with user-provided observations.
• Individual signals being unknown — score them Partial with a verification action and continue.

Instructions

When a user requests entity optimization:

Step 1: Entity Discovery

Establish the entity's current state across all systems.

### Entity Profile

**Entity Name**: [name]
**Entity Type**: [Person / Organization / Brand / Product / Creative Work / Event]
**Primary Domain**: [URL]
**Target Topics**: [topic 1, topic 2, topic 3]

#### Current Entity Presence

| Platform | Status | Details |
|----------|--------|---------|
| Google Knowledge Panel | ✅ Present / ❌ Absent / ⚠️ Incorrect | [details] |
| Wikidata | ✅ Listed / ❌ Not listed | [QID if exists] |
| Wikipedia | ✅ Article / ⚠️ Mentioned only / ❌ Absent | [notability assessment] |
| Google Knowledge Graph API | ✅ Entity found / ❌ Not found | [entity ID, types, score] |
| Schema.org on site | ✅ Complete / ⚠️ Partial / ❌ Missing | [Organization/Person/Product schema] |

#### AI Entity Resolution Test

**Note**: Claude cannot directly query other AI systems or perform real-time web searches without tool access. When running without ~~AI monitor or ~~knowledge graph tools, ask the user to run these test queries and report the results, or use the user-provided information to assess entity presence.

Test how AI systems identify this entity by querying:
- "What is [entity name]?"
- "Who founded [entity name]?" (for organizations)
- "What does [entity name] do?"
- "[entity name] vs [competitor]"

| AI System | Recognizes Entity? | Description Accuracy | Cites Entity's Content? |
|-----------|-------------------|---------------------|------------------------|
| ChatGPT | ✅ / ⚠️ / ❌ | [accuracy notes] | [yes/no/partially] |
| Claude | ✅ / ⚠️ / ❌ | [accuracy notes] | [yes/no/partially] |
| Perplexity | ✅ / ⚠️ / ❌ | [accuracy notes] | [yes/no/partially] |
| Google AI Overview | ✅ / ⚠️ / ❌ | [accuracy notes] | [yes/no/partially] |

Step 2: Entity Signal Audit

Evaluate entity signals across 6 categories. For the detailed 47-signal checklist with verification methods, see Entity Signal Checklist.

Evaluate each signal as Pass / Fail / Partial with a specific action for each gap. The 6 categories are:

1. Structured Data Signals — Organization/Person schema, sameAs links, @id consistency, author schema
2. Knowledge Base Signals — Wikidata, Wikipedia, CrunchBase, industry directories
3. Consistent NAP+E Signals — Name/description/logo/social consistency across platforms
4. Content-Based Entity Signals — About page, author pages, topical authority, branded backlinks
5. Third-Party Entity Signals — Authoritative mentions, co-citation, reviews, press coverage
6. AI-Specific Entity Signals — Clear definitions, disambiguation, verifiable claims, crawlability

Reference: Use the audit template in Entity Signal Checklist for the full 47-signal checklist with verification methods for each category.

Step 3: Report & Action Plan

Produce an Entity Optimization Report with: overview (entity/type/date), signal category summary (6-category ✅/⚠️/❌ table with findings), critical issues, top 5 priority actions (impact × effort), entity building roadmap (Week 1-2 → Month 1 → Month 2-3 → Ongoing), and CORE-EEAT A07/A08 + CITE I01-I10 cross-reference.

Reference: See Entity Signal Checklist for the full Step 3 report template.

Save Results

Ask "Save these results for future sessions?" (see Skill Contract §Save Results Template) — if yes, write the canonical entity profile to memory/entities/<entity-slug>.md using the Profile schema above. If the entity is project-critical, also add a 1-3 line pointer to memory/hot-cache.md; do not save canonical profiles to the generic memory/YYYY-MM-DD-<topic>.md pattern.

Before writing any canonical profile, check memory/audits/gdpr-purges.md for a prior purge of this entity (by redacted label or domain). If one exists, do not silently recreate the profile; return NEEDS_INPUT and ask the user to confirm the entity should be re-added.

Example

User: "Audit entity presence for Acme Analytics, our B2B SaaS analytics platform at acme-analytics.example"

Output (abbreviated): AI resolution test shows partial recognition — ChatGPT described it as a generic "analytics tool" without B2B specificity; not listed among enterprise analytics players; founder unknown to AI systems. Health summary flags a missing Wikidata entry and no Knowledge Panel, with priority actions covering Wikidata submission, sameAs links, and a founder-bio page.

Reference: See Example Audit Report for the full entity audit report including AI resolution test results, entity health summary, top 3 priority actions, and CORE-EEAT/CITE cross-references.

Entity Type Reference

Reference: See Entity Type Reference for entity types with key signals, schemas, and disambiguation strategies by situation.

Knowledge Panel & Wikidata Optimization

Reference: See Knowledge Panel & Wikidata Guide for Knowledge Panel claiming/editing, common issues and fixes, Wikidata entry creation, key properties by entity type, and AI entity resolution optimization.

Reference Materials

Detailed guides for entity optimization:

• Entity Signal Checklist — Complete signal checklist with verification methods, Step 3 report template, and Tips for Success
• Knowledge Graph Guide — Wikidata, Wikipedia, and Knowledge Graph optimization playbook

Next Best Skill

Primary: schema-markup-generator. Also consider: geo-content-optimizer (AI recognition gap) or seo-content-writer (new About/founder page needed).