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 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/privacy/tombstones.md for a matching salted fingerprint or redacted label. If reingest_blocked: true, do not recreate the profile; return NEEDS_INPUT and ask the user to resolve the privacy block.

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 missing Wikidata entry, no Knowledge Panel, and 3 priority actions — 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.

Tips for Success

Reference: See Entity Signal Checklist for the full 7-item Tips for Success list (start with Wikidata, leverage sameAs, test AI recognition before/after, compounding signals, consistency > completeness, disambiguation-first, pair with CITE I-dimension).

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).

Entity Signal Checklist

Part of entity-optimizer. See also: knowledge-graph-guide.md

Work through signals by priority tier. Mark each: present/correct, incomplete, or absent.

Priority 1: Foundation Signals (Must-Have)

On-Site Structured Data

Key External Profiles

Branded Search Presence

Priority 2: Authority Signals (Should-Have)

Knowledge Graph Depth

Third-Party Validation

Content Authority

Priority 3: AI-Specific Signals (Must-Have for GEO)

AI Recognition

AI Optimization

Priority 4: Advanced Signals (Nice-to-Have)

Priority Action Matrix

---

Report & Action Plan Template

## Entity Optimization Report
- **Entity**: [name] | **Type**: [type] | **Date**: [date]

### Signal Category Summary
| Category | Status | Key Findings |
|----------|--------|-------------|
| Structured Data | Strong / Gaps / Missing | [findings] |
| Knowledge Base | Strong / Gaps / Missing | [findings] |
| Consistency (NAP+E) | Strong / Gaps / Missing | [findings] |
| Third-Party | Strong / Gaps / Missing | [findings] |
| AI-Specific | Strong / Gaps / Missing | [findings] |

### Top 5 Priority Actions
1. **[Signal]** — [action] | Impact: [H/M] | Effort: [L/M/H]
2-5. [Same format]

### Roadmap
**Week 1-2 (Foundation)**: Schema, sameAs, NAP+E consistency, About page
**Month 1 (Knowledge Bases)**: Wikidata, CrunchBase, directories, Wikipedia notability path
**Month 2-3 (Authority)**: Authoritative mentions, co-citation, topical clusters, PR
**Ongoing (AI)**: Quarterly AI testing, update factual claims, monitor AI output

Tips for Success

1. Start with Wikidata — most influential editable KB; often triggers KP creation within weeks 2. sameAs is your most powerful Schema.org property — always include Wikidata URL first 3. Test AI recognition before and after — query ChatGPT, Claude, Perplexity, Google AI Overview 4. Entity signals compound — 5 weak signals together > 1 strong signal alone 5. Consistency beats completeness — consistent name across 10 platforms > perfect profile on 2 6. Don't neglect disambiguation — if name is shared, disambiguation is first priority

Entity Type Reference

Reference tables for entity types, key signals, and disambiguation strategies.

Entity Types and Key Signals

Disambiguation Strategy by Situation

Example: Entity Optimization Report

Full example output for an entity audit request.

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

Output:

## Entity Optimization Report

### Entity Profile

**Entity Name**: Acme Analytics
**Entity Type**: Organization (B2B SaaS)
**Primary Domain**: acme-analytics.example
**Target Topics**: analytics platform, business intelligence, enterprise analytics

### AI Entity Resolution Test

Queries tested with results reported by user:

| Query | Result | Assessment |
|-------|--------|------------|
| "What is Acme Analytics?" | Described as "an analytics tool" with no further detail | Partial recognition -- generic description, no mention of B2B focus or key features |
| "Best analytics platforms for enterprises" | Acme Analytics not mentioned in any AI response | Not recognized as a player in the enterprise analytics space |
| "Acme Analytics vs Datadog" | Correctly identified as a competitor to Datadog, but feature comparison was incomplete and partially inaccurate | Partial -- entity is associated with the right category but attributes are thin |
| "Who founded Acme Analytics?" | No answer found by any AI system tested | Entity leadership not present in AI knowledge bases |

### Entity Health Summary

| Signal Category | Status | Key Findings |
|-----------------|--------|--------------|
| Knowledge Graph | Missing | No Wikidata entry exists; no Google Knowledge Panel triggers for branded queries |
| Structured Data | Partial | Organization schema present on homepage with name, url, and logo; missing Person schema for CEO and leadership team; no sameAs links to external profiles |
| Web Presence | Strong | Consistent NAP across LinkedIn, Twitter/X, G2, and Crunchbase; social profiles link back to acme-analytics.example; branded search returns owned properties in top 5 |
| Content-Based | Partial | About page exists but opens with marketing copy rather than an entity-defining statement; no dedicated author pages for leadership |
| Third-Party | Partial | Listed on G2 and Crunchbase; 2 industry publication mentions found; no awards or analyst coverage |
| AI-Specific | Weak | AI systems have only surface-level awareness; entity definition is not quotable from any authoritative source |

### Top 3 Priority Actions

1. **Create Wikidata entry** with key properties: instance of (P31: business intelligence software company), official website (P856: acme-analytics.example), inception (P571), country (P17)
   - Impact: High | Effort: Low
   - Why: Wikidata is the foundational knowledge base that feeds Google Knowledge Graph, Bing, and AI training pipelines; without it, the entity cannot be formally resolved

2. **Add Person schema for leadership team** on the About/Team page, including name, jobTitle, sameAs links to LinkedIn profiles, and worksFor pointing to the Organization entity
   - Impact: High | Effort: Low
   - Why: Addresses the "Who founded Acme Analytics?" gap directly; Person schema for key people creates bidirectional entity associations that strengthen organizational identity

3. **Build Wikipedia notability through independent press coverage** -- target 3-5 articles in industry publications (TechCrunch, VentureBeat, Analytics India Magazine) that mention Acme Analytics by name with verifiable claims
   - Impact: High | Effort: High
   - Why: Wikipedia notability requires coverage in independent reliable sources; press mentions simultaneously feed AI training data, build third-party entity signals, and create the citation foundation for a future Wikipedia article

### Cross-Reference

- **CORE-EEAT**: A07 (Knowledge Graph Presence) scored Fail, A08 (Entity Consistency) scored Pass -- entity optimization should focus on knowledge base gaps rather than consistency
- **CITE**: I-dimension weakest area is I01 (Knowledge Graph Presence) -- completing Wikidata entry and earning Knowledge Panel directly improves domain identity score

Knowledge Graph Guide

Use this guide to turn an entity into a consistent, verifiable profile that downstream SEO/GEO skills can cite.

Entity Profile Core

Signal Sources

Optimization Steps

1. Build or refresh the Canonical Entity Profile. 2. Normalize names, descriptions, URLs, and identifiers across owned surfaces. 3. Add or fix Organization/Person/Product/LocalBusiness schema where eligible. 4. Strengthen SameAs links with official, verifiable profiles. 5. Identify missing citations, weak sources, and conflicts. 6. Hand off to schema-markup-generator, geo-content-optimizer, or domain-authority-auditor.

Wikidata / Wikipedia Notes

Do not create weak or promotional pages. Only propose Wikidata/Wikipedia work when notability, sourcing, neutrality, and conflict-of-interest handling are realistic.

GEO Entity Pack

Quality Checks

• Every factual claim has source/date.
• Profile avoids marketing language.
• Volatile claims are labeled current as of date.
• Downstream schema fields match visible page content.
• Handoff includes confidence, gaps, and next best skill.

Knowledge Panel & Wikidata Optimization Guide

Knowledge Panel Optimization

Claiming and Editing

1. Google Knowledge Panel: Claim via Google's verification (search entity -> "Claim this knowledge panel") 2. Bing Knowledge Panel: Driven by Wikidata and LinkedIn -- update those sources 3. AI Knowledge: Driven by training data -- ensure authoritative sources describe entity correctly

Common Issues

Wikidata Best Practices

Creating an Entry

1. Check notability: at least one authoritative reference 2. Create item: label, description, aliases in relevant languages 3. Add statements: instance of, website, social links, founding date, founders, industry 4. Add identifiers: P856, social media IDs, CrunchBase ID, ISNI, VIAF 5. Add references: every statement needs an authoritative source

COI Note: Wikipedia prohibits self-editing. Focus on building notability through independent sources. Use Requested Articles process for Wikipedia involvement.

Key Properties by Entity Type

AI Entity Optimization

Resolution Pipeline

User query -> Entity extraction -> Entity resolution -> Knowledge retrieval -> Answer generation

Signals AI Systems Use

Entity-Specific GEO Tactics

1. Define clearly: About page first paragraph should be AI-quotable 2. Be consistent: Identical description across all platforms 3. Build associations: Content connecting entity to target topics 4. Earn mentions: Third-party mentions > self-description 5. Stay current: Outdated info causes AI to lose confidence