entity-optimization
Skill2 starsChanged 5 months agoMITView on GitHub
Make a brand a recognized entity that answer engines can confidently name — a clear entity home, Organization schema with sameAs, Wikidata and (where it qualifies) Wikipedia presence, consistent facts across the web, and disambiguation. Works for any business, B2B or B2C, product or service. Use when the request is to get AI to recognize a brand, build an entity or knowledge-graph presence, fix how AI describes or confuses a brand, add Organization schema or sameAs, or pursue Wikidata/Wikipedia. Pairs with structured-data and author-authority.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- 6t9xstar/one-step-seotheir own version, first seen Nov 8, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- 6t9xstar/one-step-seo★ 5same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository26 other files it gives its agents.
- aeo-foundationSkill
- ai-capability-signalingSkill
- ai-crawler-accessSkill
- ai-referral-analyticsSkill
- ai-retrievabilitySkill
- ai-visibility-auditSkill
- ai-visibility-trackingSkill
- answer-engineeringSkill
- author-authoritySkill
- chatgpt-optimizationSkill
- claim-accuracySkill
- claude-optimizationSkill
- community-and-reviewsSkill
- comparison-contentSkill
- competitor-ai-analysisSkill
- content-freshnessSkill
- crawler-log-analysisSkill
- digital-prSkill
- evidence-and-citationsSkill
- gemini-optimizationSkill
- google-ai-overviews-optimizationSkill
- llms-txtSkill
- multimodal-aeoSkill
- perplexity-optimizationSkill
- prompt-researchSkill
- structured-dataSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 5 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 35
Read aeo-foundation.md for the brand-entity facts: official name, category, founding, HQ, key people, and existing profiles.
- Distinctive: line 54
Disambiguation: If the name is generic, always pair it with its category and identifiers ("Acme (analytics software)") so the brand is not …
- Distinctive: line 59
Audit the entity: Search the brand across engines and the web.
- Distinctive: line 61
Build the entity home: Write or tighten the About page as the canonical definition.
- Very specific: line 62
Implement schema: Add Organization schema with a complete sameAs set.
- Distinctive: line 64
Establish knowledge bases: Create/complete Wikidata; pursue Wikipedia only with genuine third-party notability (see the playbook).
- Distinctive: line 88
Check whether canonical entity facts appear consistently across profiles (live URLs or local files):
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Entity Optimization
This skill makes a brand a recognized entity — a distinct, verified thing engines can name with confidence. You can rank for a keyword and still be invisible in AI answers if the model does not recognize you as an entity in its knowledge graph. Entity optimization fixes that by giving the web a single, consistent, well-connected definition of who the brand is. It works for any business, B2B or B2C.
See references/entity-playbook.md for the Wikidata,
Wikipedia, and sameAs details.
When to use this skill
- A brand is absent from AI answers despite decent search rankings.
- AI describes the brand inaccurately, vaguely, or confuses it with another.
- Establishing knowledge-graph presence (Organization schema, Wikidata, Wikipedia).
- Standardizing brand facts across the web.
Before you start
Read aeo-foundation.md for the brand-entity facts: official name, category, founding,
HQ, key people, and existing profiles. If it is missing, point to the aeo-foundation
skill.
The levers
- An authoritative entity home. Usually the About page — the canonical definition of the brand: what it is, its category, founding, location, key people, and what makes it distinct, in consistent language. Crawlable and linked from the homepage.
- Organization schema with
sameAs. Mark up the entity (name, url, logo, description, foundingDate) and link every authoritative profile viasameAsso engines collapse the scattered mentions into one entity. Recipes in the schema cookbook. - Knowledge-base presence. A complete Wikidata item (low barrier, machine-readable, feeds many systems) and, where the brand genuinely qualifies on notability, a Wikipedia article (high authority). See the playbook.
- Fact consistency (NAP and core facts). The same name, founding date, HQ, leadership, and category everywhere — site, schema, profiles, directories, review platforms, press. Engines apply a "majority rule"; contradictions weaken recognition.
- Disambiguation. If the name is generic, always pair it with its category and identifiers ("Acme (analytics software)") so the brand is not merged with namesakes.
Workflow
- Audit the entity. Search the brand across engines and the web; note how it is described, what is inconsistent or wrong, and which knowledge bases list it.
- Build the entity home. Write or tighten the About page as the canonical definition.
- Implement schema. Add Organization schema with a complete
sameAsset; link key people with Person schema (see author-authority). - Establish knowledge bases. Create/complete Wikidata; pursue Wikipedia only with genuine third-party notability (see the playbook).
- Reconcile facts. Standardize core facts everywhere they appear; correct outdated or conflicting listings.
- Disambiguate. Apply the full name-plus-category form in key places.
- Monitor. Recheck periodically; entity facts drift as the company changes.
Output format
- An entity audit: how the brand is currently recognized and where facts conflict.
- The entity home content and Organization/
sameAsmarkup. - A knowledge-base plan (Wikidata now; Wikipedia if/when notable).
- A fact-reconciliation list of profiles/directories to correct.
(assumption)tags on any unverified facts.
Common pitfalls
- Inconsistent core facts across the web — the top reason engines stay uncertain.
- Chasing a Wikipedia article without the independent coverage notability requires.
- Skipping Wikidata, which is lower-friction and directly machine-readable.
- Generic brand name left undisambiguated, so AI conflates it with others.
Tool
Check whether canonical entity facts appear consistently across profiles (live URLs or local files):
python scripts/check_entity_consistency.py --sample
python scripts/check_entity_consistency.py --input entity.jsonOptional. The script only automates this step; it needs
python3(standard library only, no install). No Python? Just follow the steps above manually.
Related Skills
- structured-data — the Organization/Person markup that anchors the entity.
- author-authority — people-entities (founders, authors) connected to the brand.
- digital-pr — the third-party coverage that builds notability and corroboration.
- aeo-foundation — the source of the canonical entity facts.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

