agentleFS
oegeyilmaz9oegeyilmaz9/seo-aeo-geo-ultimate/skills/seo-geo/SKILL.md

seo-geo

Skill6 starsChanged 3 months agoApache-2.0View on GitHub

Audit supplied pages, entity records, source captures, and citation observations for generative-engine entity consistency, evidence traceability, citation suitability, cited-source alignment, and documented engine controls against a pinned AI-search Research Pack. Use for GEO, generative-engine optimization, AI citations, brand or entity mentions in generative answers, source alignment, or documented AI-search control audits. Do not use for direct-answer formatting or extractability, live research, content rewriting, schema generation, technical SEO implementation, longitudinal visibility measurement, or guaranteed placement claims.

58 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use seo-google, seo-image-gen and 4 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • timruebenachSkill

    seo-google

    Google SEO APIs: Search Console (Search Analytics, URL Inspection, Sitemaps), PageSpeed Insights v5, CrUX field data with 25-week history, Indexing API v3, and GA4 organic traffic. Provides real Google field data for Core Web Vitals, indexation status, search performance, and organic traffic trends. Use when user says "search console", "GSC", "PageSpeed", "CrUX", "field data", "indexing API", "GA4 organic", "URL inspection", "google api setup", "real CWV data", "impressions", "clicks", "CTR", "position data", "LCP", "INP", "CLS", "FCP", "TTFB", or "Lighthouse scores".

    Also in 13 projects that use this

  • timruebenachSkill

    seo-image-gen

    AI image generation for SEO assets: OG/social preview images, blog hero images, schema images, product photography, infographics. Powered by Gemini via nanobanana-mcp. Requires banana extension installed. Use when user says \"generate image\", \"OG image\", \"social preview\", \"hero image\", \"blog image\", \"product photo\", \"infographic\", \"seo image\", \"create visual\", \"image-gen\", \"favicon\", \"schema image\", \"pinterest pin\", \"generate visual\", \"banner\", or \"thumbnail\".

    Also in 12 projects that use this

  • +4 more from timruebenach

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 53 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read markdown-delivery-contract.md for every task.

    line 10
  2. Distinctive:

    Read geo-audit-protocol.md before classifying a finding or recommendation.

    line 22
  3. Very specific:

    Create capture-tied direct_observation audit evidence.

    line 38
  4. Very specific:

    Create optimization-brief.json with optimization_domain: "geo" and producer_skill: "seo-geo".

    line 41
  5. Distinctive:

    Do not create a universal GEO score, treat a correlation as a control, recommend off-page manipulation, or claim a change will cause …

    line 53

“Common” is measured: kept by at least 6 in 10 of the 53 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

SEO GEO

Markdown delivery contract

Read markdown-delivery-contract.md for every task. Write a substantive .md document for every material work step and register its direct destination in the work index.md. For public-site work, apply the owner-required Markdown discovery profile across the full eligible inventory; preserve native standards and immutable evidence formats.

Lane outputs: geo-findings.md; claim-source-map.md (combine small related steps with stable section links). Bind entities and claims to exact Markdown passages, primary supporting sources and canonical HTML owners. Audit revision/locale consistency and contradictions. A direct source link is citation readiness evidence, not proof of engine citation.

Produce an evidence-linked GEO Optimization Brief from immutable inputs. Audit generative-engine entity, source, and citation readiness; do not implement remedies or predict placement.

Required inputs

  • Require a contract-valid research-pack.json from ai-search-research.
  • Require hash-pinned target metadata and captures. For web targets, use only the metadata-supplied URL.
  • Require dated raw observations for any claim about an engine answer, mention, citation, or cited source. Record missing or inaccessible observations as limitations.
  • Read geo-audit-protocol.md before classifying a finding or recommendation.

Procedure

  1. Validate the complete Research Pack contract and semantic provenance: identity, version, hash, stable-ID uniqueness, raw references, locales, queries, entity integrity, evidence, observations, ground truth, freshness, and gaps.
  2. Validate each target metadata file, metadata hash, capture hash, target URL, locale, capture time, and chronology.
  3. Audit only these GEO dimensions:
    • entity_consistency: names, aliases, attributes, disambiguation, and target/source agreement;
    • evidence_traceability: material assertions resolve to current, scope-compatible evidence;
    • citation_suitability: supplied sources clearly support the relevant entity/fact without claiming an engine will select them;
    • source_credibility: supplied source identity, ownership, expertise, independence, update state, and primary/secondary role are explicit without relying on a proprietary authority score;
    • claim_source_entailment: cited or candidate text actually supports the bounded answer claim, with partial, conflicting, and unverifiable support preserved;
    • conflict_resolution: conflicting current sources remain visible and the applicable system of record, scope, and resolution owner are named;
    • cited_source_alignment: a metadata-bound content_set target under raw/observations/ contains the exact raw-observation fields defined in the protocol, and its dated engine/surface/locale answer plus cited URLs agree with referenced Research Pack sources;
    • documented_engine_control: a current vendor document or applicable standard supports the scoped control.
  4. Bind every finding to resolved Research Pack query IDs, one target, that target's locale, and engine/surface pairs within query applicability.
  5. Create capture-tied direct_observation audit evidence. Never copy Research Pack evidence or invent a URL, answer, citation, mention, crawler behavior, control, or engine result.
  6. Classify evidence as confirmed, vendor-recommended, experimental, or speculative. A recommendation also inherits the weakest classification of every linked finding; it cannot hide a weak finding by repeating only stronger references. Speculative or experimental findings never support implementation; experimental-only support belongs in experiments.
  7. Decline fixed scores, universal ranking factors, fixed passage formulas, universal engine-mandatory llms.txt, blanket crawler directives, platform guarantees, and correlation presented as causation.
  8. Create optimization-brief.json with optimization_domain: "geo" and producer_skill: "seo-geo". Keep stable IDs unique, external artifacts hash-pinned, and audit evidence metadata-bound.
  9. Give every recommendation resolved evidence overlapping each linked finding, a desired outcome, confidence, verification method, and exactly one candidate implementation owner. A Brief does not approve a change.
  10. Validate the Research Pack, metadata/capture provenance, evidence resolution and scope, GEO dimension ownership, documented-control evidence, chronology, and canonical Optimization Brief contract.

Ownership boundaries

  • Route direct-answer completeness, clarity, intent coverage, and extractability to seo-aeo.
  • Route live AI-search research and missing source collection to ai-search-research.
  • Route longitudinal mention, citation, accuracy, referral, or drift measurement to ai-visibility-monitor.
  • Route backlink/source-landscape discovery to seo-authority and site-owned source structure to seo-architecture.
  • Route a validated Brief to seo-action-plan before implementation, then to the exact approved content, schema, technical, locale, commerce, local, video, news, agentic, architecture, authority, performance, or broad implementation owner.

Do not create a universal GEO score, treat a correlation as a control, recommend off-page manipulation, or claim a change will cause mentions or citations.

Severity

  • critical: the audit or handoff would be materially false, unsafe, or unusable without correction.
  • important: a required entity, source, evidence link, scope, or owner handoff is missing or misleading.
  • minor: non-blocking clarity or maintainability improvement; record it in backlog.

Close critical and important audit findings. Backlog minor findings.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.