skillZs
★ LIVE SKILL TAGS ★
>>> LIVE SKILLS INDEX <<<
* OPEN SOURCE *
NO LOGIN, NO TRACKING
※ REAL INSTALL DATA ※
← back to all skills
magnus919/agent-skills115 installs

seo

Audit and improve website discoverability across traditional search, answer engines, and generative search. Use for technical SEO, on-page content, structured data, question and entity architecture, AI citations, crawler controls, agent-readable content, local/national site portfolios, scaled-content quality, and reproducible visibility measurement. Do not use for only copy-editing, writing, CMS operations, or generic AI marketing claims without a defined search surface and verification plan.

How do I install this agent skill?

npx skills add https://github.com/magnus919/agent-skills --skill seo
view source ↗

Is this agent skill safe to install?

  • Gen Agent Trust Hubpass

    The SEO skill is a comprehensive toolkit for technical search and generative engine optimization. It follows security best practices by defining clear read-only boundaries for its included scripts and explicitly prohibiting unauthorized actions such as credential transfers or automated deployments. No malicious patterns or obfuscation were detected.

  • Socketpass

    No alerts

  • Snykpass

    Risk: LOW · No issues

What does this agent skill do?

SEO

A full-spectrum search visibility skill. It treats traditional SEO, Answer Engine Optimization (AEO), and Generative Engine Optimization (GEO) as overlapping work across different search and answer surfaces, not as separate collections of ranking hacks.

Operating model

  1. Scope the surface and outcome. Name the provider, product or search surface, audience, entity, questions, business outcome, and exclusions. Define whether success means crawl access, index eligibility, retrieval, mention, citation, citation correctness, share of voice, referral, or conversion.
  2. Inspect and research. Audit the public/rendered page and technical delivery. Read current first-party provider guidance and authoritative subject sources. Treat practitioner claims and vendor studies as hypotheses unless methods and scope support more.
  3. Map intent to canonical content. Use topics and question clusters, but avoid manufacturing near-duplicate pages. Assign one canonical answer location, entity ownership, evidence, freshness owner, and internal links.
  4. Improve people-first content and structure. Put a concise answer near the relevant heading, then supporting evidence, qualifications, and useful detail. Preserve natural prose, distinct point of view, accessibility, and human value.
  5. Implement only supported controls. Fix crawlability, indexability, metadata, internal links, page experience, textual content, structured-data parity, sitemaps, freshness, and provider-specific crawler or preview controls. Optional files such as llms.txt or Markdown representations are provider-scoped proposals, not universal requirements.
  6. Measure at the correct boundary. Freeze prompts and versions, capture exact answers and citations, score citation correctness, and use provider-native reports where available. Separate implementation evidence from observed visibility and causal claims.
  7. Verify and learn. Recheck the rendered/public boundary, validate structured data, inspect search-console or provider evidence, and run bounded one-variable experiments. Do not declare success from HTTP 200, parseable JSON-LD, a single answer, or a third-party score.

Business GEO workflow

When a business wants accurate AI descriptions or qualified recommendations, first separate identity accuracy, unbranded discovery and recommendation fit. A pasted-page comprehension check is not a search test. Audit current offers and public contradictions; map real customer questions to commercially relevant topics and defensible original evidence; assess existing content before expanding it; then consider suitable independent distribution. Use a bounded pilot with explicit access, consent, publication and rollback gates.

Use research-methodology for source-to-claim closure when a video, vendor study or disputed statistic drives a decision. Treat retrieval tools, including Grok discovery or Crawl4AI extraction when available, as evidence-gathering aids rather than authorities. Preserve source URLs, accessed dates, extraction limits and contradictions; never substitute a generated summary for the cited study's actual methods.

Action boundary

Confirm the target, scope, and rollback path before acting. Read-only discovery may proceed without confirmation. Research does not authorize domain purchases, profile creation, publication, deployments, submissions, provider outreach or lead-data transfers. Preserve existing user edits and use the owning tool skill for authorized mutations.

For local/national or coordinated-site work, start with verified business footprint and distinct user needs, compare one-site and multi-site architectures, and require a bounded pilot before expansion. Site counts, valid schema and generated pages are not evidence of commercial success.

Terminology and boundaries

  • SEO is the umbrella: improving a site's eligibility, discoverability, interpretation, and useful visibility in search systems.
  • AEO is a stakeholder label for answer-oriented work, including direct answers, snippets, knowledge surfaces, and answer-engine inclusion.
  • GEO is a stakeholder label for visibility in generated answers, especially being selected, cited, or factually absorbed into a synthesized response. The term originated in the 2024 KDD paper by Aggarwal et al.; it does not establish a universal algorithm.
  • LLMO and AI-search optimization are overlapping labels. Preserve the target organization's term, then define the measurable outcome and provider scope.
  • These terms do not guarantee ranking, inclusion, citation, traffic, recommendation, or conversion. A mention is not a citation, a citation is not proof of correctness, and a citation is not a click.

Evidence rules

Use these labels in plans and reports:

  • Primary documentation: provider, standards body, schema vocabulary, or tool owner describes its own behavior.
  • Observed: recorded crawl, rendered page, provider dashboard, exact answer, URL, or reproducible local result.
  • Independent study: disclosed method and dataset, with generalization limits stated.
  • Vendor-reported: useful for hypothesis generation, not a universal rule.
  • Inference: reasoned interpretation beyond direct observation.
  • Unresolved: provider-dependent, stale, contradicted, or not verified.

Reject claims such as “FAQ schema guarantees citations,” “short paragraphs are required by all engines,” “llms.txt is a search standard,” or “allowing a crawler guarantees inclusion.” Record source URL, access date, provider scope, exact support, what it does not prove, confidence, and refresh trigger for every material claim.

Reference routing

NeedRead
Crawlability, indexability, robots, sitemaps, performance, canonicals, mobile, HTTPSreferences/technical-seo.md
Titles, descriptions, headings, content quality, links, imagesreferences/onpage-seo.md
Schema.org, JSON-LD, rich-result eligibility, visible parityreferences/schema-markup.md and references/structured-data.md
Topics, question clusters, entities, answer blocks, evidence architecturereferences/content-and-entity-architecture.md
Full answer/generative implementation sequence and completion gatereferences/implementation-playbook.md
Provider guidance, crawler identities, robots and preview controlsreferences/platform-guidance.md and references/discovery-and-freshness.md
llms.txt, Markdown delivery, content negotiation, provider supportreferences/agent-readable-content.md
Outcome definitions, confidence, and rejected claimsreferences/evidence-boundaries.md
Prompt sets, citation logs, metrics, experiments, and confoundersreferences/measurement-and-experimentation.md
Ghost metadata and injectionreferences/ghost-metadata.md
Content strategy, topic clusters, keywords, gaps, SERP featuresreferences/content-strategy-seo.md
Service geography, Maps eligibility, local/national intentreferences/local-and-national-search.md
Domain/section decisions, portfolio overlaps, economics and scale gatesreferences/site-portfolio-strategy.md
Registration cost control, subdomains versus domains, quotas and pilot ADRreferences/domain-architecture-economics.md and templates/domain-decision-record.md
Cross-property Search Console collection, completeness and bulk export limitsreferences/search-portfolio-collection.md
Programmatic content, truth checks, QA and lead-flow acceptancereferences/scaled-content-quality.md
Practitioner microsite workflow and evidence limitsreferences/microsite-evidence.md
Business misdescription, stale biographies, service clarity, offer hubsreferences/business-identity-and-offers.md and templates/business-identity-audit.md
Commercial topic selection, original proof, case-study consentreferences/commercial-topics-and-original-evidence.md and templates/topic-proof-map.md
Updating, consolidating, archiving or retiring old content safelyreferences/content-retirement-and-consolidation.md and templates/content-disposition-register.md
Earned versus owned/shared/paid distribution and venue selectionreferences/earned-distribution-and-citation-fit.md and templates/citation-opportunity-matrix.md
Video-derived GEO claims, statistic scope and contradictory evidencereferences/geo-practitioner-evidence.md
Source URLs, access dates, authority tiers, and refresh notesreferences/source-index.md

Scripts and templates

Run from the skill directory:

python3 scripts/aeo_audit.py <page.html-or-URL> --json
python3 scripts/build_prompt_matrix.py <topics.json> --output prompt-matrix.json
python3 -m pytest scripts/test_aeo_scripts.py

The scripts are read-only and use the Python standard library. They inspect source HTML; they do not execute JavaScript, call an LLM, publish, submit URLs, or change crawler policy. Templates cover implementation plans, question clusters, citation observations, optional llms.txt, and crawler-policy decisions. For portfolios use templates/search-portfolio-plan.md, templates/location-evidence-register.md, templates/intent-ownership-map.md, and templates/rollout-review.md.

Audit output

Use assets/audit-report-template.md and distinguish:

  • Observed findings: what the inspected page, response, dashboard, or answer actually shows.
  • Recommended changes: proposed actions with owner, risk, expected mechanism, and verification.
  • Provider scope: which engine or search surface the evidence applies to.
  • Status: implemented, verified, observed, inferred, or unresolved.

When not to use

Do not use this skill alone for only mechanical copy-editing, ordinary article writing, CMS administration, or a generic request to “rank better” without a defined target, evidence boundary, or measurable outcome. Route those to the relevant writing, copy-editing, CMS, or product skill.

Ownership and completion

SEO owns intent, architecture, search eligibility and provider-scoped measurement. Route market/partner/channel decisions to go-to-market, unit costs to capacity-and-cost-engineering, user journeys to product-design-and-ux, identity to brand-designer, implementation to frontend-engineering or the relevant CMS/tool skill, tracking contracts to product-analytics-and-measurement, and causal inference to data-scientist.

Complete when the requested audit or plan has sourced findings, explicit unknowns, owners and bounded verification; for authorized implementation, record actual final-boundary checks. Hold publication on unsupported business claims, missing fulfillment or untested lead routing. Stop scale-up when distinct utility, maintenance capacity or commercial evidence is missing; propose repair or consolidation rather than manufacturing progress.

Portability

Use the host agent's normal mechanisms to load references, templates, and scripts. Do not assume a particular profile system, orchestrator, memory service, CMS, search console, or provider API.

Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.

<a href="https://skillzs.dev/skills/magnus919/agent-skills/seo">View seo on skillZs</a>