seo-authority
Use when auditing backlinks, referring domains, source citations, brand mentions, unlinked mentions, linkable assets, digital PR evidence, or off-site source landscapes from authorized first-party, Bi
Files4
View on GitHubSKILL.mdskills/seo-authority/SKILL.md
GitHubAuthority and Source Landscape
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: authority-review.md; source-landscape.md (combine small related steps with stable section links). Record source ownership, expertise, referring evidence and claims directly in Markdown handoffs; distinguish owned citations from independent endorsement. Keep paid/organic/affiliate relationships explicit and no fabricated authority metrics.
Audit off-site evidence that helps users and systems verify an entity: genuine links, mentions, citations, source coverage, and risk. This skill does not manufacture authority.
Read authority-evidence-protocol.md before a formal audit.
Procedure
- Define entity, domains, markets/locales, comparison scope, authorized data sources, time window, and the decision to make.
- Preserve each link/mention row with source URL/domain, target URL/entity, anchor or mention text, first/last seen date when supplied, link attributes, source type, collection method, and limitations.
- Normalize URLs without discarding raw values. Separate backlinks, citations, unlinked mentions, syndication, scraper copies, social/profile links, and self-controlled properties.
- Evaluate source relevance, editorial independence, claim support, topical/locale fit, target-page usefulness, and visible context. Keep proprietary authority/risk/traffic metrics labeled with vendor and date.
- Identify broken earned links, incorrect entity facts, missing first-party evidence, unsupported claims, spam patterns, paid/sponsored disclosure, and link-scheme risk.
- Recommend source-worthy first-party assets, corrections, reclamation, documentation, partnerships, or editorial outreach only when truthful and policy-safe. Do not prescribe volume quotas or paid/manipulative links.
- Route entity/citation suitability to
seo-geo, competitor-page copy toseo-competitor-pages, content assets toseo-content, and internal links toseo-architecture. - Package findings as SEO Findings
1.1.0withbacklink_profile,content_set,web_page, orsitetargets andauthority,entity,content, orpolicycategories.
Formal evidence handoff
Package only supported observations as SEO Findings 1.1.0. Let <suite-root> mean ${CLAUDE_PLUGIN_ROOT} in Claude Code. In Codex, read .seo-suite-runtime.json beside this SKILL.md when present and use its suite_root value; otherwise use the absolute repository checkout, then run python "<suite-root>/scripts/validate_seo_findings.py" validate-findings <bundle>/seo-findings.json --bundle <bundle>. Keep the handoff provisional until this command passes.
Output
Return the source and scope, normalized link/mention inventory, source-quality and claim-support observations, risk patterns, evidence gaps, owners, verification, and limitations. Never collapse the result into a universal domain-authority score.