Skip to content
Back to skills

Seo Audit

ASecurity

Use when a site needs a bounded multi-lane SEO assessment with explicit scope, evidence capture, findings, ownership, and limitations; coordinate specialists rather than produce a universal audit score or unverified implementation claim.

  • 2 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added September 6, 2026
ai-agentspythongorailssecurityperformancedocumentation

Works with

  • claude code
  • cli

Security analysis

A100/100

Pro scans all 3 files and shows the line behind each finding

Scanned October 6, 2026

npx -y skills add oegeyilmaz9/seo-aeo-geo-ultimate --skill seo-audit --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Seo Audit?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Seo Audit
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/oegeyilmaz9-seo-audit/badge)](https://www.skillsdirectory.com/skills/oegeyilmaz9-seo-audit)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: seo-audit
description: Use when a site needs a bounded multi-lane SEO assessment with explicit scope, evidence capture, findings, ownership, and limitations; coordinate specialists rather than produce a universal audit score or unverified implementation claim.
---

# Multi-lane SEO Audit

## Markdown delivery contract

Read [markdown-delivery-contract.md](references/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: `site-audit.md; markdown-coverage.md` (combine small related steps with stable section links). Audit full eligible HTML-to-Markdown coverage, direct discovery, source parity and ownership alongside conventional SEO lanes. Do not declare full-site coverage from only llms.txt or an XML sample.


## Purpose

Plan and synthesize a site assessment across the lanes that matter for the stated goal. This skill does not assume that every site needs every check, crawl a site without authorization, fabricate a complete inventory, or implement the findings.

Read `references/audit-scope-protocol.md` before starting an audit.

## Scope first

Record objectives, domains/properties, representative URLs/templates, locales, environments, access/consent, data sources, time window, exclusions, and decision owners. Choose only relevant lanes: technical, page/content, structured data, media, sitemaps, hreflang, programmatic systems, competitive evidence, AEO/GEO, or measurement.

If an authorized crawler, analytics property, Search Console property, log source, or application access is unavailable, state the gap. Do not treat public snippets or third-party scores as a substitute for the inaccessible evidence.

## Workflow

1. **Design the evidence plan.** Define what capture/report proves each expected condition and which findings need current primary documentation.
2. **Run bounded lane assessments.** Route work to the relevant technical, page/content, schema, media, sitemap, international, programmatic, commerce, local, video, news/Discover, agentic, architecture, authority, conventional-performance, or AI-search specialist. Preserve their artifacts and disagreements.
3. **Classify findings.** Mark confirmed defects, supported opportunities, experiments, and unknowns separately. Do not convert incomplete sampling into site-wide certainty.
4. **Synthesize without false precision.** Prioritize by user/business risk, scope, reversibility, dependency, evidence confidence, and owner readiness—not by one blended SEO number.
5. **Plan delivery.** Send validated findings to `seo-action-plan` for owner/approval/verification/rollback, then use `seo-plan` for cross-team sequencing. Establish a baseline before change only when comparison is requested.

## Guardrails

- No universal SEO score, universal engine-mandatory `llms.txt`, generic crawler policy, or ranking/citation guarantee.
- Do not count pages, links, words, or tests as proof of quality.
- Do not say a crawl, bot request, report row, or tool health check proves indexation, AI retrieval, citation, referral, or conversion.
- Keep security, privacy, accessibility, and legal risks visible even when they are not search-ranking claims.

## Formal evidence handoff

When this audit needs a cross-team, approval-ready plan, package evidence-bound findings as an immutable `seo-findings.json` bundle using the checked-out suite contract. 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. Keep every referenced capture/source below `raw/`, retain declined claims and limitations, and run `python "<suite-root>/scripts/validate_seo_findings.py" validate-findings <bundle>/seo-findings.json --bundle <bundle>`. Send only a passing bundle to `seo-action-plan`; otherwise label the handoff `provisional`.

## Output

Produce a scoped audit charter, evidence inventory, lane findings, limitations, prioritized ownership map, and proposed next steps. Mark any implementation proposal as pending approval and link it to an action plan when a formal handoff is needed.

Files in this skill

  • SKILL.md3.6 KB
  • agents/openai.yaml212 B
  • references/audit-scope-protocol.md499 B

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.