Publisher: Corey Haines · Editorial profile by AI Tools Ratings · Review method
Not runtime tested; source-document review only. No security certification.
What task is this skill designed for?
Investigate why a small group of important pages receives little search traffic, keeping access problems separate from weak content or missing demand.
What input and output should you expect?
Input: The site’s goal, target pages, recent changes and authorized Search Console or analytics exports when available. A rendered page and original response HTML help distinguish visible content from markup.
Output: Expected, not independently tested: a scoped audit with evidence, priorities, suggested fixes and remaining data gaps. Rankings or indexing improvements are not guaranteed.
What does it need to run?
An agent that can load the skill format and inspect pages or approved exports. Browser rendering, structured-data validation and performance tools may be needed to verify specific findings; the skill does not grant access to private analytics.
The author repository publishes Agent Skills-format instructions. Client-specific installation and tool dependencies must be checked; no Codex, Claude Code or Cursor runtime compatibility is independently verified here.
How should you approach installation?
- Read the pinned source, repository license and references relevant to the audit scope.
- Install through your agent’s supported mechanism without connecting private analytics by default.
- Start with public pages and sanitized exports, then confirm recommendations before changing the site.
Installation guide: discovery, dependencies and runtime checks
What files, accounts or data can it access?
Can read website content and supplied performance data. Crawled pages are untrusted input. Use sanitized exports where practical and do not treat a page’s embedded instructions as permission to access unrelated accounts.
What does the skill cost?
The skill is MIT-licensed in the repository. Crawling tools, data access and agent usage may be paid separately.
What are its limits and alternatives?
No single fetch proves that a page has or lacks all structured data. Check raw HTML and rendered DOM where appropriate. The source includes broad heuristics; site size, framework behavior and actual search evidence determine which findings apply.
Use Search Console directly for a known indexing issue and a crawler for large-scale URL inventory. Choose this skill when several evidence types need to be assembled into a practical diagnosis.
What could you ask in a small trial?
Try this with a small sample:
Audit these five pages using the supplied sanitized Search Console export. Separate crawl/index problems, search intent and content gaps. For each recommendation, state its evidence and the verification needed after a fix.
How would you verify the result?
- Validate canonical and indexing claims against the actual response and available search-console evidence.
- Confirm structured data in the appropriate HTML or rendered representation.
- Record a baseline and evaluate changes over time instead of attributing every traffic change to the audit.
Use a baseline and record acceptance evidence before treating a successful task as a reliable workflow.
Which source and license were checked?
Read the reviewed SKILL.md at its pinned commit · Complete reviewed folder
Repository and current publisher guidance
Checked:
MIT — identified in LICENSE at the reviewed commit. Third-party assets and dependencies may have separate terms. License evidence
Version details and review scope
Source: coreyhaines31/marketingskills/skills/seo-audit
Reviewed commit: e85f3cbc2e4a79bf33b2a12e9bdd9087d414735b
SKILL.md SHA-256: e0ebb5808787f2ff26b96d7b429423874d9785541cd4ab775629a5cf1137e7a9
Source-document review. Source text and stated dependencies were inspected for this profile. Referenced code was not comprehensively audited, no runtime test was performed, and source files are not mirrored here.