On Page Seo Auditor
PassAudited by ClawScan on May 1, 2026.
Overview
This is a coherent, instruction-only SEO auditing skill, with only low-level notes around optional connected SEO data, external reference docs, and suggested persistent audit memory.
This skill appears safe for its stated purpose. Before installing, be aware that it may fetch webpages, use connected SEO or Search Console data if available, consult linked GitHub workflow docs, and suggest saving audit summaries to memory. Use it with URLs, exports, and memory updates you are comfortable sharing with the agent.
Findings (3)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
If connected to SEO or Search Console tools, the agent may inspect private analytics or query data for the selected site.
The skill may use connected SEO or Search Console data if available. This is expected for an SEO auditor, but it can involve account-linked site performance data.
Use ~~web crawler, ~~SEO tool, and ~~search console when connected; otherwise ask for page URL/HTML, target keywords, and competitor URLs.
Only connect properties and exports you intend to audit, and avoid granting unrelated site or account access.
The agent may consult external instructions that were not part of this packaged review.
The skill points to external project documentation that is not included in the provided file manifest. This is not code execution, but it is a mutable external dependency for workflow details.
finish with the standard handoff summary from [Skill Contract](https://github.com/aaron-he-zhu/seo-geo-claude-skills/blob/main/references/skill-contract.md)
Review external linked workflow documents before relying on them, or prefer packaged copies for stable behavior.
SEO findings or priorities may persist beyond the current task and be reused in later sessions.
The skill suggests writing audit summaries and priorities into persistent memory files, which can shape future agent context.
Writes: a user-facing audit or optimization plan plus a reusable summary that can be stored under `memory/audits/`. Promotes: blocking defects, repeated weaknesses, and fix priorities to `memory/open-loops.md` and `memory/decisions.md`.
Review any memory updates before saving them, and keep untrusted page text or sensitive business details out of persistent summaries.