On-Page SEO Auditor & EEAT Scorer
v7.2.0On-page SEO audit: analyze titles, headers, images, internal links, and content quality with scored report, EEAT checks, and prioritized fix list. Part of a...
⭐ 2· 2.5k·6 current·6 all-time
byAaron Zhu@aaron-he-zhu
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description match the instructions and templates: the skill fetches pages, analyses titles/headers/images/links/content, and produces a scored repair plan. No unrelated binaries, env vars, or installs are requested.
Instruction Scope
Runtime instructions rely on WebFetch to read target pages and reference optional contextual files (CLAUDE.md, shared State Model) and memory/audits/ for handoff. These reads/writes are coherent with producing audits, but the skill will access any page URL you provide and will write audit outputs to agent memory/storage if available.
Install Mechanism
Instruction-only skill with no install spec and no code files; nothing is written to disk by an installer and there is no external package download.
Credentials
No environment variables, secrets, or unrelated credentials are requested. The optional note about 'MCP network access for SEO tool integrations' is only optional and not required by the skill as packaged.
Persistence & Privilege
always is false (not permanently forced), user-invocable is true, and model invocation is allowed (normal). The skill may write audit artifacts to memory/audits/ as part of its handoff behaviour, which is expected for an audit skill.
Assessment
This skill appears internally consistent for on-page SEO audits: it fetches pages and uses the included templates and rubrics to produce scored reports. Before installing or running it, avoid giving it URLs that expose internal/private systems (e.g., http://localhost or internal intranet addresses) because WebFetch will attempt to fetch whatever URL you supply. Also note it may read available agent context files (CLAUDE.md, shared state) and write audit outputs to your agent memory/storage (memory/audits/). There are no requested credentials, but if you later enable optional integrations (the SKILL.md mentions external SEO tools), review any additional required API keys before granting them. If you want higher assurance, inspect the full SKILL.md and templates locally to confirm no unexpected data-exfiltration instructions exist and monitor the first runs to verify stored outputs do not contain sensitive information.Like a lobster shell, security has layers — review code before you run it.
content-auditvk97dke0cpfgv76grp029s3tnbn84b94heeatvk97dke0cpfgv76grp029s3tnbn84b94hlatestvk97dke0cpfgv76grp029s3tnbn84b94hon-page-seovk97dke0cpfgv76grp029s3tnbn84b94hseovk97dke0cpfgv76grp029s3tnbn84b94hseo-auditvk97dke0cpfgv76grp029s3tnbn84b94h
License
MIT-0
Free to use, modify, and redistribute. No attribution required.