SEO agent skill for OpenClaw,Claude Code, and AI agents. Generate beginner SEO audits and advanced technical SEO reports for any page.
v1.0.0An SEO agent skill for quick, lightweight, default single-page SEO audits. Performs basic on-page and site-level checks and outputs a structured basic SEO au...
⭐ 0· 65·0 current·0 all-time
by程序员泥瓦匠@jeffli1993
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
medium confidencePurpose & Capability
The name/description (lightweight single‑page SEO audit) matches the included scripts and SKILL.md: page checks, site checks, JSON‑LD/schema validation, and PageSpeed calls. Required capabilities (HTTP fetch, HTML parsing, optional PageSpeed API) align with the stated purpose.
Instruction Scope
SKILL.md limits the checks (whitelist) and instructs the agent to run the included scripts and save an HTML report; it does not ask to read unrelated local files or secrets. It does require the agent to perform LLM reviews in some cases (llm_review_required flags), which means the agent will examine script outputs and page content for semantic judgement — expected for this skill but worth noting since LLM review can surface page text to models.
Install Mechanism
There is no install spec (instruction-only), but the package includes Python scripts. The scripts depend on the 'requests' package (SKILL.md and script comments mention 'pip install requests') — this dependency is not declared in registry metadata. No remote downloads or obscure installs are used.
Credentials
The skill requests no environment variables, credentials, or config paths. The only external service used is Google PageSpeed Insights (optional API key), which is appropriate for PageSpeed checks. There are no unrelated credentials requested.
Persistence & Privilege
always is false and the skill does not demand persistent system privileges or modify other skills. It writes report files (reports/<...>.html) as part of normal behavior; that is expected for a reporting tool.
Assessment
This skill appears to do what it claims: run site/page checks, schema validation, and optionally call Google PageSpeed. Before installing or running it, consider: 1) The scripts perform network requests to arbitrary target URLs and will save HTML reports to disk — run them in a controlled environment if you are concerned about file writes or contacting untrusted hosts. 2) The code includes SSRF protections (it resolves hostnames and blocks private/loopback/reserved IPs), but the checks are not bulletproof (single IP resolution, limited IPv6 handling). If you plan to run against untrusted or adversarial domains, test the SSRF protections first. 3) The scripts require Python and the 'requests' package; the registry metadata does not declare this dependency — ensure your runtime has it. 4) PageSpeed calls go to googleapis.com; you can optionally supply an API key. 5) Some checks mark items as 'llm_review_required' — running the skill will cause the agent to read/interpret page content and use the LLM for semantic judgements, which you should accept only if you are comfortable sending that content to the model. If you need higher assurance, review the included scripts yourself or run them in a sandbox before granting the agent access.Like a lobster shell, security has layers — review code before you run it.
latestvk973j95752hjjw1nv8jhedbajx84mtss
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
