⏳ This skill is pending AI review.
Scores will appear once the review pipeline completes.
seo-audit-agent
Deploy or update the SEO Audit Agent on Omnara, an agent that audits a web page for SEO, answer engines, and AI search citations and delivers a PDF report. Use when the user asks to deploy, set up, update, or remove the SEO audit agent.
Choose how to use this skill
You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.
1. Native installer
This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.
Do not guess an installer command or replace an existing version without reviewing the diff.
2. Complete package recommended
Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.
No complete ProSkills package is published for this listing yet.3. Prompt-only
Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.
Need only the instruction file?
Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.
No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.
// RATINGS
Not yet listed on ClawHub or SkillsMP
// README
SEO Audit Agent
An agent that audits a web page for an SEO agency. Give it a client's URL and it checks the page for classic search (SEO), answer engines (AEO), and AI search citations (GEO), compares it with the pages that compete for its query, and delivers a report as a PDF plus a markdown copy:
SEO audit: Acme Pricing, for "invoice software for small business"
SEO: B. Indexable and fast on desktop, but the mobile hero image delays the main content by 2.1 s.
AEO: C. The page never says what Acme costs in a sentence; the prices live in a JavaScript-rendered table.
GEO: D. The firewall answers OAI-SearchBot and PerplexityBot with 403, so ChatGPT search and Perplexity likely can't read the page; none of 10 buyer questions surfaced it, and two competitors appeared in 7.
Top fix: allow AI search crawlers in the firewall rule; the robots.txt already permits them.
Each fix comes ready to paste: a rewritten title and meta description, a JSON-LD block with the page's real details, robots.txt lines, and an answer-first opening paragraph. Every finding is marked measured or best practice, and the report lists what it couldn't check.
What you need
- An Omnara account (app.omnara.com) with a machine
pool;
default-poolworks as is - Optional: a Google API key for real-user speed data, and an OpenAI API key to check which sites OpenAI's web search cites. Without them, the agent uses lab speed numbers and a simulated AI search check.
Deploy
Open Claude Code, Codex, Cursor, or any other coding agent and say:
Read https://raw.githubusercontent.com/omnara-ai/omnara/main/examples/seo-audit-agent/SKILL.md and follow it to deploy the SEO audit agent.
Your coding agent follows SKILL.md, which is plain steps with the
exact npx omnara commands if you'd rather run them yourself. Run it again
any time to add a key or change the agent; it updates it in place.
How it works
agent.yaml is the whole agent. It runs on a machine from your project's pool, where the startup script installs Lighthouse and two helpers built on Playwright's headless Chromium: one renders the page after JavaScript runs, the other prints the report as a PDF.
- Without keys, it fetches the page as a browser and as each AI crawler, compares the HTML before and after JavaScript runs, runs Lighthouse for mobile and desktop, and checks robots.txt, the sitemap, metadata, headings, and structured data. For AI visibility, it writes the questions a buyer would ask and runs them through Omnara's web search, an AI search index, so the report labels those results simulated.
- With
GOOGLE_API_KEY, it adds real-user Core Web Vitals from the Chrome UX Report. - With
OPENAI_API_KEY, it asks the same questions through OpenAI's web search and reports which sites it cites, measured.
Keys are injected as environment variables on the machine and never appear in the config or the event log. The checks, the grading, and the report layout are plain instruction text you can read and edit.
// HOW IT'S BUILT
KEY FILES