Technical SEO & Keyword Cluster Audit

What it does

/seo-audit is a Cursor slash command. Type it in chat to run a saved workflow: Technical SEO & Keyword Cluster Audit.

Conducts full technical SEO audits: checks title tag lengths, meta descriptions, single H1 tags, JSON-LD schemas, canonical links, and keyword rankings.

Scans meta titles, descriptions, heading tags, schema markup, and sitemaps. Unlike a skill, a command is something you invoke on purpose. The agent does not decide to run /seo-audit for you.

Why it exists

Founders retype the same multi-step prompt until it rots. /seo-audit exists so the pipeline, all 4 steps of it, is a file in .cursor/commands, versioned with the repo.

It ships in the Marketing Kit. It is wired to the Technical & On-Page SEO Lead (seo-specialist) and Content Strategy Lead (content-marketer) agents. Required skills: On-Page SEO & Semantic HTML Architecture; Entity SEO & JSON-LD Structured Data; Pillar-and-Cluster Content Architecture.

When to use it

• Use to ensure marketing pages rank high on Google and avoid search penalties.
• Use /seo-audit when you want that pipeline, not a freeform chat. If you only need one step, use a narrower command or a single agent.
• Start a new chat. Do not run this command in a thread that just touched production SQL.

When not to use it

• Do not run /seo-audit as a substitute for reading the diff. The command produces files; you still gate them.
• Do not chain it into a 40-turn chat. Fresh context is part of the design.
• Do not run it if you have not filled CURSOR.md. The pipeline will invent a stack.

Example workflow

1. Audit title tags and meta descriptions for target keyword density and character length
2. Validate single H1 tag presence and proper semantic heading hierarchy
3. Inspect JSON-LD structured data (SoftwareApplication, Organization, FAQ)
4. Generate actionable SEO fixes report with exact replacement tags

Example usage

Type this in Cursor chat: /seo-audit Perform technical SEO scan on landing page and pricing table

The command file tells the session which agents to adopt and which skills to read. You should see phase headers, not a single dump of code.

If a phase fails its gate, stop. Do not add 'just continue'.

Example output

• Expected artifact: docs/marketing/seo-audit.md

Best practices

• Keep the prompt specific. /seo-audit Perform technical SEO scan on landing page and pricing table is the shape: object, constraint, and outcome.
• Let the listed agents work in order: seo-specialist → content-marketer.
• Save outputs in the repo. Chat-only answers evaporate.
• Marketing commands write to docs/marketing/ so the next command can read positioning before it writes a landing page.

Common mistakes

• Typing /seo-audit with no object ('do the thing'). The pipeline will guess.
• Re-running the command in the same chat after a failed gate instead of fixing the failing file.
• Editing the command file to skip review so it 'goes faster'.
• Skipping the On-Page SEO & Semantic HTML Architecture skill that the command depends on.