Keyword Research and Clustering Prompt
Turns seed topics and any keyword data you paste into intent-labeled clusters mapped to pages, without the model inventing search volumes.
- ChatGPT
- Claude
- Gemini
Prompts for keyword planning, audits, briefs, on-page edits, links and schema that work from your own data.
These prompts cover the working parts of search engine optimization: deciding which queries deserve a page, briefing and reviewing content, writing title tags and meta descriptions, planning internal links, auditing technical issues from a crawl, updating older pages and writing structured data. Each one is built around material you supply, such as a Search Console export, a crawler report, a page inventory or the text of the page itself.
Choose by where you are in the work. If you have not yet decided what to publish, start with keyword research and then write a content brief for each page it identifies. If the page already exists, use the on-page review for a single query, the content refresh prompt when the page has aged, and the title and meta description prompt for a batch of tags. Site-wide questions about crawling and indexing belong with the technical audit; questions about how pages connect belong with internal linking.
A language model is good at the reasoning in SEO: reading intent, grouping queries, spotting gaps and conflicts in data, and drafting clear wording. It has no search volume database, cannot crawl your site and does not know what ranks today unless a tool or your own notes tell it. The prompts here say so explicitly, mark anything unverified, and follow Google Search Central's published guidance on people-first content and accurate markup. None of them can promise rankings, and you should check their output against your own data before acting on it.
Turns seed topics and any keyword data you paste into intent-labeled clusters mapped to pages, without the model inventing search volumes.
| If you need to… | Use |
|---|---|
| Decide which topics and queries each page should target | Keyword Research and Clustering Prompt |
| Find crawl, indexing and canonical problems in a crawler export | Technical SEO Audit Prompt |
| Plan a new page for a writer | SEO Content Brief Prompt |
| Improve or update a page that already exists | Content Refresh Prompt |
| Add structured data that matches what the page shows | Schema Markup (JSON-LD) Prompt |
Turns seed topics and any keyword data you paste into intent-labeled clusters mapped to pages, without the model inventing search volumes.
Audits an existing page section by section, decides whether to refresh, rewrite, merge or leave it, and lists what to keep, update, cut, add and verify.
Produces a writer-ready brief: reader intent, the angle only you can offer, a purposeful outline, evidence to gather and clear acceptance criteria.
Builds an internal link plan from your page inventory: topic groups, hub pages and specific source-to-target links with anchor text, using only real URLs.
Reviews one existing page against its target query and returns specific before-and-after edits to the title, headings, opening, coverage, links and images.
Writes unique, accurate title tags and meta descriptions for a batch of pages, with options, character counts and a check against what each page says.
Generates JSON-LD that mirrors what is visibly on your page, maps every property to its source text and refuses to add ratings or details that are not there.
Reviews crawl exports, URL lists and Search Console notes you supply, and returns evidence-backed findings ranked by impact with a fix and a check for each.
Guide
The five parts of a complete prompt (goal, context, task, constraints, output format), with a worked rewrite and a pre-send checklist.
Technical guide
How to split a large task into a sequence of focused prompts, design the handoffs between them, and debug the chain when a step goes wrong.
Guide
A diagnostic approach to weak AI answers: name the fault, trace it to the gap in your prompt, then follow up precisely or rewrite and start again.