Prompt: Cluster Keywords by Search Intent
A prompt for grouping a keyword list into intent-based clusters for content planning, without inventing search volume data.
The prompt
You are an SEO strategist grouping keywords for content planning.
Objective: Analyse the keyword list below and organise it into clusters by shared search intent, suitable for one page per cluster.
Context: The site covers {{SITE TOPIC — e.g. a project management tool for small agencies}}. Example: a cluster labelled "buying-stage decision" would group transactional keywords like "software pricing" together, separate from an informational cluster like "how to manage projects". Keywords:
{{PASTE KEYWORD LIST HERE, ONE PER LINE}}
Constraints:
- Use only the keywords supplied — do not add keywords you think should exist
- Do not state or estimate search volume, difficulty or ranking potential; none of that data was supplied
- Each cluster needs a short label and the intent type (informational, commercial, navigational or transactional)
- Flag any keyword that doesn't clearly fit an intent as "unclear" rather than forcing it into a cluster
Output format: Return each cluster as a Markdown heading with its intent type, followed by its keywords as a bulleted list, then a final "Unclear" section for anything that didn't fit.
Before finishing, check every supplied keyword appears exactly once across the clusters and the unclear section combined, and that no search volume or ranking figures were stated.
Example
Input
SITE TOPIC — e.g. a project management tool for small agencies: a project management tool for small agencies PASTE KEYWORD LIST HERE, ONE PER LINE: project management software for agencies best project management tool for small teams how to manage client projects project management software pricing agency project management what is a gantt chart project management software free trial
Output
## Best-fit comparison (commercial) - best project management tool for small teams - project management software for agencies ## Buying-stage decision (transactional) - project management software pricing - project management software free trial
Show more
## Concept education (informational) - how to manage client projects - what is a gantt chart ## Unclear - agency project management — too broad to assign a single intent without more context on the searcher's stage All 7 supplied keywords appear exactly once across the three clusters and the unclear section, no search volume or difficulty figures were stated anywhere, and no keyword beyond the original list was added.
Why it works
- Restricting the model to only the supplied keywords stops it inventing plausible-sounding search terms nobody actually searches for.
- Banning invented search volume or difficulty numbers keeps the output honest about what data was and wasn't provided.
- An explicit 'unclear' category is more useful than forcing every keyword into a cluster it doesn't cleanly belong to.
Why the basic version fails
“Cluster these keywords for me” often returns confident-sounding search volume estimates and difficulty scores that were never supplied, alongside clusters that force ambiguous keywords into categories where they don’t really belong.
What this prompt fixes
Restricting the model to only the supplied keyword list stops it padding the output with invented terms. Banning volume and difficulty estimates keeps the output honest about what data exists, and the “unclear” category is more useful than a forced, wrong classification.
Tips per model
- ChatGPT occasionally adds search volume figures unprompted, drawing on general knowledge — the explicit ban is needed even with a clear list.
- Claude tends to be more conservative about inventing data by default, which suits this task well.
- If most keywords end up “unclear,” the list is probably too broad for one content plan — narrow it to a single topic area first.