Build a competitor messaging teardown with a prompt built for Claude and Perplexity. It supplies context, constraints and an output contract, then asks the model to surface assumptions and gaps. Copy it, fill the variables and treat the result as a structured draft, not a final answer.
4.7(74 ratings)668 copies
Updated By Site Admin
49 words · v1.0
Fill in the blanks · 1 variable
Claude promptReplace every highlighted token before sending
<task>
Analyse the competitor pages below and produce a messaging teardown. For each: positioning, primary promise, proof, target segment, tone and gaps. Then give a positioning map and three messaging angles we could own. Cite the exact page text for each claim and mark anything you are inferring.
Pages:
{pages}
</task>
Think carefully before answering. Keep any reasoning separate and put the final deliverable inside <answer> tags.
Share what worked, what broke and which model you used. Comments appear after posting and are moderated for spam.
How to use this prompt
1
Open Claude and start a new chat. Paste the prompt exactly as written.
2
Replace each placeholder ({pages}) with your own details. Leave the instructions and the output format untouched.
3
Add one concrete example or data point if the model's first answer is vague. Specific input produces specific output.
4
Run it once, then ask for a single revision with a specific critique rather than regenerating from scratch.
5
Review the result. Search volume, competition, every statistic and the final claim in a real keyword tool and primary source.
Worked example
This is the kind of input the prompt expects and the shape of output it produces. Your result will differ with the model and the details you supply.
Example input
Pages: your pages
Example output
**Search intent:** informational, early-stage. The searcher wants a definition and a comparison, not a sales page.
**Recommended H1:** What Is X and When Should You Use It?
**Direct answer (52 words):** X is … It matters because … Use it when … Avoid it when …
**Outline:** five H2s, each answering a real question, with one original example and one cited source per section. Internal links point to the pricing page and two related guides. Flagged two claims that need a citation and one keyword that is too broad to target.
Tips for a better result
Ask for the direct answer first, then the outline. It keeps the page anchored to search intent.
Require a 'what the current results miss' section to avoid producing the same page as everyone else.
Keep keyword targets realistic; a model cannot validate search volume, so check it in a real tool.
Change one variable at a time and compare the outputs; it is the fastest way to learn what this model responds to.
Common mistakes
Publishing keyword-stuffed pages with no first-hand experience or original evidence.
Trusting invented search volumes, difficulty scores or competitor traffic numbers.
Using AI to scale hundreds of near-duplicate location pages without unique value.
Verified Knowledge · FAQ
Questions about this prompt
Practical answers about running the build a competitor messaging teardown prompt.
Related prompts
Same job, a different angle — or the next step in the workflow.
A seo & marketing prompt for create a UTM naming convention. It gives ChatGPT and Claude a clear role, explicit constraints and a defined output, so the first answer is closer to usable. Fill in the variables, run it once, then use the verification notes on this page to review the result.
Turn customer objections into content with a prompt built for Claude and ChatGPT. It supplies context, constraints and an output contract, then asks the model to surface assumptions and gaps. Copy it, fill the variables and treat the result as a structured draft, not a final answer.
A seo & marketing prompt for write a press pitch with a news hook. It gives ChatGPT and Claude a clear role, explicit constraints and a defined output, so the first answer is closer to usable. Fill in the variables, run it once, then use the verification notes on this page to review the result.
ChatGPTClaude
4.8(51)625 copies
SA
Written and reviewed by Site Admin
Author & Platform Administrator
Administrator and lead editor at AIPrompt123, curating high-performance AI prompts, SEO/AEO/GEO strategies, and developer repositories.
Last reviewed 7 November 2025 · version 1.0 · tested on Claude, Perplexity
Comments
Share what worked, what broke and which model you used. Comments appear after posting and are moderated for spam.