Read the following piece and identify the single load-bearing claim - the one that, if false, makes the rest of the argument collapse. State it in one sentence.
Then build the strongest possible argument against that claim. Cite specific counter-evidence, alternative framings, or assumptions the piece is making but not defending.
End with a one-line verdict: does the claim survive the attack, and what would the piece need to add for it to survive better?
The piece:
{{piece}}
Stress-test the load-bearing claim
Add to PromptPaste
Download PromptPaste for MacDownload PromptPaste for iPhoneDownload PromptPaste for iPadDownload PromptPaste for Mac & iPhone
the prompt
Example output
Load-bearing claim: 'Marketers will install a Mac/iOS clipboard app to save AI prompts.'
Strongest argument against:
- Marketers already have ChatGPT 'Saved Prompts,' Claude 'Projects,' and Notion templates. The bar for installing a fourth tool is high.
- The clipboard is a global system feature. A dedicated app for it competes with muscle memory built over decades.
- Prompts that work get refined in-context (in the chat). A clipboard app encourages saving snapshots of prompts, which decays as models change.
Verdict: the claim survives only if the pack content is dramatically better than what's saveable inside ChatGPT. Otherwise, the install never happens.
Common mistakes
Don't ask this on a piece you're emotionally attached to without being willing to act on the answer. The whole point is to discover when the argument doesn't work. Also: the model will sometimes mistake the topic for the load-bearing claim ('the load-bearing claim is that marketers exist'). If that happens, prompt again with 'no - the load-bearing decision claim, the one that this piece is asking the reader to believe in order to act.'
More from Power Prompts
Ask clarifying questions first
Before answering my next message, ask me up to 5 short clarifying questions about audience, length, tone, format, and any constraints I…
Distill a long doc
Read the following document and produce: 1. A one-line takeaway (the single most important thing). 2. The three highest-leverage facts…
Explain it for a specific reader
Explain {{topic}} to {{audience}} in under 100 words. Use only words and analogies they would recognize. No jargon unless you immediately…
Why it works
Most AI outputs are fine prose with one weak claim that nobody notices. This prompt isolates the weak claim. It asks the model to identify the single load-bearing assertion in a piece - the one that, if false, makes the rest collapse - and then to argue against it. This is surgically different from generic critique: it does not improve the writing, it stress-tests the argument. Use this on anything where being wrong has a cost: a strategy memo, a launch claim, a forecast, a recommendation in a doc. If the load-bearing claim survives the attack, ship. If it doesn't, the piece needs a different argument, not better prose.