Spot Logical Fallacies and Weak Arguments in Any Opinion Piece
Returns a ranked table that quotes each weak passage in an essay, names the fallacy, explains in one line why it fails, and suggests evidence that would fix it.
You getMain claim, table with columns and strongest points
Prompt
You are a critical-thinking instructor who teaches argument analysis to university students.
I will paste an opinion piece or essay right after this message. Read all of it, then find the logical fallacies and weak arguments in it.
Rules:
1. Quote each problematic passage exactly, in quotation marks, using no more than two sentences. Do not paraphrase.
2. Name the specific fallacy or weakness, such as hasty generalization, false dilemma or unsupported causal claim. If it does not fit a named fallacy, label it "weak support" and say why.
3. Explain why it fails in one sentence tied to this passage, not a textbook definition.
4. For each issue, describe the kind of evidence or reasoning that would make the point stronger. Do not invent statistics, studies or sources.
5. Rank issues from most to least damaging to the main argument and skip minor style nitpicks. Also name the piece's strongest points so the review is fair.
Output format:
1. Main claim: one sentence restating the author's thesis.
2. Table with columns: # | Quoted passage | Fallacy or weakness | Why it fails | What would strengthen it
3. Strongest points: 1-2 bullets.
4. Overall verdict: 2-3 sentences on how well the argument holds up.
End with one line listing any claims you could not judge without checking outside facts.Example output
Tips and common edits
Why this works
- Exact quotes force the model to point at real text, so you can verify each claim instead of trusting a vague summary.
- Ranking by damage to the main argument keeps the output focused on what matters, not on minor wording issues.
- Asking for strongest points and fixable evidence makes the review fair and useful rather than a one-sided takedown.
Use before sharing, citing or replying to an op-ed, essay or blog post. Paste the full text right after the prompt in ChatGPT, Claude or Gemini. It also works for checking your own draft.
Common edits
- Ask it to review your own essay draft and rewrite each flagged sentence with a stronger version.
- Limit the table to the top three issues for a quick read before sharing an article on social media.
Make it repeatable
Keep using this prompt without pasting it in every time.
Prompt details
- By
- Prompts-GPT editors
- Published
Did this prompt work?
Keep exploring
More like this
Break Down a News Article into Facts, Opinions and Loaded Wording
Paste any news article and get a table of quoted claims labeled verifiable, interpretation or unattributed, plus loaded words, missing context and a pre-share checklist.
Check a Website's Reliability with Lateral Reading Before You Cite It
Get a five-point lateral reading check of any site or organization, with search steps to verify each point and a clear cite, cite-with-caution or avoid verdict.
Compare How Different Articles Report the Same News Event
Get a side-by-side table showing which facts all your pasted articles agree on, where they conflict, what each leaves out, and how each frames the story.
Source Credibility Check with Claim-by-Claim Verification Plan
Lists every factual claim in a pasted article or claim, rates the evidence for each and says exactly what to verify and where.
Check Whether a Health Headline Matches the Study Behind It
Paste a headline and its study abstract to get a 1-5 accuracy score, a check table on study design and risk figures, and a plain-English rewrite.
Fact-Check a Viral Post or Forwarded Message Claim by Claim Before Sharing
Splits a viral post into separate claims, rates each one, and gives you exact search phrases and source types to confirm or debunk it before you share.
- Check Whether a Statistic or Chart in an Article Is Used Honestly
- Build a Verification Checklist for AI Answers and Their Citations
- Trace a Quote or Claim Back to Its Original Source Step by Step
- Paper Breakdown for Students with Seminar Questions
- Code Interview Transcripts into Themes with Participant Counts and Verbatim Quotes
- Design a Bias-Checked Survey Where Every Question Informs a Decision