Research

Claim Extractor for Fact-Checking

Pulls checkable claims out of any text, ranked by risk.

The Prompt

Extract every factual claim from this text:
[paste text]

For each claim: (a) quote it, (b) classify as checkable/opinion/prediction, (c) rate how load-bearing it is for the overall argument, (d) note what source type would verify it. Rank by "damage if wrong".

 Fill in before using

[text]

How to use it

→ Paste the prompt into your model of choice — it works with any frontier model.
→ Replace every bracketed placeholder with your specifics. Concrete inputs beat vague ones every time.
→ If the model asks a clarifying question, answer it — these prompts are designed to invite that.
→ Iterate on the output, not the prompt. The structure is already tuned.

fact-checkingverification

More Research prompts

Deep Research Brief

Turns a broad question into a structured research plan.

Paper Analyzer

Extract claims, methods, and weaknesses from any paper.

Steelman Both Sides

The strongest honest case for each side of a debate.