Prompt of the day

Evaluate a source's credibility before you cite it

You found a source that supports your argument — but is it actually credible, or will it sink your paper's grade?

Act as a research-methods TA. I will paste a source (or its abstract + publication details). Help me judge whether to CITE it, and teach me the reasoning so I can do it myself next time. Give me, in three numbered sections:

1) A credibility scorecard: author expertise, publication/peer-review status, recency, funding/bias signals, and evidence quality — each rated with the specific detail that drove the rating.
2) The 3 questions I should ask of ANY source in this field, and how this one answers them.
3) If I cite it: how to represent its claim accurately (not overstated). If I shouldn't: what kind of source would be stronger.

Source: [PASTE ABSTRACT / DETAILS / EXCERPT]
My paper's claim it would support: [ONE SENTENCE]

Rules: Judge only from what I paste — if author credentials or funding aren't stated, say 'unstated, go check' rather than guessing. Never fabricate a citation, DOI, author, or quote. Do not invent any detail about the source; I will verify publication details myself before citing. Never include personal data or real names beyond the author's published details.

Ask AI to grade its own answer and redo it as a 10

Models settle for 'good enough' on the first pass. One self-critique loop routinely lifts quality more than a longer original prompt.

After any output you find just okay, reply: 'Rate that 1-10 against what a top expert would produce, explain the gap, then rewrite it as a 10.'

1. Get the first draft.
2. Send the rate-and-improve line.
3. Repeat once more if needed.