Critically appraise a research paper

Runs a full critical appraisal of a paper — findings, study quality, conflicts of interest and 1-10 scores for novelty, rigor and empiricism — ending in an A-F grade that penalises unreproducible methods.

PLPromptByte Library@promptbytePublished Jul 20

TextResearch #academic #critical reading #paper review #peer review #research

Version 1 of 1 · published Jul 20, 2026Version 1 · only version

Example output

See all results

Anthropic · Claude Opus 5 PLPromptByte Library Version 1

Prompt

Version 1 · 2 variables · 1 required

Fill in the values below — the customized prompt updates as you type. marks a required value.

Paper text{{paper_text}}

Paste the full paper or preprint, including the methods and results sections. Abstract-only input will produce mostly "not reported" rows.

Review focus(optional){{review_focus}}

What you most want scrutinised — a specific claim, the statistics, or the fit between the method and the conclusion. Default: the overall scientific rigor and whether the conclusions are supported by the data

Fill in Paper text to copy the customized prompt.

Resultsfor version 1

All models Claude Opus 51

Version 1 · only version

Claude Opus 5 result by PromptByte Library
Anthropic · Claude Opus 5 PLPromptByte Library (@promptbyte)Version 1Published Jul 20
Compare
SUMMARY Spaced retrieval beat massed review on delayed statistics tests, but weak transparency limits confidence. AUTHORS Okonkwo, A.; Lindqvist, M. AUTHOR ORGANIZATIONS Department of Psychology, Northfield University. FINDINGS - Spaced group outperformed massed group on the eight-week delayed test. - Reported effect: d = 0.42, 95% CI [0.13, 0.71], p = .004. - No advantage on the immediate post-test, only on delayed testing. STUDY OVERVIEW - Randomized classroom trial, 214 undergraduates, two conditions, one site, one semester. STUDY QUALITY - STUDY DESIGN: Randomized…
Community submittedFull output
Settings: Unknown
Open result

Showing all 1 public result on version 1.

Usage notes

Paste the full text of the paper or preprint. An abstract alone is not enough — the quality scores depend on the methods and results sections, and with only an abstract most of the STUDY QUALITY rows will come back "not reported".

The grading is deliberately harsh on transparency: a paper that reports statistics without showing how they were produced loses grades, and so does one whose data or code are unavailable. That is the point of the pattern, not a bug — it is calibrated for the reproducibility problem rather than for politeness.

Good uses: triaging papers before you cite them, preparing for a journal club, or running it on your own draft to see how a hostile reviewer will score you.

Two habits keep it honest. Check every extracted number against the paper yourself — the model transcribes, it does not verify. And read the "not reported" answers as findings in their own right: a paper that never states its sample size, effect size or analysis method has told you something important.

This appraises internal rigour only. It cannot check the paper against the wider literature or confirm that the results are correct, so pair it with a real literature search before you rely on the grade.

Attribution: adapted from https://github.com/danielmiessler/fabric by danielmiessler, licensed MIT. Source file: https://github.com/danielmiessler/fabric/blob/main/data/patterns/analyze_paper/system.md

Output1,987 characters

SUMMARY Spaced retrieval beat massed review on delayed statistics tests, but weak transparency limits confidence. AUTHORS Okonkwo, A.; Lindqvist, M. AUTHOR ORGANIZATIONS Department of Psychology, Northfield University. FINDINGS - Spaced group outperformed massed group on the eight-week delayed test. - Reported effect: d = 0.42, 95% CI [0.13, 0.71], p = .004. - No advantage on the immediate post-test, only on delayed testing. STUDY OVERVIEW - Randomized classroom trial, 214 undergraduates, two conditions, one site, one semester. STUDY QUALITY - STUDY DESIGN: Randomized between-subjects classroom trial; allocation procedure not described. - SAMPLE SIZE: 214 undergraduates at a single site; no power analysis reported. - CONFIDENCE INTERVALS: 95% CI [0.13, 0.71]; lower bound sits close to negligible. - P-VALUE: p = .004 on the delayed test; secondary comparisons uncorrected. - EFFECT SIZE: d = 0.42, small-to-moderate, with a wide interval around it. - CONSISTENCY OF RESULTS: Not reported; no replication or subgroup analysis. - METHODOLOGY TRANSPARENCY: Materials and code available on request only, not deposited. - STUDY REPRODUCIBILITY: Cannot be reproduced as written; scoring rubric unavailable. - DATA ANALYSIS METHOD: Independent-samples comparison of delayed scores; not preregistered. CONFLICTS OF INTEREST None declared in the text. Rating: NONE DETECTED. PAPER QUALITY Novelty: 4 - spacing effects are long established; the classroom setting is new. Rigor: 5 - randomized, but request-only materials and no preregistration. Empiricism: 8 - conclusions rest on collected outcome data rather than argument. Known [---4------] Novel Weak [----5-----] Rigorous Theoretical [-------8--] Empirical FINAL SCORE: C Clean randomization undercut by request-only materials and no preregistration. SUMMARY STATEMENT Spacing aided retention here, but the curriculum claim outruns one unreproducible single-site trial.

Critically appraise a research paper

Example output

Prompt

Resultsfor version 1

Models represented

Something wrong with this prompt?

Check reading comprehension against the supplied article

Plan a point-by-point response to manuscript reviewers

Turn study findings into a research-poster content plan

Map conflicting terminology across research disciplines

Audit in-text citations against the reference list

Create a repeatable observational data-collection protocol

Discussion 0

Example output

Prompt

Resultsfor version 1

Models represented

Something wrong with this prompt?

Related prompts

Check reading comprehension against the supplied article

Plan a point-by-point response to manuscript reviewers

Turn study findings into a research-poster content plan

Map conflicting terminology across research disciplines

Audit in-text citations against the reference list

Create a repeatable observational data-collection protocol

Discussion 0