Rate the truth claims in an argument

Breaks a piece of writing into its individual truth claims and rates each one A-F, with supporting evidence, counter-evidence and the logical fallacies at work.

PLPromptByte Library@promptbytePublished Jul 23

TextResearch #argument analysis #critical thinking #fact checking #research

Version 1 of 1 · published Jul 23, 2026Version 1 · only version

Example output

See all results

OpenAI · GPT-6 Astra PLPromptByte Library Version 1

Prompt

Version 1 · 1 variable · 1 required

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

Text to analyze{{input_text}}

The article, post, transcript or excerpt whose claims you want separated out and rated.

Fill in Text to analyze to copy the customized prompt.

Copy the prompt and open a model site to paste it. PromptByte never sends your prompt anywhere — providers do not accept pre-filled prompts through a link.

opens in a new tab

Resultsfor version 1

All models GPT-6 Astra1

Version 1 · only version

GPT-6 Astra result by PromptByte Library
OpenAI · GPT-6 Astra PLPromptByte Library (@promptbyte)Version 1Published Jul 23
Compare
ARGUMENT SUMMARY: Remote work destroyed productivity; universal return-to-office mandates and self-evident data are offered as proof. TRUTH CLAIMS: CLAIM: Remote work caused productivity to collapse. CLAIM SUPPORT EVIDENCE: - Firm-level studies of fully remote periods report lower measured output in some coordination-heavy roles; cite each study, year and outcome measure. [insert verified reference] - Manager-reported surveys in several sectors record perceived declines in collaboration. [insert verified reference] CLAIM REFUTATION EVIDENCE: - Randomized and quasi-experimental studies of…
Community submittedFull output
Settings: Unknown
Open result

Showing all 1 public result from GPT-6 Astra on version 1.

Usage notes

Paste an opinion piece, a press release, a policy brief, a founder's blog post — anything that mixes assertions with rhetoric. The value is the separation: the pattern pulls each factual claim out of the prose so you can see how many of them are actually load-bearing, and how few tend to be checkable.

Run it on writing you agree with as well as writing you don't. Claims that support your own position get the same A-F treatment, which is the whole point.

The hard limit is references. A model without live search cannot supply verifiable citations, and this pattern explicitly demands them, so run it with browsing or retrieval enabled where you can. Without that, read the evidence sections as a research to-do list — the shape of the case for and against each claim, which you then go and confirm — not as findings. Anything left marked unverified has not been checked by anyone.

The LABELS list in the original included political characterisations; this version keeps the neutral ones (specious, weak, baseless, emotional, fallacious) so the output stays about argument quality rather than tribe.

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

Rate the truth claims in an argument

Example output

Prompt

Resultsfor version 1

Something wrong with this prompt?

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

Draft a qualitative codebook from anonymized excerpts

Discussion 0

Example output

Prompt

Resultsfor version 1

Something wrong with this prompt?

Related prompts

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

Draft a qualitative codebook from anonymized excerpts

Discussion 0