hermes

Fact-check claims in a text

Checks each factual claim in a text against sources it actually retrieves, rates it with evidence and links, and says plainly when a claim cannot be verified. Use before publishing or sharing.

context

Professional fact-checkers check claims, not opinions, and they trace each claim to the most authoritative source available: the original dataset, study, document, statement or record, rather than another article repeating it. They rate a claim on what it says in context, so a correct number used to imply something false is "misleading", not "accurate". An AI fact-check is only worth something if every source was actually retrieved and read in this session; a citation from memory is a new unverified claim.

task

Fact-check this text ( mode):

text

  1. Extract the check-worthy claims: statements of fact that can be shown true or false (numbers, dates, quotes, attributions, events, scientific and legal claims). Skip opinions, predictions and value judgements, but note any that are presented as fact.
  2. Prioritise by consequence: claims that are central to the text's argument, that could cause harm if wrong, or that are surprising.
  3. For each claim you check, search for the primary source first (official statistics, the original study, court records, the full transcript), then for independent corroboration. Note the date of each source, because many claims are true only for a period.
  4. Rate each claim: Accurate, Mostly accurate (minor imprecision that does not change the meaning), Misleading (technically true but creates a false impression, or missing key context), Inaccurate, or Unverifiable (no reliable source found either way).
  5. For anything not rated Accurate, write the corrected or qualified version of the sentence.
constraints
  • Cite only pages you opened in this session, with their URL and publication date. Never cite from memory, and never construct a URL.
  • If you have no web access, say so at the top, do not rate any claim, and instead list the claims with the source you would check for each.
  • Treat "Unverifiable" as an honest result. Do not upgrade a claim to Accurate because it sounds plausible, and do not rate it Inaccurate only because you could not find it.
  • Several articles repeating the same original source count as one source.
  • Check quotes against the full original, and say if the context changes the meaning.
  • Stay neutral: rate the claim, not the author or their politics.
output format

Verdict

Two or three sentences: how reliable the text is overall and the most important problem.

Claims

A table: # | claim (quoted or tightly paraphrased) | rating | key source (linked).

Details

For each claim not rated Accurate: what the evidence shows, the sources with dates, and the reasoning.

Suggested corrections

The original sentence and the corrected version, for each claim that needs one.

1 required value still a placeholder; the assistant will ask for it.

details

kind
Prompt: a task you run by name to get one finished thing back
domain
Research and science
category
Fact-checking
level
Intermediate
made for
Writer / author, Editor, Researcher / scientist, Content creator
needs
web
risk
network
version
v1.0.0 · experimental
reviewed
2026-10-02
works in
Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Antigravity, OpenCode, Windsurf, Zed, Continue, AGENTS.md, ChatGPT, claude.ai

Edit on GitHubReport a problem

use in

Hodios CLI
npx @hermes-hq/hodios install fact-check-claims --target claude-code
Agent Skills
npx skills add hermes-hq/hodios-dist --skill fact-check-claims -a claude-code
Add the Hodios marketplace (once)
claude plugin marketplace add hermes-hq/hodios-dist
Install the research-science plugin
claude plugin install hodios-research-science@hodios

The plugin brings every entry in this domain at once.

pairs well with

All of Fact-checking
PromptFact-checking

Evaluate a source's credibility

Assesses how far a source can be trusted for a specific claim using lateral reading (author, evidence, funding, corroboration) and gives a reasoned verdict. Use before citing a source.

evaluate-source-credibility
PromptFact-checking

Check the statistics in an article

Checks an article's numbers for misleading percentages, missing base rates, cherry-picked windows and correlation sold as causation, recomputing what it can. Use before quoting it.

check-statistics-in-article
RuleFact-checking

Source and citation rules

Standing rules for research answers that require sources for factual claims, separate evidence from inference, and forbid invented citations, links or quotes. Use in any research or writing setup.

source-citation-rules
PromptFact-checking

Check a health or nutrition claim

Checks a health or nutrition claim against the hierarchy of evidence and explains in plain words what the research does and does not show, without personal medical advice. For health news readers.

check-health-claim
PromptFact-checking

Check a science news story against the paper

Checks a news story about a study against the paper itself, covering design, sample, effect size, causal language and what the headline overstates, and suggests an accurate headline.

check-science-news-against-paper
PromptFact-checking

Compare how outlets frame the same story

Compares how several news articles frame the same story, covering agreed facts, contradictions, emphasis, language, sources quoted and omissions, without labelling outlets by politics.

compare-news-framing