Skip to content
  1. Home
  2. Prompt libraries
  3. Fabric pattern: analyze_claims

Fabric pattern: analyze_claims

Rate the truth claims in a text with evidence for and against

What it is

A Fabric pattern for critical reading. It asks the model to summarise the argument, separate out each truth claim, list supporting evidence and counter-evidence, flag logical fallacies and give each claim a rating, ending with an overall assessment. Useful as a first pass over opinion pieces, pitches or reports.

Good for

  • Check claims in an opinion article
  • Review a sales pitch for weak arguments
  • List counter-arguments to a report

Install or run

fabric --pattern analyze_claims

Command as given in the project README. Read the repository before you run anything on your machine.

What you need

Fabric CLI with a model API key, or paste system.md into any chat model

Worth knowingEvidence comes from the model's memory unless you add search, so cited facts need checking.

Sources

The summary is ours, written from the README. Spotted an error? See how we work.

More for data & research

See the topic →
  • Fabric pattern: extract_wisdom

    danielmiessler/Fabric

    Pull ideas, insights, quotes and habits out of long content

    PromptsGitHub stars: 45k
  • Academic Research AI Prompt Library

    bohyy/academic-ai-prompt

    Prompts for thesis topics, paper search and literature reviews

    PromptsGitHub stars: 2.4k
  • deep-research-prompts

    langgptai/awesome-deep-research-prompts

    Prompts for the deep research modes of ChatGPT, Gemini and others

    PromptsGitHub stars: 131
  • arXiv Search

    NousResearch/hermes-agent

    Search arXiv papers by keyword, author, category or ID

    SkillGitHub stars: 263k