skills.rest
itsadijmbt
itsadijmbtCOMMUNITY
Explore all skills by this author →
GitHub

dingo-verify

Extract and verify factual claims from articles using Dingo's ArticleFactChecker.

1|Updated Apr 24, 2026
Search Tags:#fact-checking#web search#evidence#json report#claim extraction#llm verification#article verification
One-click install
npx skills add https://github.com/itsadijmbt/SecureMCP-Servers --skill dingo-verify
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: dingo-verify
Source: https://github.com/itsadijmbt/SecureMCP-Servers/tree/main/TEST_SERVERS/PORTED_TO_SECUREMCP/dingo/.claude/skills/dingo-verify
Command: npx skills add https://github.com/itsadijmbt/SecureMCP-Servers --skill dingo-verify

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill helps you verify factual claims in an article, reducing the risk of accepting misinformation by producing evidence-backed verdicts.

Core Features & Use Cases

  • Claim extraction and verification: Extracts multiple factual claim types from a document and verifies each claim using Dingo’s ArticleFactChecker.
  • Web-search supported evidence: Uses optional web search (via Tavily) to ground verdicts with external evidence when available.
  • Structured, machine-readable output: Outputs JSON containing summary metrics, false-claim comparisons, and a full per-claim overview suitable for downstream tooling.

Use case: You have a blog post or report and want to quickly audit whether key statements (dates, numbers, attributions, and technical claims) are true, false, or unverifiable.

Quick Start

Run the fact-check on your article file by calling: python ${CLAUDE_SKILL_DIR}/scripts/fact_check.py path/to/article.md.

Frequently Asked Questions about dingo-verify

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I fact-check an article with web-backed evidence?▼

Fact-checking an article involves extracting factual claims and running them through Dingo's ArticleFactChecker to generate a JSON report with evidence-backed verdicts. It accepts markdown, plaintext, and JSON/JSONL document formats.

Do I need an OpenAI API key to verify claims in a document?▼

Yes, an OPENAI_API_KEY is required to perform LLM verification on extracted claims. Optionally providing a TAVILY_API_KEY enables web search to ground the verification verdicts with external evidence.

What output format does the fact-checking report use?▼

The fact-checking process outputs a structured JSON report containing summary metrics, false-claim comparisons, and a full per-claim overview. This machine-readable format is designed for integration with downstream tooling.

Can I audit claims in a JSON file or only markdown articles?▼

You can audit claims in JSON and JSONL files in addition to markdown and plaintext articles. The Skill extracts multiple factual claim types from any of these supported document formats for verification.

What is the best way to verify dates and numbers in a blog post?▼

Verifying dates, numbers, attributions, and technical claims in a blog post is best handled by automated claim extraction and web-search supported evidence. This process evaluates key statements and flags them as true, false, or unverifiable.

Why does claim verification return a statement as unverifiable?▼

Claim verification returns a statement as unverifiable when the ArticleFactChecker cannot find sufficient external evidence via web search to confirm or deny the extracted factual claim. This reflects a lack of available sources rather than a processing error.

Related Skills

Explore More Content & Communication Skills→
devopstalesdevopstales
1

tavily

Search, extract, map, and crawl web content via Tavily's REST API.

Community
Intermediate
BIsnake2001BIsnake2001
12

hic-matrix-qc

Compute coverage, cis/trans ratios, and P(s) curves for Hi-C files.

Community
Advanced
Ramprasad4121Ramprasad4121
1

fp-check

Verify suspected security bugs and produce documented TRUE POSITIVE or FALSE POSITIVE verdicts.

Community
Advanced
MigoXLabMigoXLab
736

dingo-verify

Verify factual claims in articles using OpenAI GPT models and web search.

Official
Intermediate