blog-factcheck

Extract numeric claims from blog posts and verify them against cited URLs.

8|5|Updated Feb 18, 2026
One-click install
npx skills add https://github.com/shenxingy/Clade --skill blog-factcheck-shenxingy
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: blog-factcheck
Source: https://github.com/shenxingy/Clade/tree/main/configs/skills/blog-factcheck
Command: npx skills add https://github.com/shenxingy/Clade --skill blog-factcheck-shenxingy

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Blog posts often include statistics, percentages, and attributed claims that may be outdated, misquoted, or missing proper sourcing, and you need a reliable way to confirm what the cited sources actually say.

Core Features & Use Cases

  • URL-backed claim verification: Fetches each cited URL and checks whether the claimed numeric values appear on the page.
  • Claim extraction for numeric assertions: Extracts statistical claims (numbers, percentages, dollar figures, and related attribution) from the blog text.
  • Confidence scoring with clear outcomes: Produces a report with VERIFIED, PARAPHRASE, WEAK, NOT FOUND, and UNVERIFIED results, flagging uncited claims for follow-up.

Quick Start

Ask the assistant to fact check a blog post file by running: /blog factcheck path/to/post.md

Frequently Asked Questions about blog-factcheck

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

FAQPage Schema
How do I verify statistics and claims cited in a blog post?

To verify blog statistics, this Skill extracts numeric assertions and fetches each cited source URL to check if the claimed values appear on the page. It scores verification confidence and flags uncited or unreachable evidence as UNVERIFIED.

Can I check if the numeric figures in my markdown blog match their web sources?

Yes, you can run a source check on a markdown file to validate blog citations. The Skill fetches cited URLs, searches retrieved page content for claimed values, and produces a report confirming whether your figures match the sources.

What does the confidence scoring report look like for blog fact checking?

The blog fact checking report produces outcomes including VERIFIED, PARAPHRASE, WEAK, NOT FOUND, and UNVERIFIED. It flags uncited claims or unreachable evidence for follow-up to ensure source attribution aligns with the post text.

How do I extract statistical claims from blog text for validation?

Claim extraction identifies numbers, percentages, dollar figures, and related attribution from the blog text. Extracted numeric assertions are then matched against fetched web page content to confirm the cited sources actually say what the post claims.

What happens to uncited claims or broken links when validating blog citations?

When validating blog citations, the Skill flags uncited claims and unreachable source URLs as UNVERIFIED. This ensures that any missing or broken source attribution is explicitly highlighted in the final confidence scoring report for follow-up.

Do I need to install any dependencies to run a source validation on a blog post?

No dependencies are required to run source validation. You can execute the fact checking process directly by asking the assistant to run the command on your target blog post file path.