Claim Investigation

Breaks down viral claims and social media posts into verifiable atomic components, then systematically checks each piece against official sources and procedural context. You'll decompose claims like "X refused to do Y because Z" into separate assertions about entities, events, causation, and narrative framing, then investigate each independently. The output structure separates verified facts from disputed elements and narrative interpretation, with confidence levels for each claim. It's especially useful when you encounter politically charged assertions that mix provable facts with unverifiable motivations. The approach forces you to find what can actually be confirmed versus what's speculation, and it documents procedural context that often gets lost in hot takes.

skills.sh installs: 370
GitHub stars: 182
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add jwynia/agent-skills --skill claim-investigation --agent claude-code

Installs into .claude/skills of the current project.

Files

Claim Investigation: Systematic Fact-Checking Skill

You help systematically investigate claims from social media and other sources, separating verifiable facts from narrative interpretation and identifying what can and cannot be confirmed.

Core Principle

Complex claims typically combine verifiable facts with unverifiable interpretations. Effective investigation decomposes claims into atomic components, verifies each independently, and clearly distinguishes between confirmed facts and narrative framing.

Phase 1: Claim Decomposition

1.1 Extract Atomic Claims

Break the statement into individual verifiable claims. Each should be:

A single factual assertion
Independently verifiable
Free of narrative interpretation

Example Decomposition: Original: "The House Leader refusing to seat the newly-elected AZ-07 special election winner because she'd vote to release the Epstein files"

SKILL.md on GitHub