Fact Checker

This does the unglamorous work of keeping technical docs accurate when AI models and specs change every few months. It scans documents for verifiable claims like context windows, API limits, and version numbers, searches official sources to confirm them, then flags outdated info with corrections and citations. The workflow is methodical: identify claims, search authoritative sources, compare, generate a report, wait for your approval, then apply edits. It's built for the specific pain of maintaining AI model comparisons and technical specifications that go stale fast. Honest take: if you maintain docs that reference Claude, GPT, or other rapidly evolving tools, this saves you from manually cross-checking everything against changelog pages.

skills.sh installs: 1.6K
GitHub stars: 1.5K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add daymade/claude-code-skills --skill fact-checker --agent claude-code

Installs into .claude/skills of the current project.

Files

Fact Checker

Verify factual claims in documents and propose corrections backed by authoritative sources.

When to use

Trigger when users request:

"Fact-check this document"
"Verify these AI model specifications"
"Check if this information is still accurate"
"Update outdated data in this file"
"Validate the claims in this section"

Workflow

Copy this checklist to track progress:

Fact-checking Progress:
- [ ] Step 1: Identify factual claims
- [ ] Step 2: Search authoritative sources
- [ ] Step 3: Compare claims against sources
- [ ] Step 4: Generate correction report
- [ ] Step 5: Apply corrections with user approval