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claims like context windows, API limits, and version numbers, searches official sources to confirm them, then flags outdated info with corrections and citations.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.
npx skills add https://github.com/daymade/claude-code-skills --skill fact-checker