Fact Check
Installation
SKILL.md
Fact Check: Verify Before You Ship
Verify that every claim, reference, and technical detail is backed by current evidence. AI models have training data cutoffs and frequently hallucinate version numbers, API signatures, field names, CLI flags, and dates. This skill provides a systematic process to catch these errors before they reach users.
Why This Exists
AI models commonly produce these types of false information:
| Category | Example of Hallucination |
|---|---|
| Model names/versions | Referencing "GPT-5" or "Claude 4" when they don't exist yet |
| API field names | Writing likeCount when the real API returns like_count |
| CLI flags | Using --recursive when the tool only supports -r |
| Library methods | Calling .transformAll() on a library that has no such method |
| Dates | Getting today's date wrong, or citing a "2024 release" that happened in 2025 |
| SDK versions | Referencing v2.0 features when the latest is v1.8 |
| Repo structure | Claiming a file exists at a path where it doesn't |
| Default values | Stating "default is 100" when the actual default is 50 |