Doublecheck

This is a three-layer verification pipeline that checks AI output for hallucinations and sourcing problems. It runs in two modes: active mode that stays on and adds inline verification to every substantive response, or one-shot mode where you point it at specific text. The pipeline extracts verifiable claims, runs web searches for supporting or contradicting sources, looks for hallucination patterns, and produces a structured report with links you can check yourself. It auto-escalates to a full report when it finds disputed claims or fabrication risks, and always runs the full check on high-stakes content like legal analysis or regulatory guidance. Useful when you need to trust the output or hand it to someone else.

skills.sh installs: 4.3K
GitHub stars: 41K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add github/awesome-copilot --skill doublecheck --agent claude-code

Installs into .claude/skills of the current project.

Files

Doublecheck

Run a three-layer verification pipeline on AI-generated output. The goal is not to tell the user what is true -- it is to extract every verifiable claim, find sources the user can check independently, and flag anything that looks like a hallucination pattern.

Activation

Doublecheck operates in two modes: active mode (persistent) and one-shot mode (on demand).

Active Mode

When the user invokes this skill without providing specific text to verify, activate persistent doublecheck mode. Respond with:

Doublecheck is now active. I'll verify factual claims in my responses before presenting them. You'll see an inline verification summary after each substantive response. Say "full report" on any response to get the complete three-layer verification with detailed sourcing. Turn it off anytime by saying "turn off doublecheck."

Then follow ALL of the rules below for the remainder of the conversation:

Rule: Classify every response before sending it.

Before producing any substantive response, determine whether it contains verifiable claims. Classify the response:

SKILL.md on GitHub