biaschecklisted

## Customization **Before executing, check for user customizations at:** `~/.claude/LIFEOS/USER/CUSTOMIZATIONS/SKILLS/BiasCheck/` If this directory exists, load and apply any `PREFERENCES.md` or additional reference files found there. These override default behavior. If the directory does not exist, proceed with skill defaults. # BiasCheck ## Voice Notification **When executing a workflow, do BOTH:** 1. **Send voice notification**: ```bash curl -s -X POST http://localhost:31337/notify \ -H "Content-Type: application/json" \ -d '{"message": "Running the Check workflow in the BiasCheck skill to audit the source"}' \ > /dev/null 2>&1 & ``` 2. **Output text notification**: ``` Running the **Check** workflow in the **BiasCheck** skill to audit the source... ``` ## What It Does Runs a three-layer bias audit on any source — a URL, a file path, or raw text. It fetches the content plus any study it cites, then checks (1) biases inside the data, (2) conflicts of interest in the source organization, and (3) distortions the journalism added on top. The output separates what the data actually supports from what got editorialized. ## The Problem Most "this is biased" arguments are vibes — a feeling about a source, with nothing concrete underneath. They're not repeatable and they don't tell you where the distortion lives. The other failure is analyzing an article without ever reaching the study it cites, so you critique the headline and never see