DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to fact-check a viral video claim by claim before you act on it with Bullshit Detector

Get per-claim verdicts, sources, and a 0-10 BS score for a YouTube or TikTok video.

Short answer: Install uv from https://docs.astral.sh/uv/ if you don't have it; then npx skills@latest add SerhiiKorniienko/bullshit-detector; open your agent and ask: is this bullshit? <video URL>. All steps.

  • Top pick
  • Research
  • Intermediate
  • 30 minutes
  • From the README
  • Claude Code
  • Codex
  • Cursor
  • Gemini CLI

Remote script. The skills.sh installer copies skills from this GitHub repo, and the fetch script uses uv to resolve its own dependencies, so review the repo before running it on a machine you care about.

Who it is forA person who is about to act on, buy into, or share a viral 'make money with AI' or finance video and wants the claims checked first.

The problemViews, production value, and confidence are not evidence, and checking each claim by hand takes far longer than watching the video.

The outcomeA report that lists each claim with a verdict (confirmed, plausible, misleading, false, or unverifiable), a hype-signal scan, an incentive analysis, and a 0-10 BS score.

What you need first

  • uv installed (the fetch script uses it to resolve its dependencies)
  • An agent with web search and the ability to run scripts, such as Claude Code, Codex, Cursor, or Gemini CLI
  • A YouTube, TikTok, article, tweet, or PDF link, or pasted text

Steps

  1. Install uv from https://docs.astral.sh/uv/ if you don't have it.
  2. npx skills@latest add SerhiiKorniienko/bullshit-detector
  3. Open your agent and ask: is this bullshit? <video URL>
  4. Read the BS score and the per-claim verdicts.
  5. Open the sources linked for any claim you plan to act on and confirm them yourself.

Prompt for your agent

Using the bullshit-detector skills in SerhiiKorniienko/bullshit-detector, fact-check the video at <video URL> claim by claim. Return each claim with its verdict, its sources, and the overall 0-10 BS score. Verify that every verdict links to a source rather than relying on model memory.

Caveat. Web search is non-deterministic, so verdicts can change between runs and a single report is one reading, not a measurement.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for SerhiiKorniienko/bullshit-detector and "Fact-check a viral video claim by claim before you act on it"

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer