What it does. Separate what's verifiably true from what's hype in any piece of content.
Start at step 1 now. The steps below are the plan — they are already ordered, and each one says what it needs. There is nothing to work out in advance, and working it out anyway is measurably expensive: across 35 instrumented runs the phase before the first tool call is almost entirely deliberation, 15% of all the thinking a run does, and the single longest uninterrupted block on record — 421 seconds — sits there, before a claim had been read or a search issued. Read step 1, do step 1.
When to use it. Fact-check and hype-audit content. Extracts the discrete claims from a video, article, tweet, or PDF, verifies each against independent sources via web search, and produces a report card with…
Install
npx skills add SerhiiKorniienko/bullshit-detector --skill bullshit-detector
Or copy the skill folder manually:
git clone https://github.com/SerhiiKorniienko/bullshit-detector.git
cp -r bullshit-detector/skills/analysis/bullshit-detector/ ~/.claude/skills/bullshit-detector
Source: SerhiiKorniienko/bullshit-detector — 139 stars, MIT, last pushed 2026-09-02.