--- title: GitHub - SerhiiKorniienko/bullshit-detector: Agent... description: Bullshit Detector is an open-source agent skills package that fact-checks YouTube videos, articles, tweets, TikToks, and PDFs. It extracts claims one by one,... canonical: https://daily.dev/posts/github---serhiikorniienko-bullshit-detector-agent-skills-that-fact-check-the-internet-claim-by-cla-wbgraxovk twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: GitHub - SerhiiKorniienko/bullshit-detector: Agent skills that fact-check the internet: claim-by-claim verification with sources and a 0-10 BS score for any YouTube video, article, tweet, or PDF | daily.dev og:description: Bullshit Detector is an open-source agent skills package that fact-checks YouTube videos, articles, tweets, TikToks, and PDFs. It extracts claims one by one,... og:url: https://daily.dev/posts/github---serhiikorniienko-bullshit-detector-agent-skills-that-fact-check-the-internet-claim-by-cla-wbgraxovk og:image: https://api.daily.dev/og/posts/WbGrAXovk.png og:image:alt: GitHub - SerhiiKorniienko/bullshit-detector: Agent skills that fact-check the internet: claim-by-claim verification with sources and a 0-10 BS score for any YouTube video, article, tweet, or PDF og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # GitHub - SerhiiKorniienko/bullshit-detector: Agent skills that fact-check the internet: claim-by-claim verification with sources and a 0-10 BS score for any YouTube video, article, tweet, or PDF **[Hacker News](https://daily.dev/sources/hn)** · 7 min read · 1 upvotes · 0 comments ## Summary Bullshit Detector is an open-source agent skills package that fact-checks YouTube videos, articles, tweets, TikToks, and PDFs. It extracts claims one by one, verifies each against independent web sources, scans for hype signals, analyzes incentives, and produces a 0–10 BS score with per-claim verdicts (confirmed, plausible, misleading, false, unverifiable). Built as portable Agent Skills in plain markdown and self-contained Python, it works with Claude Code, OpenAI Codex, OpenCode, Cursor, and other agents supporting the skills format. A companion fetch-content skill handles ingestion from any URL without API keys, using yt-dlp for video captions and readability extraction for articles. Installation takes 30 seconds via npx or as a Claude Code plugin. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Community take How the wider developer community reacted, aggregated from 1 discussion and 78 comments across hackernews (as of 2026-07-29). **TL;DR:** The community is cautiously interested in an AI-powered fact-checking/bullshit-detector tool, but raises serious concerns about ground truth sourcing, news syndication, and whether LLMs are fundamentally suited for truth verification. The author's use of AI-generated comments early on also drew criticism. **Sentiment:** 30% positive · 45% mixed · 25% skeptical **The case for** - Using AI enables real-time, scalable fact-checking that was previously impossible by human hands (e.g., tracking political misinformation). - The approach of splitting content into claims and doing per-claim web searches is seen as a reasonable architecture. - Telling the model to use 'credible sources' and watching its reasoning trace can be surprisingly effective. **The pushback** - No reliable ground truth: when sources conflict, the tool can only flag 'misleading/unverifiable' without resolving the dispute. - News syndication means what looks like 10 independent sources may actually be just 2, undermining multi-source verification. - LLMs may not be capable of genuine truth-discernment when most news sources are incentivized for views rather than accuracy. - The author initially posted AI-generated comments on HN, which the community flagged as ironic and off-putting for a 'bullshit detector' project. - One commenter dismissed it as a low-effort, vibe-coded project unworthy of Show HN. **By community** - hackernews (mixed): Commenters engage substantively with the tool's concept but are skeptical about its epistemological foundations and the author's credibility after using AI-generated comments. **Hottest debate:** Whether LLMs can meaningfully determine truth when sources are syndicated, politically biased, or incentivized for engagement rather than accuracy. **Open questions** - How are independent sources vetted for truthfulness, and how are contradictory sources reconciled? - Who checks the checkers — is there a judge agent or community-driven source blacklist? - Can the tool work with local models given the dependency on a search backend? - Would a browser extension with Ollama/OpenRouter be a more practical delivery mechanism? **Highlights** > This is extremely problematic. Much of news is highly syndicated, so what looks like 10 credible sources are actually just 2. I think the best you can aim for is empirical sources: receipts, videos, photo evidence, public disclosures directly at the source. Archiving is ok if disclosed. I don't think LLMs can discern truth when the majority of news sources are incentivized primarily for views. > — [mtweak on hackernews · 2 comments](https://news.ycombinator.com/item?id=49098125) > Who checks the checkers? > — [N\_Lens on hackernews · 2 comments](https://news.ycombinator.com/item?id=49097557) > The author is posting comments here (all flagged at this time) that are very clearly AI slop, which is quite ironic. > — [outime on hackernews · 1 comments](https://news.ycombinator.com/item?id=49097550) > god i wish these low effort projects were banned from Show HN the entire premise of a "bullshit detector" that's entirely vibe-coded is laughable > — [o10449366 on hackernews · 1 comments](https://news.ycombinator.com/item?id=49098068) > I could imagine running multiple different AIs seeing if they agree if something is true. I imagine this is similar to how Twitter's/X's community notes work. Something along the lines of when you have two accounts that disagree traditionally and they agree on something. That's how you know it's likely to be true. So from that approach, you actually want to have two AIs that are on the other side of the spectrum of whatever you're trying to find out if it's true e.g. if a conservative AI and a liberal AI both agree that something is false, it's highly likely to be false. > — [autonomousErwin on hackernews · 1 comments](https://news.ycombinator.com/item?id=49098024) **Source threads** - [hackernews](https://news.ycombinator.com/item?id=49096917) · 48 points · 78 comments ## Similar posts on daily.dev - [Bots, bias, and bunk: How to tell what's real on the net](https://daily.dev/posts/bots-bias-and-bunk-how-to-tell-what-s-real-on-the-net-3ns3elibx) · The Register · 1 upvotes · 0 comments - [Detecting Vulnerabilities in Agent Skills with SkillSpector: From Green Checkmark to Real Security Judgment](https://daily.dev/posts/detecting-vulnerabilities-in-agent-skills-with-skillspector-from-green-checkmark-to-real-security-j-u6pwwx1n8) · Towards Data Science · 1 upvotes · 0 comments - [A fresh AI memory can still be false](https://daily.dev/posts/a-fresh-ai-memory-can-still-be-false-61h67oyao) · Medium · 0 upvotes · 0 comments - [Auditing Agent Skills: A Threat Model for the Next Generation of AI Package Managers](https://daily.dev/posts/auditing-agent-skills-a-threat-model-for-the-next-generation-of-ai-package-managers-vxdluywso) · DEV · 10 upvotes · 0 comments --- Tags: [#python](https://daily.dev/tags/python), [#ai-agents](https://daily.dev/tags/ai-agents), [#claude-code](https://daily.dev/tags/claude-code) [View this post on daily.dev](https://daily.dev/posts/github---serhiikorniienko-bullshit-detector-agent-skills-that-fact-check-the-internet-claim-by-cla-wbgraxovk) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"GitHub - SerhiiKorniienko/bullshit-detector: Agent skills that fact-check the internet: claim-by-claim verification with sources and a 0-10 BS score for any YouTube video, article, tweet, or PDF","url":"https://daily.dev/posts/github---serhiikorniienko-bullshit-detector-agent-skills-that-fact-check-the-internet-claim-by-cla-wbgraxovk","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/github---serhiikorniienko-bullshit-detector-agent-skills-that-fact-check-the-internet-claim-by-cla-wbgraxovk"},"datePublished":"2026-07-29T14:26:14.246Z","dateModified":"2026-07-29T15:11:45.104Z","description":"Bullshit Detector is an open-source agent skills package that fact-checks YouTube videos, articles, tweets, TikToks, and PDFs. It extracts claims one by one,...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/1a9d0cea7d7cd8c61f3e8ca136e641b7?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/1a9d0cea7d7cd8c61f3e8ca136e641b7?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Hacker News","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Hacker News","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/hn","url":"https://daily.dev/sources/hn"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/github---serhiikorniienko-bullshit-detector-agent-skills-that-fact-check-the-internet-claim-by-cla-wbgraxovk","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"python,ai-agents,claude-code","timeRequired":"PT7M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Hacker News","item":"https://daily.dev/sources/hn"},{"@type":"ListItem","position":3,"name":"GitHub - SerhiiKorniienko/bullshit-detector: Agent skills that fact-check the internet: claim-by-claim verification with sources and a 0-10 BS score for any YouTube video, article, tweet, or PDF"}]} ```