truthcheck
di baiyishr
PDF & DocumentsSintesi
Verify claims, fact-check content, check URL trustworthiness, and trace claims to their origin using the TruthCheck.
Descrizione
Cosa fa questa skill
TruthCheck is a CLI tool that verifies claims, rates URL trustworthiness, and traces misinformation to its origin. It returns a TruthScore from 0 to 100 with a breakdown across publisher credibility, corroboration, and existing fact-checks. An LLM can be added optionally to improve content analysis accuracy.
It combines publisher reputation scoring, web corroboration, and optional LLM analysis in one command, removing the need to manually cross-reference multiple fact-checking sites.
Quando usarla
- Checking a viral social media claim before sharing it
- Verifying sources cited in a document or report
- Detecting hallucinated URLs in AI-generated content
- Tracing a news story back to its original source
- Assessing publisher credibility before citing an article
Esempio di workflow
User asks: Fact-check this claim: 'Drinking coffee daily reduces Alzheimer's risk'
- 1
Run
truthcheck verify "Drinking coffee daily reduces Alzheimer's risk" --llm gemini - 2
Wait for the TruthScore and breakdown across publisher, content, corroboration, and fact-check dimensions
- 3
Parse the score label and supporting evidence summary
- 4
Report the verdict and which sources corroborate or contradict the claim
TruthScore: 65/100 (POSSIBLY TRUE) — some studies support an association, but evidence is inconclusive and no major health body has confirmed causation
Requisiti
- GEMINI_API_KEY — Google AI API key, needed only for --llm gemini (free tier available)
- OPENAI_API_KEY — needed only for --llm openai
- ANTHROPIC_API_KEY — needed only for --llm anthropic
- BRAVE_API_KEY — Brave Search API key, optional, improves search quality over default DuckDuckGo
Installazione
clawhub install baiyishr/truthcheckEsegui il comando CLI oppure incolla il prompt in Claude Code, Cursor, Codex o nell'agente di coding che usi.