{
 "schema": "aiblocks-page/1",
 "id": "persuasive-claim-truth-checker",
 "type": "skill",
 "name": "Persuasive claim truth checker",
 "summary": "Check a persuasive article, pitch or post with this claim truth checker. Get each claim sorted as supported, false, misleading or unknown.",
 "headline": "Persuasive claim truth checker",
 "subhead": "Share the message and the decision it is trying to influence. It separates factual claims from hints, value judgments, and predictions, then checks authoritative sources. You get a claim-by-claim report showing what is supported, contradicted, misleading, unclear, or still unknown.",
 "job": {
  "id": "research-topics",
  "name": "Research a topic properly"
 },
 "level": "intermediate",
 "thinking": "high",
 "tested": true,
 "updated": "2026-10-28",
 "first_published": "2026-10-25",
 "inputs": [
  {
   "type": "source_text",
   "required": true,
   "label": "Source text",
   "what": "a long source in full: an article, a video or talk transcript, or notes from a book, with its title, author and link"
  },
  {
   "type": "question",
   "required": false,
   "label": "Question",
   "what": "the problem, decision or piece of work you want help with, and what a good outcome looks like"
  }
 ],
 "outputs": [
  {
   "type": "audit_report",
   "required": true,
   "label": "Audit report",
   "what": "findings with evidence, severity, missing inputs and next actions"
  }
 ],
 "you_give": [
  "The original message or source, its context, and the decision or claim to check."
 ],
 "you_get": [
  "A truth assessment, source ledger, missing context, and proportionate next verification step."
 ],
 "use_when": [],
 "skip_when": [
  "You want broad research on a whole topic, not one message: use the Literature reviewer, or ask your AI to run a wider search first.",
  "You need a medical, legal or technical claim settled: ask a doctor, lawyer or domain expert.",
  "You want to know if a person is lying from their video, voice or body language: this tool does not do that."
 ],
 "output_sample": {
  "input": [
   "The article, pitch or post you want checked",
   "Its link, if it has one",
   "The decision it is trying to move (buy, share, vote, act)"
  ],
  "prerequisites": [
   "An AI that can search the web or open original sources such as official records and studies"
  ],
  "output": [
   {
    "name": "Bottom line",
    "contains": "One verdict for the message: supported, false, misleading, complicated, unsupported or unknown."
   },
   {
    "name": "What is true",
    "contains": "The parts that evidence supports, each linked to its source."
   },
   {
    "name": "What is false",
    "contains": "Only the claims that evidence directly contradicts, with that evidence."
   },
   {
    "name": "What is complicated, and why",
    "contains": "Qualifiers, mixed evidence, limits of scope and value judgments that are not facts."
   },
   {
    "name": "How the message steers perception",
    "contains": "The persuasion techniques used and the conclusion each one invites, without guessing intent."
   },
   {
    "name": "Authoritative-source check",
    "contains": "The direct source for each key claim, when it was opened, and whether it settles the claim."
   },
   {
    "name": "Evidence ledger",
    "contains": "Each claim with its source, source type, limits and confidence."
   },
   {
    "name": "Decision-safe next step",
    "contains": "The smallest action that would cut the remaining doubt."
   }
  ]
 },
 "how_to_use": [
  "Open a chat AI that can search the web or read links. Paste in this skill. If it cannot browse, it will mark sources it could not open as unknown. The skill also names two helper files, references/claim-audit.md and assets/claim-audit.md. The check works without them in a chat.",
  "Paste the full article, pitch or post. Add its link if it has one.",
  "Say what decision it is trying to move, such as a purchase, a share or a vote.",
  "Read the Bottom line first. Then open the sources in the Authoritative-source check.",
  "Do the Decision-safe next step before you act on a high-stakes claim.",
  "To check the claims in your own copy before you publish, use the Claim evidence checker."
 ],
 "checks": [],
 "next": [
  {
   "name": "Claim evidence checker",
   "url": "https://useaiblocks.com/skills/claim-and-proof-matcher",
   "why": "Check it before it goes live"
  },
  {
   "name": "Claim fact checker",
   "url": "https://useaiblocks.com/skills/claim-fact-checker",
   "why": "Decide what to do"
  }
 ],
 "source": {
  "by": "Magnus Hedemark",
  "repo": "magnus919/agent-skills",
  "url": "https://github.com/magnus919/agent-skills/tree/92c327e525da69c9ad3812fd223a1770e977c2e3/de-spin",
  "licence": "MIT",
  "original_name": "de-spin",
  "commit": "92c327e525da69c9ad3812fd223a1770e977c2e3"
 },
 "credits": [
  {
   "title": "de-spin skill",
   "by": "Magnus Hedemark",
   "url": "https://github.com/magnus919/agent-skills/tree/92c327e525da69c9ad3812fd223a1770e977c2e3/de-spin",
   "used": "Copied under the MIT licence. We gave it a plain name. We added Before you start and After this sections that link to other AI Blocks steps."
  }
 ],
 "files": [
  "assets/claim-audit.md",
  "evals/evals.json",
  "LICENSE.md",
  "README.md",
  "references/claim-audit.md",
  "references/empirical-foundations.md"
 ],
 "links": {
  "page": "https://useaiblocks.com/skills/persuasive-claim-truth-checker",
  "markdown": "https://useaiblocks.com/skills/persuasive-claim-truth-checker.md",
  "json": "https://useaiblocks.com/skills/persuasive-claim-truth-checker.json",
  "instructions": "https://useaiblocks.com/skills/persuasive-claim-truth-checker/SKILL.md",
  "download": "https://useaiblocks.com/skills/persuasive-claim-truth-checker.zip",
  "api_item": "https://useaiblocks.com/api/v1/items/persuasive-claim-truth-checker",
  "api_document": "https://useaiblocks.com/api/v1/documents/skill/persuasive-claim-truth-checker",
  "mcp": "https://useaiblocks.com/mcp"
 }
}