- Home
- Skills
- Research & Analysis
- Fact Check Pro — Investigate Claims & Separate Evidence
Works with the AI Agents you already use
Fact Check Pro — Investigate Claims & Separate Evidence
Investigate exact claims through source origins, chronology, context, independent evidence and quantitative checks with explained uncertainty.
$9.99
Fact Check Pro — Investigate Claims & Separate Evidence
Example session with this skill installed
Illustrative scenario: A fictional headline says “Service delays increased 100%.” Supplied data show two delayed jobs out of 100 last month and four out of 200 this month. No other records exist. Check the headline’s numerical context.
- Read your context and instructions
- Compiled the fact check pro
Exact claim: Service delays increased 100%. Ambiguity: Does it refer to delayed-job count or delay rate?
Count check: Delayed jobs rose from 2 to 4. Relative count increase = (4−2)/2 = 100%. This is supported by the supplied numbers.
Rate check: Prior rate = 2/100 = 2%; current rate = 4/200 = 2%. The delay rate did not increase in these supplied data. Total workload also doubled.
Verdict: Misleading if the headline implies deterioration in delay rate. Numerically accurate only as a count comparison, with a material denominator omission. No intent to mislead inferred.
Corrected context: “Delayed-job count doubled from two to four as total jobs doubled; the supplied delay rate remained 2%.”
Provenance: User-supplied fictional headline and figures only. Dates, definitions and underlying records are not independently verified.
Remaining checks: Confirm comparable delay definitions, periods and complete counts before publication; no causal or service-quality conclusion from these figures alone.
Execution: Manual claim analysis only. No live source search, external investigation or media inspection performed.
Connects securely to your tools. The creator never sees your data.
About this skill
Fact Check Pro helps researchers, editors and teams investigate claims from headlines, posts, advertisements, screenshots and supplied documents. It separates factual assertions from opinion, prediction, satire and inference, then traces origins and restores relevant context.
The skill audits dates, units, denominators, quotations, source independence and credible counter-evidence. It reconstructs timelines and prepares reasoned verdicts and corrected wording without equating repetition with corroboration or inferring intent. Media verification depends on actually available evidence and tools.
Works in ChatGPT and Claude with supplied material or legitimate research access. It does not invent sources, events or verification, amplify rumor as fact or claim current investigation without retrieval. Unresolved questions and source limits remain explicit.
Conclusions depend on accessible evidence and source quality. Cannot invent verification, infer intent or resolve unseen media details. Current claims require current evidence; missing support and uncertainty remain visible.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 1 month ago
Permissions
File Scopes
Optional authorized claim and evidence-source reading; write agreed fact-check reports. No publication or external investigation implied. Attribute allegations and preserve source/context distinctions, especially for identifiable people.