- Home
- Skills
- Agents & Orchestration
- Fact Check
Fact Check
Automated factual verification using tiered official sources to eliminate hallucinations and circular reasoning.
Free
Works with the AI Agents you already use
Fact Check
Example session with this skill installed
Fact check this AI-generated summary of the 2023 tech subsidy policy. It claims a 500 million grant was issued on March 15th.
- Read your context and instructions
- Compiled the fact check
Claim: 500 million grant issued on March 15.
Rating: ⚠️ Deviated
Evidence: Official filing [link] shows the grant was 450 million. The March 15 date refers to the media report date; the actual policy execution started on March 10.
Source: Ministry of Industry T0 Archive.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Manually verifying claims in news drafts, reports, or AI-generated content is slow and prone to oversight. Relying on search engine snippets often leads to circular reasoning where the source being checked is the one providing the verification.
What it does
- Extracts every factual claim including dates, amounts, and entities using a "verbatim capture" principle to ensure no detail is missed.
- Forces external cross-referencing against a tiered source hierarchy, prioritizing official government filings (T0) and authoritative media (T1).
- Detects sophisticated misinformation tactics like time-shifting (using old news as current), title-body mismatch, and AI hallucinations.
- Generates structured verification reports with deep-link evidence, categorizing claims as accurate, incorrect, biased, or unverifiable.
Frameworks & tools
Python 3, Cue API, and official financial/regulatory data sources like SSE, HKEX, and EDGAR.
Why this beats prompting it yourself
Standard LLM prompting often results in internal hallucinations or "lazy" verification that accepts surface-level search results. This skill implements a strict anti-circular-reasoning firewall and a forced deep-search protocol that bypasses homepages to find primary source documents.
Use cases
- Fact-checking PR drafts against historical financial reports and official corporate filings.
- Verifying AI-generated industry analysis to catch hallucinated statistics and fabricated market data.
- Vetting social media content for "zombie news" where old events are rebranded as breaking stories.
Known limitations
Does not verify subjective opinions, private data, or content behind paywalls. Not designed for real-time breaking news where official sources haven't yet commented.
Requires CUE_API_KEY. Does not verify subjective opinions or private data. Cannot bypass paywalls or provide official legal testimony.
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
This skill has been used 17 times.
Trust & safety
Security scan
Security scan passed 3 months ago
- Free with an Agensi account
Requires
Permissions
Allowed Hosts