- Home
- Skills
- Technical Documentation
- AI E book Fact Checking & Source Verification Agent
Works with the AI Agents you already use
AI E book Fact Checking & Source Verification Agent
Audit e-book manuscripts for factual accuracy, verify sources, and validate citations with a structured report.
$24
AI E book Fact Checking & Source Verification Agent
Example session with this skill installed
Verify the factual claims in this paragraph: "The 2022 Census reported that 14.5% of the population lived in rural areas, a 2% increase from 2010. The Rural Act of 2018 governs these zones."
- Read your context and instructions
- Compiled the ai e book
I have extracted and verified the claims from the provided text against official census data and legislative records.
Claim Verification Register
| Claim ID | Location | Claim Summary | Status | Severity | Evidence / Source | Recommended Action |
|---|---|---|---|---|---|---|
| C-001 | Para 1 | 2022 Census: 14.5% rural population | Unsupported | High | US Census Bureau (2020/2022 estimates) indicates ~17.9-20%. | Verify if 14.5% refers to a specific sub-region or demographic. |
| C-002 | Para 1 | 2% increase from 2010 | Contradicted | Medium | Census trends show a relative decline or stagnation in rural share, not a 2% increase. | Review base years and denominator used for the calculation. |
| C-003 | Para 1 | Rural Act of 2018 governs these zones | Verified | Low | Public Law 115-334 (Agriculture Improvement Act of 2018). | No change needed; citation is stable. |
Numerical Audit
| Location | Original Figure | Recalculation / Evidence | Result | Action |
|---|---|---|---|---|
| Para 1 | 2% increase | Trend shows -0.6% shift | Inconsistent | Correct to reflect "relative change" vs "percentage point change". |
Author Query List
Query Q-001: The 14.5% figure does not align with national 2022 ACS 1-year estimates. Was this figure pulled from a specific state report or a non-governmental study?
Query Q-002: Please confirm if the "2% increase" refers to the total number of people or the percentage of the total population, as these represent different statistical realities.
Next steps
- Review the source for the 14.5% statistic to see if a specific geographic filter was applied.
- Update the text to clarify the Rural Act of 2018's specific title (Farm Bill).
- Cross-reference the demographic shift with the 2020 Decennial Census for higher precision.
Connects securely to your tools. The creator never sees your data.
About this skill
Publishing a manuscript with factual errors or broken citations damages credibility and risks legal liability. This skill systematically audits e-book manuscripts to identify, verify, and document the reliability of every checkable claim.
What it does
- Claim extraction identifies dates, statistics, quotes, and technical assertions for individual verification.
- Source verification traces claims to primary documents, peer-reviewed research, and official records.
- Citation auditing matches in-text citations to reference lists and validates DOI or URL stability.
- Numerical validation recalculates percentages, ratios, and totals to find arithmetic errors.
- Consistency checking flags contradictions between different chapters, tables, or external evidence.
- Risk assessment categorizes issues by severity to prioritize critical factual failures.
How it works
- Define the Brief by specifying the manuscript version, subject, and citation style requirements.
- Atomize Claims by breaking down paragraphs into a register of specific, checkable assertions.
- Research Evidence using high-authority sources like academic journals and government datasets.
- Generate Reports including a claim verification register with status labels and recommended wording.
Frameworks & tools
This skill focuses on editorial workflows and manuscript preparation. It relies on standard bibliographic formats, academic research databases, and official documentation repositories.
Why this beats prompting it yourself
Generic prompts often overlook subtle internal contradictions and fail to distinguish between "unsupported" and "false." This skill uses a structured 10-step workflow and a rigorous evidence-quality framework to ensure every conclusion is traceable and every high-stakes claim is flagged for human review.
Use cases
- Manuscript pre-flight to audit a final draft before it goes to layout or distribution.
- Academic reference checking to ensure all scholarly citations are complete and accurate.
- Technical content audit for software or medical guides where outdated facts pose a risk.
- Competitive research verification to validate statistics used in business or marketing e-books.
Known limitations
This skill cannot access private databases or bypass paywalls for restricted journals. It provides evidence assessment but is not a substitute for qualified legal, medical, or professional review.
Cannot bypass paywalls or access private databases. Does not provide professional legal or medical certifications. Scope is limited to accessible digital text and references.
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 10 days ago
Permissions
No special permissions declared or detected