- Home
- Skills
- Agents & Orchestration
- Grandmas Wisdom
Works with the AI Agents you already use
Grandmas Wisdom
Verify academic citations and claims with a rigorous bullshit detection framework for AI agents.
$12
Grandmas Wisdom
Example session with this skill installed
Run Grandma’s Wisdom on: "Long-term effects of X on cognitive flexibility", JCS 2023. Claim: X causes lasting improvements in executive function across the general adult population.
- Read your context and instructions
- Compiled the grandmas wisdom
Bullshit Meter: 3/10 (Solid with Minor Caveats)
Analysis: Core claim reasonably supported by 2023 study data.
Tenable: Cognitive improvement in adults aged 18-45.
Not Tenable: Generalization to the "general population" (elderly groups not tested).
Action: Use with light qualification.
Connects securely to your tools. The creator never sees your data.
About this skill
What it does
Grandma’s Wisdom is a high-precision authentication framework designed to verify academic citations and claims. It moves beyond simple cross-references by evaluating the evidential substance, logical consistency, and longitudinal validity of a scholarly source. It acts as a rigorous filter that prevents your AI agent from hallucinating or propagating academic "bullshit."
Problem solved
AI agents often struggle with "hallucinated" citations or taking low-quality academic claims at face value based on institutional prestige. This skill provides a systematic way to verify if a citation actually supports the claim being made, calculating a definitive "Bullshit Meter" score to guide your agent's reasoning process.
How it works
The skill uses a multi-pass helical process to analyze inputs. It delivers:
- A 1-10 Bullshit Meter score with actionable interpretation.
- A structured breakdown of evidential support and overclaim risks.
- Clear "Tenable" vs "Not Tenable" statements.
- Longitudinal reevaluation as new literature is discovered.
Why it's better than standard prompting
Unlike raw prompting, this skill integrates specialized logic like the Spiral Reasoning Tree and Veritas Aegis safeguards. It doesn't just ask "is this true?"; it maps conceptual connections and evaluates the gap between what a source supports and what is being inferred, ensuring your agent produces only grounded, defensible academic work.
- Effectiveness depends on the quality of available literature in the connected network.
- Not a replacement for primary peer review in niche, emerging fields.
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 15 times.
Trust & safety
Security scan
Security scan passed 2 months ago