grill

Generate probing questions to stress-test answers across six evaluation angles.

6|1|Updated Jun 23, 2026

Search Tags:#cross-examination #LLM tooling #information reliability #adversarial questioning #answer analysis

Ready to run

npx skills add https://github.com/JGalego/Bag-of-Tricks --skill grill-jgalego

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: grill
Source: https://github.com/JGalego/Bag-of-Tricks/tree/main/grill
Command: npx skills add https://github.com/JGalego/Bag-of-Tricks --skill grill-jgalego

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires anthropic, openai, google-genai, and includes scripts (resource) components.

What problem does it solve?

This Skill scrutinizes answers for hidden assumptions, potential errors, and lack of support, helping you ensure the reliability and accuracy of information.

Core Features & Use Cases

Adversarial Interrogation: Generates probing questions that challenge an answer's weak points.
Cross-Examination: Evaluates answers across six angles: assumptions, edge cases, contradictions, sources, overconfidence, and falsifiability.
Model Analysis: Optionally run the questions against a model to see how well the answer holds up under scrutiny.
Use Case: Use grill to analyze an answer to a technical question or a business decision, identifying potential weaknesses and ensuring the answer is well-supported.

Quick Start

Analyze an answer with grill. Run the command 'python3 grill.py answer.txt'.

Frequently Asked Questions about grill

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I stress-test LLM outputs for hidden assumptions and unsupported claims?▼

To stress-test LLM outputs for hidden assumptions, you can use an adversarial questioning framework to interrogate answers across six angles: assumptions, edge cases, contradictions, sources, overconfidence, and falsifiability. This process identifies unsupported claims and potential errors.

What is the best way to cross-examine a draft answer to ensure information reliability?▼

Cross-examining a draft answer for information reliability involves generating probing questions that challenge weak points and evaluating the response under scrutiny. This ensures the answer is well-supported and highlights areas of overconfidence or lack of falsifiability.

Can I use this adversarial questioning framework with Anthropic, OpenAI, and Google generative AI models?▼

Yes, you can use this adversarial questioning framework with Anthropic, OpenAI, and Google generative AI models. The tool requires a compatible LLM provider and SDK to optionally run the generated questions against a model for analysis.

How do I analyze an answer file for potential contradictions and edge cases from the command line?▼

To analyze an answer file for contradictions and edge cases from the command line, run the Python script with your text file as an argument. The command 'python3 grill.py answer.txt' initiates the cross-examination process on the provided text.

When do I need to apply falsifiability checks to technical or business decision answers?▼

You need to apply falsifiability checks to technical or business decision answers when information reliability is critical. This scrutiny identifies hidden assumptions, potential errors, and lack of support, ensuring your decisions are well-supported and robust against adversarial interrogation.