Model Detection
Identifies underlying language models powering text generation, providing insights into source and potential biases.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add model-detection npx -- -y @trustedskills/model-detection
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"model-detection": {
"command": "npx",
"args": [
"-y",
"@trustedskills/model-detection"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
The model-detection skill allows an AI agent to identify the underlying language model powering a given text or response. It can determine if a piece of text was generated by GPT-3, Claude, Gemini, or other models. This capability is useful for understanding biases and limitations inherent in different models.
When to use it
- Bias Analysis: Determine if a generated response might be influenced by the training data of a specific model.
- Source Attribution: Identify which language model was used to create a particular piece of content.
- Model Comparison: Evaluate the characteristics and strengths/weaknesses of different models based on their output.
- Content Verification: Assess the authenticity or origin of text by identifying its likely generative source.
Key capabilities
- Language Model Identification
- Text Analysis
- Response Attribution
Example prompts
- "Can you tell me what model generated this text: '[insert text here]'"
- "Analyze this response and identify the language model used to create it."
- "Determine if this content was likely produced by GPT-3 or Claude."
Tips & gotchas
The accuracy of model detection can vary depending on the complexity and length of the input text. It's best suited for analyzing relatively short, self-contained responses rather than large documents.
Tags
TrustedSkills Verification
Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.
Security Audits
| Gen Agent Trust Hub | Pass |
| Socket | Pass |
| Snyk | Pass |
🌐 Community
Passed automated security scans.