Skip to content
TrustedSkillsbeta
Back to all skills

Llm Debugger

Listed
monkey1sai·vlatest·ai-ml

Provides LLMs guidance and assistance for building AI and machine learning applications.

Repository

Install on your platform

This skill no longer installs under the name llm-debugger. monkey1sai/openai-cli is deleted or private, so it cannot be installed from.

We check each listing against its upstream repository with the rules the skills CLI uses, last on 2026-10-22. We don't show a command we know will fail.

Repository install instructions

What we know about this skill

Publisher

monkey1sai

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

Nobody has reviewed this code. TrustedSkills indexes and links skills; it does not audit, run or scan them. A skill runs with whatever access you give your agent — read the source before you install it.

Automated safety checks

scanned

We could not read this skill's source, so none of the checks below were run.

Not scanned. repository not found or private Source recorded as monkey1sai/openai-cli.
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

The llm-debugger skill provides tools to inspect and understand the internal workings of Large Language Models (LLMs). It allows you to view intermediate states, trace token probabilities, and analyze the decision-making process within an LLM. This helps in diagnosing issues, improving prompt engineering, and gaining insights into model behavior.

When to use it

  • Debugging unexpected outputs: When an LLM produces incorrect or undesirable results, use this skill to examine its internal state and identify potential causes.
  • Prompt optimization: Understand how different prompts influence the LLM's token selection process for more effective prompt design.
  • Model behavior analysis: Gain a deeper understanding of how an LLM arrives at its conclusions by observing its intermediate steps.
  • Educational purposes: Learn about the inner workings of LLMs and how they generate text.

Key capabilities

  • Token probability tracing
  • Intermediate state inspection
  • Decision-making process analysis
  • Debugging tools for LLMs

Example prompts

  • "Debug this prompt: [prompt text]"
  • "Show me the token probabilities for the last 5 tokens generated."
  • "Analyze the decision-making process when generating the response to 'Write a short story about a cat.'"

Tips & gotchas

The skill requires familiarity with LLM concepts like tokens and probability distributions. Results can be verbose, so focus on specific areas of interest for efficient debugging.