Skip to content
TrustedSkillsbeta
Back to all skills

Pseo Llm Visibility

Checked
lisbeth718·vlatest·ai-ml·MIT

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

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add lisbeth718/pseo-skills --skill pseo-llm-visibility -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

lisbeth718

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.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Makes no network calls.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned lisbeth718/pseo-skills at e434f4afb7.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
e434f4afb7
Manifest
skills/pseo-llm-visibility/SKILL.md
Scanned
2 files, 333 lines
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

This skill provides visibility into the internal workings of Large Language Models (LLMs). It allows users to inspect intermediate states, track token probabilities, and understand how an LLM arrives at a given output. This is useful for debugging complex prompts or understanding model behavior in detail.

When to use it

  • Debugging Complex Prompts: When an LLM produces unexpected results with intricate prompts, this skill can help pinpoint the source of the issue.
  • Understanding Model Reasoning: Gain insight into why a model made a specific decision by observing its internal thought process.
  • Educational Purposes: Demonstrate how LLMs function to students or colleagues learning about AI and natural language processing.
  • Model Evaluation: Assess the reliability and transparency of an LLM's responses by examining intermediate steps.

Key capabilities

  • Inspect token probabilities at each step of generation.
  • View internal states during LLM operation.
  • Track the evolution of the model’s understanding.

Example prompts

  • "Show me the token probabilities for the first 5 tokens when generating 'The quick brown fox.'"
  • "Trace the internal state as you answer: What is the capital of France?"
  • "Explain your reasoning step-by-step, showing intermediate states."

Tips & gotchas

This skill requires a foundational understanding of LLM architecture and tokenization. The output can be verbose; consider limiting the scope (e.g., number of tokens) to avoid overwhelming results.