Skip to content
TrustedSkillsbeta
Back to all skills

Model Equivariance Auditor

Checked
lyndonkl·vlatest·other

Verifies if an AI model's outputs consistently transform as expected under specified input transformations (e.g., rotations, translations).

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 lyndonkl/claude --skill model-equivariance-auditor -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

lyndonkl

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 lyndonkl/claude at 4acc337d4d.

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

Commit
4acc337d4d
Manifest
skills/model-equivariance-auditor/SKILL.md
Scanned
5 files, 1,367 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

The model-equivariance-auditor skill assesses AI models for equivariance, a property where transformations applied to input data are reflected in corresponding transformations of the output. This helps ensure consistent and predictable behavior across different perspectives or coordinate systems. It can identify potential biases or vulnerabilities arising from lack of equivariance, improving model robustness and fairness. The auditor provides detailed reports highlighting areas needing attention.

When to use it

  • Evaluating self-driving car models: Verify that changes in camera position consistently affect the perceived environment.
  • Analyzing medical imaging AI: Ensure rotations or translations of scans don’t lead to incorrect diagnoses.
  • Testing robotics perception systems: Confirm object recognition remains consistent under varying lighting conditions or viewpoints.
  • Auditing generative models: Check that transformations applied to prompts are reflected in the generated output, ensuring predictable creative results.

Key capabilities

  • Equivariance assessment for AI models
  • Detailed reporting of equivariance violations
  • Identification of potential biases and vulnerabilities
  • Analysis across various coordinate systems/perspectives

Example prompts

  • "Audit this image classification model for rotational equivariance."
  • "Generate a report detailing the translational invariance of this object detection system."
  • "Assess the equivariance properties of this generative art model under prompt transformations."

Tips & gotchas

The skill's effectiveness depends on having access to the underlying AI model and its training data. Understanding the specific types of transformations relevant to your application is crucial for interpreting the auditor’s results effectively.