Skip to content
TrustedSkillsbeta
Back to all skills

Feature Audit

Checked
srstomp·vlatest·other·MIT

Analyzes data features to identify potential biases, errors, or areas needing refinement for improved model performance.

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 srstomp/pokayokay --skill feature-audit -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

srstomp

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 srstomp/pokayokay at ef6a34d63b.

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

Commit
ef6a34d63b
Manifest
plugins/pokayokay/skills/feature-audit/SKILL.md
Scanned
7 files, 2,018 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 feature-audit skill allows an AI agent to analyze a set of features and provide feedback on their completeness, consistency, and potential gaps. It can assess feature descriptions, identify missing attributes, and suggest improvements based on best practices for feature engineering. This helps ensure that features are well-defined and contribute effectively to the overall model performance.

When to use it

  • Feature Engineering Review: Before training a machine learning model, use this skill to review newly engineered features for clarity and completeness.
  • Model Debugging: If a model is underperforming, leverage feature-audit to identify potential issues with the feature set itself.
  • Knowledge Transfer: When onboarding new team members or documenting existing projects, utilize this skill to ensure everyone understands the purpose and characteristics of each feature.
  • Feature Store Validation: Validate features added to a centralized feature store for quality and consistency across different models.

Key capabilities

  • Feature completeness assessment
  • Consistency checking between features
  • Identification of missing attributes
  • Suggestion of improvements based on best practices

Example prompts

  • "Analyze these feature descriptions: [list of feature descriptions] and tell me if there are any gaps."
  • "Review the 'customer_age' and 'product_price' features. Are their definitions consistent?"
  • "I have a new feature called 'purchase_frequency'. Can you suggest attributes I should include in its description?"

Tips & gotchas

The quality of the audit depends heavily on the clarity and detail provided in the initial feature descriptions. Ensure that the input data is well-structured for optimal results.