Skip to content
TrustedSkillsbeta
Back to all skills

Eval Session Scorecard

Checked
whitespectre·vlatest·ai-ml

This skill generates a detailed scorecard evaluating AI session performance based on key metrics, optimizing for better results and insights.

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 whitespectre/ai-assistant-evals --skill eval-session-scorecard -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

whitespectre

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 whitespectre/ai-assistant-evals at 8d48470982.

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

Commit
8d48470982
Manifest
skills/eval-session-scorecard/SKILL.md
Scanned
2 files, 91 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 generates a scorecard to evaluate AI assistant sessions. It provides structured feedback based on predefined criteria, allowing for consistent and objective assessment of performance. The resulting scorecard can be used to identify strengths and weaknesses in agent behavior and guide improvement efforts.

When to use it

  • Evaluating chatbot responses: Assess the quality and relevance of a chatbot's answers across various user queries.
  • Analyzing code generation tasks: Score an AI assistant’s ability to generate correct, efficient, and well-documented code.
  • Reviewing creative writing outputs: Evaluate the creativity, coherence, and overall quality of stories or other written content produced by an AI agent.
  • Tracking progress over time: Use scorecards repeatedly to measure improvements in agent performance after training or adjustments.

Key capabilities

  • Scorecard generation based on predefined criteria.
  • Structured feedback format for consistent evaluation.
  • Objective assessment of AI assistant performance.

Example prompts

  • "Generate a scorecard for this conversation with the AI assistant: [conversation transcript]"
  • "Create a scorecard evaluating the code generated by the agent, focusing on efficiency and readability."
  • "Score this story written by the AI assistant using these criteria: [list of criteria]."

Tips & gotchas

The quality of the scorecard depends heavily on the clarity and specificity of the evaluation criteria. Providing detailed instructions or a rubric will improve the accuracy and usefulness of the generated scorecard.