Skip to content
TrustedSkillsbeta
Back to all skills

Eval Boundary Adherence

Checked
whitespectre·vlatest·ai-ml

Evaluates if a language model’s responses stay within defined boundaries, ensuring safety and relevance for reliable outputs.

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-boundary-adherence -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-boundary-adherence/SKILL.md
Scanned
2 files, 62 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, eval-boundary-adherence, evaluates an AI agent's ability to respect specified boundaries and constraints. It assesses whether the agent stays within defined limits regarding topic, tone, or output format. The evaluation focuses on adherence to these pre-set rules rather than the quality of content itself.

When to use it

  • Testing Agent Safety: Ensure an AI assistant doesn't generate harmful or inappropriate responses by setting boundaries around sensitive topics.
  • Enforcing Output Format: Verify that a chatbot consistently delivers information in a specific format (e.g., bullet points, JSON).
  • Topic Restriction: Confirm the agent remains focused on a particular subject area and avoids irrelevant tangents.
  • Tone Consistency: Evaluate if an AI maintains a desired tone (e.g., professional, friendly) across interactions.

Key capabilities

  • Boundary Adherence Evaluation
  • Constraint Respect Assessment
  • Topic Limit Enforcement
  • Output Format Validation

Example prompts

  • "Evaluate this conversation for adherence to the boundary: 'Do not discuss political topics.'"
  • "Assess if the agent's response follows the constraint: 'Respond in JSON format with keys 'summary' and 'keywords'."
  • "Check if the AI stayed within the topic of 'historical fashion' during this interaction."

Tips & gotchas

This skill evaluates adherence, not quality. A perfectly compliant but unhelpful answer will still receive a high score. Clear, specific boundary definitions are crucial for accurate evaluation.