Skip to content
TrustedSkillsbeta
Back to all skills

Evaluation Anchor Checker

Checked
willoscar·vlatest·other

This tool verifies if an "anchor" value in a dataset aligns with predefined criteria, ensuring data consistency and accuracy for evaluations.

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 willoscar/research-units-pipeline-skills --skill evaluation-anchor-checker -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

willoscar

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 willoscar/research-units-pipeline-skills at f53f82f8d7.

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

Commit
f53f82f8d7
Manifest
.codex/skills/evaluation-anchor-checker/SKILL.md
Scanned
4 files, 543 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 evaluation-anchor-checker skill assesses the quality of generated text by comparing it to a provided "anchor" or reference text. It identifies deviations and inconsistencies, helping ensure that AI outputs remain grounded in factual information and maintain desired stylistic elements. This skill is particularly useful for evaluating research unit pipelines where accuracy and consistency are paramount.

When to use it

  • Evaluating Summaries: Check if a generated summary accurately reflects the key points of an original document.
  • Assessing Translations: Verify that translated text preserves the meaning and tone of the source material.
  • Reviewing Creative Content: Ensure AI-generated stories or articles adhere to specific guidelines or character traits defined in an anchor example.
  • Validating Research Outputs: Confirm that research unit outputs align with established methodologies and findings.

Key capabilities

  • Anchor text comparison
  • Deviation identification
  • Inconsistency detection
  • Quality assessment

Example prompts

  • "Evaluate this summary against the provided anchor text: [summary] [anchor]"
  • "Check if this translation maintains the tone of the original document, using this as an anchor: [translation] [anchor]"
  • "Assess this creative writing piece for consistency with the style in this example: [creative writing] [example]"

Tips & gotchas

The quality of the "anchor" text is crucial; it should be a clear and accurate representation of the desired output. Without a well-defined anchor, the evaluation will lack context and be less meaningful.