Skip to content
TrustedSkillsbeta
Back to all skills

Completion Evaluator

Checked
masanao-ohba·vlatest·ai-ml

This tool assesses generated text completions for quality and relevance, streamlining workflows by automatically identifying strong 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 masanao-ohba/claude-manifests --skill completion-evaluator -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

masanao-ohba

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 masanao-ohba/claude-manifests at 3e765ad5ee.

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

Commit
3e765ad5ee
Manifest
skills/generic/completion-evaluator/SKILL.md
Scanned
1 file, 306 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 completion-evaluator skill assesses the quality of text completions generated by AI models. It provides evaluations based on criteria such as relevance, coherence, and factual accuracy. This allows for iterative improvement of prompts and fine-tuning of language model behavior.

When to use it

  • Prompt refinement: Evaluate different prompt variations to identify which produces the best results from a language model.
  • Model comparison: Compare the output quality of multiple AI models given the same task.
  • Content generation review: Automatically assess generated content for accuracy and relevance before publication or further use.
  • Iterative development: Track improvements in completion quality as you adjust prompts or fine-tune a model.

Key capabilities

  • Evaluates text completions based on multiple criteria.
  • Provides scores reflecting the quality of each completion.
  • Supports comparison of different completions.

Example prompts

  • "Evaluate the following completion: [completion text]"
  • "Compare these two completions and tell me which is better: [completion 1] | [completion 2]"
  • "Assess this generated paragraph for factual accuracy: [paragraph text]"

Tips & gotchas

The effectiveness of the evaluation depends on clearly defining the desired qualities in your prompts. Consider providing specific examples or guidelines to guide the evaluation process.