Skip to content
TrustedSkillsbeta
Back to all skills

Image Evaluation

Checked
ppdbxdawj·vlatest·other·MIT

Evaluates images based on aesthetic quality, content relevance, and technical aspects according to provided criteria.

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 ppdbxdawj/ai-skills --skill image-evaluation -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

ppdbxdawj

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 ppdbxdawj/ai-skills at bef9a4686f.

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

Commit
bef9a4686f
Manifest
image-evaluation/SKILL.md
Scanned
6 files, 716 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 allows AI agents to evaluate images based on provided criteria. It can assess aspects like aesthetic quality, relevance to a prompt, or adherence to specific guidelines. The agent provides feedback and scores related to the image's characteristics.

When to use it

  • Content Moderation: Evaluate user-submitted images for appropriateness and policy compliance.
  • Image Generation Feedback: Provide constructive criticism on AI-generated images to improve future generations.
  • Stock Photo Selection: Help choose the best stock photos based on specific project requirements.
  • A/B Testing Visuals: Compare different image variations to determine which performs better with users.

Key capabilities

  • Image assessment based on user-defined criteria
  • Scoring of images against specified parameters
  • Feedback generation for image improvement
  • Evaluation of aesthetic quality

Example prompts

  • "Evaluate this image and score it from 1 to 5 on its relevance to the prompt 'sunset over a mountain range'."
  • "Assess this photo for adherence to our brand's visual guidelines. Provide specific feedback."
  • “Can you rate this image’s composition, color balance, and overall appeal?”

Tips & gotchas

The quality of evaluation depends heavily on clearly defined criteria provided in the prompt. Vague or ambiguous instructions will result in less helpful feedback.