AI USE CASES YOU CAN REUSE.English edition · Individuals, independents, small businesses
OpenAI

Eval plugin

plugin-eval

In brief

Help engineers evaluate a local skill or plugin, explain why it marked this way, show what needs to be fixed first, measure the use of real tokens, the reference startup scripts, or decide what needs to be done. Use when the user says things like "assess this skill", "give me an analysis of the skill of dev game", "why did he make this note this way", "what should I fix first", "measure the actual use of this skill", or "what should I 1925 next?".

What it does

  • Start here
  • Requests for duality to recognize
  • Related commands

Who it is for, and an example

People whose task corresponds: Help engineers evaluate a local skill or plugin, explain why it marked in this way, show what needs to be corrected first, measure the use of real tokens, the reference boot scripts, or decide this Income of theessional.

Example request: "Eval Plugin: Help engineers evaluate a local skill or plugin, explain why it marked this way, show what needs to be corrected first, measure"

Help engineers evaluate a local skill or plugin, explain why it marked this way, show what needs to be corrected first, measure the use of real tokens, the reference startup scripts, or decide what needs to be done. Example written by iadujour.fr from the SKILL.md, not tested.

Install

In Codex:

codex plugin add plugin-eval@openai-curated

Works with

  • Codex

Source: K0: Codex plugin collection; the deposit marketplace is called "Official Codex". Other agents are not appointed.

Level: Intermediate

Supposes a project already in place at the publisher and the tools described in the K0.

Good to know

Official deposit These are examples of Codex plugins, often written by the plugin editor and hosted here. Skill plugin " plugin-eval" in

SKILL.md excerpt

The original description, which the agent reads to decide whether to load the skill (in English):

Help engineers evaluate a local skill or plugin, explain why it scored that way, show what to fix first, measure real token usage, benchmark starter scenarios, or decide what to run next. Use when the user says things like "evaluate this sk […]

Quoted from SKILL.md at commit d420d13 . The folder also contains 1 extra file (agents/).

The SKILL.md has 81 lines and 5 main sections:

  • Start Here
  • Chat Requests To Recognize
  • Matching Commands
  • Output Expectations
  • References

Licence: No licence found

Checked on 13 November 2026 : .

pas de fichier LICENSE dans le dossier de la skill For the full text, see the source.

Source. Card written by iadujour.fr from: Frontmatter, sections and body of the deposit. Checked on 13 November 2026. openai/plugins .
SAME PUBLISHER

Other OpenAI skills: DevOps and deployment

Whole category
OpenAIDevOps and deployment

Completion of a Directorate-General for Development

finishing-a-development-branch

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work

Tools: CodexLevel: Intermediateupdated 06/11/2026
OpenAIDevOps and deployment

Improving skills

improve-skill

Turn the results of the plugin-eval into a concrete rewrite brief for Codex competence.

Tools: CodexLevel: Intermediateupdated 06/11/2026
OpenAIDevOps and deployment

CAD to SimReady

omniverse-cad-to-simready

Coordinate the workflow from end to end CAD/source-asset to SimReady.

Tools: CodexLevel: Intermediateupdated 06/11/2026
DISCUSSION

Comments.

A field note, a question, a precision on this skill? Comments are reviewed before publication.

Published comments

Loading comments…

    Leave a comment

    Moderation charter. Every comment is reviewed before publication. We refuse hate speech, insulting or discriminatory language, advertising, spam and promotional links, off-topic posts and other people’s personal data.