agentsclimarketplace

Prompt to eval rubric

Skill alexzhu0/agent-ready-skills/skills/prompt-to-eval-rubric

Ten practical AI-agent skills for turning messy work into clear context, evals, reviews, and launch-ready artifacts.

Install
npx -y skills add alexzhu0/agent-ready-skills --skill prompt-to-eval-rubric

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Use when converting prompts, system instructions, assistant behaviors, or policy requirements into eval rubrics with scoring criteria, test cases, assertions, and failure modes.

SKILL.md

1.5 KB, as published. Nobody here has run it

Prompt To Eval Rubric

Purpose

Turn desired model behavior into a reusable evaluation rubric.

Fit

  • Use when prompt behavior must be evaluated repeatedly or compared across model/prompt versions.
  • Do not use when the task is only rewriting the prompt and no evaluation criteria are needed.

Inputs

  • Prompt, system instruction, policy, desired behavior, or bad output.
  • User goals, safety requirements, and known failure modes if available.
  • Preferred scoring scale if provided.

Workflow

  1. Extract expected behaviors and forbidden behaviors.
  2. Convert each behavior into a measurable criterion.
  3. Tie each criterion to prompt evidence, policy evidence, or a clearly labeled assumption.
  4. Add representative test cases, including edge cases.
  5. Define pass/fail assertions and scoring guidance.
  6. Preserve uncertainty where behavior is underspecified.

Output

Produce Markdown with:

  • Eval Goal
  • Rubric Table
  • Test Cases
  • Assertions
  • Failure Modes
  • Scoring Notes
  • Missing Requirements

Validation

  • Criteria are observable in outputs.
  • Assertions can be judged consistently.
  • Safety and correctness are not traded away for style.
  • Ambiguous prompt requirements become missing requirements.
  • Test cases include at least one likely failure case.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.