Education & Curriculum5.0 · 0 ratings

Rubric And Exemplar Co-Designer

Produces an analytic rubric with calibrated performance descriptors plus annotated exemplars at each level.

Role-BasedFew-ShotStructured-Output

Prompt

ROLE: You are an assessment designer who writes analytic rubrics teachers can score consistently and students can self-assess against.

CONTEXT: Assignment: [ASSIGNMENT]. Grade level: [GRADE]. Subject: [SUBJECT]. Learning targets being assessed: [TARGETS]. Point scale or levels: [SCALE].

TASK: Design the rubric and exemplars.
1. Identify 3-5 criteria that directly measure the [TARGETS] — no criterion for things you don't actually want to grade (e.g., neatness if irrelevant).
2. For each criterion, write performance-level descriptors across the [SCALE] using observable, distinguishable language (avoid 'good/better/best' — describe the difference).
3. Ensure adjacent levels differ by a clear, single dimension so scoring is defensible.
4. Write a SHORT annotated exemplar snippet at the top level and at a mid level, with margin notes saying why it scored there.
5. Add a student-facing 'before you submit' self-check derived from the rubric.

OUTPUT FORMAT: (1) Rubric table (Criteria x Levels); (2) two annotated exemplar snippets; (3) student self-check list.

CONSTRAINTS: Descriptors must be parallel in structure across levels. Every criterion must trace to a stated target. Avoid vague qualifiers ('somewhat', 'mostly') without an anchor. Keep it to one page.

How to use this prompt

  1. 1

    Copy the prompt above and paste it into ChatGPT, Claude, or Gemini — or open it in the visual Studio to edit each part on a canvas and run it with your own key.

  2. 2

    Replace any bracketed placeholders with your specifics. The more concrete your context and constraints, the sharper the result — see the 5-part prompt structure.

  3. 3

    Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.

Techniques in this prompt

Role-Based

Assigns the model an expert persona so it adopts the right vocabulary, depth, and standards for the task.

Learn this technique
Few-Shot

Includes worked examples so the model matches your format and quality by pattern, not description.

Learn this technique
Structured Output

Pins the response to a defined structure so it drops straight into your workflow.

Learn this technique

Recommended models

claudegpt-4ogemini

Build on this prompt

Open it in the visual Studio to wire it into a full workflow with your own API key — or learn the craft behind prompts like this.

More in Education & Curriculum