Prompt: Build a Marking Rubric

Creates a marking rubric with four performance levels and named criteria, so grading a set of student work stays consistent from first to last.

The prompt

Open in Studio

You are a teacher who writes marking rubrics that keep grading consistent across a whole class set.

Objective: Create a marking rubric for {{ASSIGNMENT — e.g. a persuasive essay}} for {{YEAR GROUP — e.g. Year 9}}.

Context: The assignment asks students to {{TASK DESCRIPTION — e.g. argue for or against a school uniform policy}}. It is marked out of {{TOTAL MARKS — e.g. 20}}.

Constraints:
- Use exactly four performance levels, in this order: Emerging, Developing, Secure, Mastery
- Score exactly three criteria, and only these three: {{CRITERION 1 — e.g. argument structure}}, {{CRITERION 2 — e.g. use of evidence}}, {{CRITERION 3 — e.g. clarity of writing}}
- Each criterion's four level descriptions must be written as observable, specific behaviour, not vague judgements like "good" or "excellent" on their own
- Do not invent a grade boundary, percentage or exam-board grade descriptor; describe only what the student does at each level

Example: instead of "good use of evidence", write "supports every claim with at least one relevant piece of evidence, correctly referenced".

Output format: Return a Markdown table with rows for each of the three criteria and columns for the four levels, followed by one line stating how the total mark of {{TOTAL MARKS — e.g. 20}} is split across the three criteria.

Before finishing, check that every cell describes an observable behaviour rather than a bare adjective, and that the mark split adds up to {{TOTAL MARKS — e.g. 20}}.

Example

Input

ASSIGNMENT — e.g. a persuasive essay: a persuasive essay
YEAR GROUP — e.g. Year 9: Year 9
TASK DESCRIPTION — e.g. argue for or against a school uniform policy: argue for or against a school uniform policy
TOTAL MARKS — e.g. 20: 20
CRITERION 1 — e.g. argument structure: argument structure
CRITERION 2 — e.g. use of evidence: use of evidence
CRITERION 3 — e.g. clarity of writing: clarity of writing

Output

| Criterion | Emerging | Developing | Secure | Mastery |
|---|---|---|---|---|
| Argument structure | States an opinion with no supporting reasons | Gives reasons but in no clear order | Presents reasons in a logical order with a clear introduction and conclusion | Builds a logical case that also anticipates and answers the opposing view |
| Use of evidence | Makes claims with no supporting evidence | Includes evidence but does not link it back to the claim | Supports every claim with at least one relevant piece of evidence | Uses varied, well-chosen evidence and explains why each piece matters |
| Clarity of writing | Sentences are hard to follow; frequent errors obscure meaning | Meaning is mostly clear but errors sometimes interrupt reading | Writing is clear throughout with only occasional minor errors | Writing is clear, varied in sentence structure, and free of distracting errors |

Mark split: 8 marks for argument structure, 8 marks for use of evidence, 4 marks for clarity of writing, totalling 20 marks.

Why it works

Fixing four named levels and exactly three criteria stops a rubric from sprawling into an unusable grid of vague, overlapping bands.
Requiring observable behaviour instead of adjectives like 'good' removes the ambiguity that causes two markers to disagree on the same script.
The pre-finish check re-verifies both the behavioural wording and the mark total, catching a split that doesn't add up before it's used.

Why the basic version fails

“Write a rubric for a persuasive essay” typically returns bands described only with adjectives — “good”, “excellent”, “needs improvement” — which sound fine but give two different teachers marking the same set of essays no shared basis for agreeing a grade.

What this prompt fixes

Fixing the level names and criterion count keeps the rubric to a size that’s actually usable while marking thirty scripts in one sitting. Requiring each cell to describe an observable behaviour, rather than a bare adjective, is what makes a rubric produce consistent marks across different markers or across a re-mark. The mark-split check catches an allocation that silently doesn’t add up to the stated total.

Tips per model

ChatGPT sometimes reuses the same adjective across two levels with only the intensity changed; check each cell describes a genuinely different behaviour.
Claude tends to write more concretely observable descriptors by default, which is useful if you plan to share the rubric with students as success criteria.
If your school uses an official grade-descriptor bank, paste a sample descriptor into the context so the tone and phrasing style matches what students already see.