Teaching and assessment

Free Rubric Generator.

Criteria with observable performance levels.

Build a rubric alongside the assignment and test its descriptors against examples of the work learners will produce.

Chrome extension + account required.
25 free automation tasks/month across tools. Browser-provider limits apply.

WHAT TO HAVE READY

Assignment and learning standards supplied by user.

YOUR STARTING POINT

A task you can make yours.

Copy it here. Paste it into WebAct when you are ready.

This page prepares your prompt. The task runs in WebAct.

01

Make the task yours.

Review the prompt above. Add your goal and any requirements that matter.

02

Bring it to WebAct.

Open WebAct, paste the task and provide your source material. Start in Chat for a draft or explanation; use Task when you want an approved browser action or file.

03

Check the useful part.

Use the result as an editable draft or analysis. Check it against the supplied facts and your intended audience before relying on it or sharing it.

A PRACTICAL GUIDE

How to use the Rubric Generator.

Rubric levels should describe observable differences in quality. Avoid circular labels such as excellent work without saying what makes it excellent.

Make the workflow fit your task.

Separate the assessment criteria and describe observable differences at each performance level. Use language a learner can apply to their work, checking that adjacent levels distinguish quality rather than merely changing adjectives.

What you provide
Assignment and learning standards supplied by user.
What you get
Criteria with observable performance levels.

See the input and the result.

Illustrative input and output · a teaching example, not a live WebAct run

Example input

Create a three-level rubric for a short scientific claim supported by supplied evidence. Criteria: claim accuracy, evidence relevance and reasoning.

Completed example

Claim accuracy: 1 = claim is unclear or conflicts with the supplied facts; 2 = accurate but scope is unclear; 3 = accurate and appropriately scoped.
Evidence relevance: 1 = absent or unrelated; 2 = relevant evidence is included; 3 = relevant evidence is selected and identified clearly.
Reasoning: 1 = evidence is listed without a connection; 2 = connection is partly explained; 3 = explains how the evidence supports the claim and notes a relevant limit.
Review the descriptors against an actual sample response before classroom use.
Download this example

Load this input into the prompt, then copy it to WebAct to try the task. Your result may differ from the illustration.

Decisions and troubleshooting.

Should rubric levels use excellent, good and poor without explanation?

Describe what is present or missing at each level. Labels alone do not tell learners or reviewers how to distinguish performance.

Why do two teachers score the same work differently?

Compare interpretations using a sample response and the criteria. Revise vague descriptors that permit incompatible readings.

Try it with your own source.

Replace the example with your material in the task prompt. Keep the requirements you need, then copy the task into WebAct.

Customize and copy the task ↑
BEFORE YOU BEGIN

Using WebAct.

The prompt and example are available here. Run your task in the WebAct Chrome extension.

Is this tool free?

You can copy and edit the prompt here for free. To use it with WebAct, install the Chrome extension, create and verify your account, and connect an available browser ChatGPT session. The Free plan includes 25 user-started automation tasks per calendar month, shared across tools. Ordinary browser Chat is separate; provider limits apply.

Learn about shared context in our privacy policy and choosing Chat or Task.

FROM A PROMPT TO YOUR OWN WORK

Bring the task to your page.

Install WebAct, add your source material and make the result yours.

Install WebAct