Instrument scorer

A Claude skill that scores standard usability questionnaires like SUS correctly, compares them to the benchmark, and checks your questions still match the standard wording.

AnalysisOctober 12, 2026

Download the skill

Enter your details to download the skill file.

What it does

Standard usability questionnaires like SUS are easy to score wrongly, and if someone rewords a question the score can no longer be compared to the benchmark.

You give it the questionnaire responses. It tells you the correct score, how it compares to the published benchmark, any responses that look inconsistent, and whether your questions still match the standard wording. Use it whenever you run SUS, SEQ, UMUX-Lite or NASA-TLX.

What you get back

  • Correctly scored results for each respondent, and the study mean with its confidence interval.
  • The benchmark comparison and grade for the study mean.
  • Possible inconsistent responses flagged for review, not deleted.
  • A wording check against the standard version of each questionnaire.
  • Plain notes on what the sample size and any changes mean for comparison.

Install it in Claude, ChatGPT, Copilot or Gemini

The same skill file works in all four. Pick your tool for the steps.

Install in Claude

  1. 1

    Download the skill

    Fill in the short form to get the .skill file.

  2. 2

    Add it to Claude

    In the Claude app go to Settings → Capabilities → Skills and upload the file. In Claude Code, run the npx command shown after the form, or drop the folder into your project's skills folder.

  3. 3

    Just ask

    Ask in plain language. Claude picks up the skill on its own when the request matches.

How to use it

Once it's installed, ask in plain language. Your AI follows the skill's method when the request matches.

Example prompt 1
Score these SUS responses and tell me how we compare to the benchmark.
Example prompt 2
Check our questionnaire wording before we send it. Is it still the standard SUS?
Example prompt 3
We used the all-positive SUS. Score it correctly.

What it won't do

It won't give individual respondents a letter grade, because the grade curve describes study means. It won't drop responses it thinks are careless; it flags them for you. And a score on its own isn't a finding, so pair it with what participants said and did.

Questions

Which questionnaires does it score?

SUS, including the all-positive version and a SUS with one item dropped, UMUX-Lite, the Single Ease Question and NASA-TLX.

What file format does it need?

A CSV or JSON with one row per respondent and one column per item. It detects header rows and ignores participant ID columns, and matches NASA-TLX columns by name.

Can I change the wording of the questions?

You can, but the score may no longer compare to the published benchmark. The validate check tells you which items have changed so you can decide.

More skills

See all skills