Skill

Draft scale and anchor descriptions for a dimension

For one scoring dimension, drafts the scale and the anchor description at each level — concrete evidence or behaviour that earns each score — written for inter-rater convergence.

In / outSingle scoring dimension + scale type → anchor description for each scale level with concrete evidence criteria

You might say…

Vague anchors meant every analyst scored the same subject differently and none of us knew it — concrete anchors made disagreement visible and fixable.

What it does

For one scoring dimension, drafts the chosen scale and the anchor description at each level — the concrete evidence or behaviour that earns each score — written so two analysts scoring independently converge. Used once dimensions are defined and a scale type is chosen. One dimension per invocation, human-reviewed.

Trigger: Use per dimension after the dimension set is locked and a scale type is chosen.

Recognise the problem?

The primitives are the commodity part. The fastest next step is a conversation about composing them into something that works for you.

Start a conversation