> ## Documentation Index
> Fetch the complete documentation index at: https://docs.learningcommons.org/llms.txt
> Use this file to discover all available pages before exploring further.
# Introduction
> Overview of Durable Skills evaluators that rate student work against a construct's indicators, with evidence and rationale for every judgment.
export const EarlyAccessBadge = ({size = "md", children}) => {
return
{children == null || children === "" ? "Early access" : children}
;
};
## The problem
Constructs like critical thinking, argumentation, or reasoning are core to what schools want students to develop, and they shape rubrics, feedback, and instruction.
But rating student work against a construct like this is harder than it looks:
* **Construct is rarely a single skill**
* Most constructs bundle several indicators (e.g., synthesizing sources, addressing counterarguments, drawing conclusions) that don't always move together
* Essay can be strong on one indicator and weak on another – a single holistic score hides that
* **Construct isn't the same as writing quality**
* Fluent, well-organized writing can be thin on reasoning, while rough writing can also carry real reasoning
* Rating must isolate the construct itself, not assess general essay quality
* **Even human experts don't always agree**
* Reliable rating takes calibration: shared rubrics, normalizing sessions, and consensus across raters
* Some indicators remain difficult to rate consistently, even after calibration – that ceiling must be reported, not hidden
Asking human experts to rate every student's work against every indicator, across a full class or cohort, does not scale.
## What we're building
Our Durable Skills evaluators rate student work against a construct's indicators, using a rubric developed and calibrated with subject-matter experts.
| Output | Description |
| :--------------------------------------------- | :------------------------------------------------------------------------------------------------------------ |
| **Fine-grained, indicator-level ratings** | Replaces a single holistic score with a rating for each named skill the construct bundles together |
| **Evidence and rationale for every judgment** | Verbatim quotes and reasoning behind each rating, so a teacher or researcher can check *why*, not just *what* |
| **Reported against a human agreement ceiling** | Human inter-rater agreement is measured and reported alongside model results, so claims are scoped honestly |
Our evaluators judge whether student work demonstrates a construct at the indicator level:
| Evaluator | Description |
| :------------------------------------------------------------------------------------------------------------------- | :-------------------------------------------------------------------------------------------------- |
| [**Critical Thinking**](/evaluators/durable-skills-evaluators/critical-thinking)
| Rates a student's source-based argumentative essay for critical thinking across 5 rubric indicators |
## Related topics
Run an evaluator in the Evaluators playground, a Python notebook, or with
the SDK.
Rate a student essay for critical thinking, with evidence quotes and
rationale for every indicator.