> ## 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.

# Evaluating outputs

> Benchmark Agent Skills outputs against published rubrics using LLM-as-judge or human review.

Once you've prompted your LLM to use an Agent Skill (e.g., [K-12 Lesson Planning](/agent-skills/skills/k12-lesson-planning)) and received an output (e.g., a lesson plan), you may want to evaluate the quality of this AI-generated output.

## Select rubrics

Find the rubric files that match the skill and/or subject addressed in your prompt.

| Skill                                                                          | Rubric files                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               |
| :----------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| [K-12 Lesson Planning](/agent-skills/skills/k12-lesson-planning)               | <ul><li>Common rubric: [`shared.csv`](https://github.com/learning-commons-org/agent-skills/blob/main/evals/k12-lesson-planning/rubrics/shared.csv?utm_source=docs\&utm_medium=agent-skills)</li><li>Subject-specific rubric<ul><li>[`math.csv`](https://github.com/learning-commons-org/agent-skills/blob/main/evals/k12-lesson-planning/rubrics/math.csv?utm_source=docs\&utm_medium=agent-skills)</li><li>[`ela.csv`](https://github.com/learning-commons-org/agent-skills/blob/main/evals/k12-lesson-planning/rubrics/ela.csv?utm_source=docs\&utm_medium=agent-skills)</li><li>[`science.csv`](https://github.com/learning-commons-org/agent-skills/blob/main/evals/k12-lesson-planning/rubrics/science.csv?utm_source=docs\&utm_medium=agent-skills)</li><li>[`social_studies.csv`](https://github.com/learning-commons-org/agent-skills/blob/main/evals/k12-lesson-planning/rubrics/social_studies.csv?utm_source=docs\&utm_medium=agent-skills)</li></ul></li></ul> |
| [K-12 Lesson Differentiation](/agent-skills/skills/k12-lesson-differentiation) | <ul><li>[`differentiation.csv`](https://github.com/learning-commons-org/agent-skills/blob/main/evals/k12-lesson-differentiation/rubrics/differentiation.csv?utm_source=docs\&utm_medium=agent-skills)</li><li>[`clarifying_question.csv`](https://github.com/learning-commons-org/agent-skills/blob/main/evals/k12-lesson-differentiation/rubrics/clarifying_question.csv?utm_source=docs\&utm_medium=agent-skills)</li></ul>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              |

## Evaluate output

Pass your output materials (e.g., the AI-generated lesson plan) and selected rubrics (e.g., `shared.csv` and `ela.csv` for an English Language Arts lesson plan) to your LLM with the prompt below:

```txt theme={null}
You are a rigorous educational content evaluator. Your job is to assess whether AI-generated lesson plan documents meet specific rubric criteria.

You will receive:
  1. The lesson-plan documents as attached files.
  2. The model's final chat response (the text it sent back to the user).
  3. A rubric with criteria to judge against.

Grading rules:
  - Judge criteria in the `M` (Model Scaffolding) bucket against the chat response. Judge all other criteria against the attached documents.
  - The content must actually be present in the documents, not merely claimed in the chat response.
  - Pass means the criterion is clearly and fully met. Fail means it is absent, incomplete, or only partially met.

Respond ONLY with a valid JSON array — no preamble, no markdown fences, no trailing text. Each element:
{
  "id": "...",
  "pass": true|false,
  "explanation": "one sentence"
}
```

Each rubric criterion will be scored independently as pass (`1`) or fail (`0`).