> ## 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.

# K-12 Lesson Differentiation

> The K-12 Lesson Differentiation skill tiers an existing lesson for below, at, and above grade level, with rubrics.

[Skill last updated Jul 14, 2026](https://github.com/learning-commons-org/agent-skills/tree/main/skills/k12-lesson-differentiation)

> [!NOTE]
>
> The K-12 Lesson Differentiation Agent Skill was co-developed with
> [Anthropic](https://www.anthropic.com/) ↗.

## Overview

The [K-12 Lesson Differentiation](https://github.com/learning-commons-org/agent-skills/tree/main/skills/k12-lesson-differentiation) ↗ skill uses research-based differentiation principles (Tomlinson framework + subject-specific access design) to adapt an existing lesson for students at different proficiency levels (below/at/above grade level).

In Turn 1, the agent produces the following artifacts from one master JSON as native documents if they're supported; otherwise, it produces `.docx` files:

* **1 teacher-facing differentiation plan**
* **3 student-ready tier documents**

The skill considers:

* Source lesson identification from conversation history, uploads, or URLs
* Subject-specific differentiation rules and document templates
* Curriculum alignment when a curriculum is named or implied (e.g., IM® v.360)
* Grounding in state-specific standards when jurisdiction signals are present
* Grade-level demand across all tiers

> [!NOTE]
>
> This skill works with or without Knowledge Graph, but we strongly recommend
> connecting to it. See [Quickstart: Connect Knowledge
> Graph](https://docs.learningcommons.org/agent-skills/getting-started/quickstart.md#connect-knowledge-graph) for
> more information.

## At a glance

| | |
| :- | :- |
| **Workflow** | Differentiate an existing lesson into below/at/above proficiency tiers |
| **Subjects** | Math, ELA, Science, Social Studies |
| **Supported grades** | K–12 |
| **Rubrics** | <ul><li>[`differentiation.csv`](https://github.com/learning-commons-org/agent-skills/blob/main/evals/k12-lesson-differentiation/rubrics/differentiation.csv) ↗ — Tiered differentiation criteria: below/at/above proficiency design, preserved core content, and grade-level demand across tiers</li><li>[`clarifying_question.csv`](https://github.com/learning-commons-org/agent-skills/blob/main/evals/k12-lesson-differentiation/rubrics/clarifying_question.csv) ↗ — Scorer for model clarification behavior before generating tiered materials</li></ul> |

## Getting started

Follow the [Quickstart](https://docs.learningcommons.org/agent-skills/getting-started/quickstart.md) to start using this skill:

| Access method | |
| :- | :- |
| **Knowledge Graph MCP** | [Quickstart: Connect Knowledge Graph](https://docs.learningcommons.org/agent-skills/getting-started/quickstart.md#connect-knowledge-graph) |
| **Example prompts** | [example-prompts.md](https://github.com/learning-commons-org/agent-skills/blob/main/skills/example-prompts.md#lesson-differentiation) ↗ |
| **Skill instructions** | [`SKILL.md`](https://github.com/learning-commons-org/agent-skills/blob/main/skills/k12-lesson-differentiation/SKILL.md) ↗ |

## Triggers

Your LLM will programmatically load this skill when explicitly or implicitly prompted to differentiate, tier, or scaffold an existing K-12 lesson:

* **Explicitly**: "differentiate this lesson," "tier for below/at/above," "scaffold for struggling and advanced students"
* **Implicitly**: "my students are at different levels," "I have struggling and advanced students"

## Output

| Artifact | Description |
| :- | :- |
| **Teacher-facing differentiation plan** | Plan explaining tier design, preserved core content, and scaffolding choices |
| **Below-level student materials** | Tier with scaffolding that preserves grade-level standard demand |
| **At-level student materials** | On-grade tier aligned to the source lesson |
| **Above-level student materials** | Extension tier with increased depth or complexity |
| **Rendered files** | Native documents OR `.docx` files, based on agent support |

## Scoring

1. Generate differentiated materials using this skill.
2. Apply `differentiation.csv` to the tiered artifacts and `clarifying_question.csv` to evaluate the model's pre-generation clarification behavior.
3. Run LLM-as-judge or human review against each criterion. See [Evaluating outputs](https://docs.learningcommons.org/agent-skills/using-agent-skills/evaluating-outputs.md).

## Skill release history

| Date | Changed |
| - | - |
| Jul 14, 2026 | First release, co-developed with Anthropic |

## Related topics

> [card] [Skills](https://docs.learningcommons.org/agent-skills/skills/introduction.md)
>
> Explore available Agent Skills and their published evaluation rubrics.

> [card] [Core concepts](https://docs.learningcommons.org/agent-skills/understanding-agent-skills/core-concepts.md)
>
> Learn how skills, rubrics, and the P/R/O/M framework work together.
