Skip to main content
Skill last updated July 14, 2026
The K-12 Lesson Differentiation Agent Skill was co-developed with Anthropic ↗.

Overview

The K-12 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). The skill produces the following artifacts in Turn 1, all rendered from one master JSON via bundled scripts:
  • 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
This skill works with or without Knowledge Graph, but we strongly recommend connecting to it. See Quickstart: Connect Knowledge Graph for more information.

At a glance

Getting started

Follow the Quickstart to start using this skill:

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

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.

Skill release history

Skills

Explore available Agent Skills and their published evaluation rubrics.

Core concepts

Learn how skills, rubrics, and the P/R/O/M framework work together.