Introduction

What Agent Skills do

Agent Skills are open, ready-to-use skills that help AI assistants produce high-quality, standards-aligned instructional materials for teachers. Edtech developers and school district technologists can use Agent Skills to plan and differentiate lessons for teachers.

Skill	Description
K-12 Lesson Planning	Builds classroom-ready, standards-aligned lesson plans, optionally aligned to a teacher’s curriculum
K-12 Lesson Differentiation	Adapts an existing lesson into tiered versions (below, at, or above proficiency level) and for specific student needs, keeping core content consistent across tiers

Agent Skills are grounded in learning science and can leverage Knowledge Graph to produce standards-aligned results.

When to use Agent Skills

Use case	Description	Examples
Ship teacher-facing features	Ship lesson planning and differentiation features in your edtech application without re-inventing pedagogy prompts or rubrics.	Embed K-12 Lesson Planning into a product workflow so teachers get classroom-ready plans on demand.
Offer standards-aligned materials at the district level	Deploy Agent Skills inside internal AI assistants at the district level to provide standards-aligned outputs to all teachers by default.	Add K-12 Lesson Differentiation to a district assistant that adapts existing lessons for mixed classrooms.
Plan standards-aligned lessons	Generate classroom-ready lesson plans with teacher-facing plans, student materials, and observation templates.	A 3rd grade teacher needs a lesson on rounding to the nearest hundred for tomorrow.
Differentiate existing lessons	Adapt a lesson into below / at / above proficiency tiers while preserving core content and grade-level demand.	A 6th grade teacher wants tiered versions of a food webs lesson linked from an external curriculum site.
Ground outputs in trusted data	Pair Agent Skills with Knowledge Graph to resolve standards, learning components, progressions, and curriculum context.	Anchor a math lesson to state standards and Illustrative Mathematics structures.
Benchmark instructional quality	Score generated materials against published evaluator rubrics using LLM-as-judge or human review.	Validate that a lesson plan meets pedagogy, rigor, formatting, and model-scaffolding criteria.

How to access Agent Skills

Agent Skills are cross-platform and model-agnostic. They can be used with any agent runtime that supports the open Agent Skills format ↗:

Claude Code
Cursor
Codex

Check out the GitHub repository ↗ to inspect skill instructions, reference files, scripts, and rubrics directly.

Our approach

Our initial set of Agent Skills and evaluator rubrics was co-developed with Anthropic ↗. These skills don’t just generate plausible-looking materials — they’re grounded in research-backed principles and refined with expert practitioners.

Principle	Description
Pedagogy	Outputs reflect sound instructional design. Standards alignment Prerequisite and forward connections Appropriate instructional model Discourse structures Attention to student struggle Visual and representational choices
Rigor	Outputs maintain grade-level cognitive demand
Usability	Outputs are classroom-ready and default to universal design

Core concepts

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

Quickstart

Install skills, connect Knowledge Graph, and try example prompts.

Understanding Agent Skills

Getting started

Skills

Resources

What Agent Skills do

When to use Agent Skills

How to access Agent Skills

Our approach

Core concepts

Quickstart

​What Agent Skills do

​When to use Agent Skills

​How to access Agent Skills

​Our approach

​Related topics

Core concepts

Quickstart

What Agent Skills do

When to use Agent Skills

How to access Agent Skills

Our approach

Related topics