> ## 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 Check for Understanding
> Reference for the K-12 Check for Understanding skill, which generates 1-3 formative assessment items with answer keys and interpretation guides.
[Skill last updated August 28, 2026](https://github.com/learning-commons-org/agent-skills/tree/main/skills/k12-check-for-understanding)
The K-12 Check for Understanding Agent Skill was co-developed with
[Anthropic](https://www.anthropic.com/) ↗. This skill was refined through
evaluation and feedback from [Student Achievement Partners
(SAP)](https://learnwithsap.org/research-grounded-products/) ↗. SAP's
involvement does not imply endorsement or guarantee of how the skill is used,
modified, or built on downstream.
## Overview
The [K-12 Check for Understanding](https://github.com/learning-commons-org/agent-skills/tree/main/skills/k12-check-for-understanding) ↗ skill generates a Check for Understanding (CFU).
A CFU is a small, targeted set of 1-3 items that surfaces what a student currently understands about a concept, skill, or standard, and what a teacher should do next.
The skill produces the following `.html` file artifacts in Turn 1:
* **Student version** — Formative assessment itself, with CFU items only
* **Teacher version** — Same items plus an answer key and an interpretation guide for each item
The skill takes into account:
* What the target standard or skill asks the student to know or do
* Aspects of rigor the standard calls for (conceptual, procedural, application)
* Common misconceptions and barriers
* Grounding items in a CCSS [standard](/knowledge-graph/schema-reference/standards), its [learning components](/knowledge-graph/schema-reference/learning-components), and its position in the [learning progression](/knowledge-graph/schema-reference/learning-progressions) when connected to the [Knowledge Graph](/knowledge-graph/)
This skill works with or without Knowledge Graph, but we strongly recommend
connecting to it. See [Quickstart: Connect Knowledge
Graph](/agent-skills/getting-started/quickstart#connect-knowledge-graph) for
more information.
## At a glance
| | |
| :------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Workflow** | Generate a short, targeted formative Check for Understanding for a math standard or topic |
| **Subject** | Math |
| **Supported grades** | K–12 |
| **Item count** | 1–3 items per CFU |
| **Rubrics** | [`math.csv`](https://github.com/learning-commons-org/agent-skills/blob/main/evals/k12-check-for-understanding/rubrics/math.csv) ↗ — 5-bucket [P/R/O/M framework](/agent-skills/understanding-agent-skills/core-concepts#the-p-r-o-m-framework) (pedagogy, rigor, output, model scaffolding, and Knowledge Graph use) |
## Getting started
Follow the [Quickstart](/agent-skills/getting-started/quickstart) to start using this skill:
| Access method | |
| :---------------------- | :--------------------------------------------------------------------------------------------------------------------------------------- |
| **Knowledge Graph MCP** | [Quickstart: Connect Knowledge Graph](/agent-skills/getting-started/quickstart#connect-knowledge-graph) |
| **Example prompts** | [example-prompts.md](https://github.com/learning-commons-org/agent-skills/blob/main/skills/example-prompts.md#check-for-understanding) ↗ |
| **Skill instructions** | [`SKILL.md`](https://github.com/learning-commons-org/agent-skills/blob/main/skills/k12-check-for-understanding/SKILL.md) ↗ |
## Triggers
Your LLM will programmatically load this skill when explicitly or implicitly prompted to create a short, targeted formative check for a math standard or topic (NOT a full lesson, unit test, or rubric):
* **Explicitly**: "check for understanding," "CFU," "formative assessment," "quick check," "exit ticket"
* **Implicitly**: "I want to see if my students get fractions before we move on," "give me something quick to gauge understanding of 5.NF.A.1," "what should I ask to see who's ready for the next lesson"
## Output
| Artifact | Description |
| :------------------ | :---------------------------------------------------------------------------------------------------------------------------------------------- |
| **Student version** | Formative assessment itself — the CFU item(s) only, formatted for a student to complete. No answer key or teacher guidance. |
| **Teacher version** | Same item(s) plus the correct answer(s) and an interpretation guide: what each response reveals, and a specific, actionable suggested next step |
| **Rendered files** | Self-contained `.html` files for both versions, viewable with no internet connection |
## Scoring
The K-12 Check for Understanding skill's outputs are scored against a 5-bucket rubric called the [P/R/O/M framework](/agent-skills/understanding-agent-skills/core-concepts#the-p-r-o-m-framework), developed with Student Achievement Partners, that separates pedagogical fidelity from item mechanics from whether Knowledge Graph data was actually used.
1. Generate a CFU (both student and teacher versions) using this skill.
2. Apply the P, R, and O bucket criteria to every output; apply M and Q where the Knowledge Graph was used.
3. Run LLM-as-judge or human review against each criterion. See [Evaluating outputs](/agent-skills/using-agent-skills/evaluating-outputs).
## Skill release history
| Date | Changed |
| --------------- | --------------------------------------------------------------------------- |
| August 28, 2026 | First release, developed in collaboration with Student Achievement Partners |