Checking for Understanding Protocol Designer Agent Skill

Design a checking-for-understanding protocol with specific techniques for each lesson stage.

Context cost
4.8k tokensestimated from the bundle, loaded when it triggers
Bundle
1 file · 19.2 kBtext throughout, nothing executable
Licence
not declarednone named by its author
Last change
—v1.0
Servers it uses
Noneruns standalone

What it does

Design a checking-for-understanding protocol with specific techniques for each lesson stage. Use when planning systematic comprehension checks during explicit or direct instruction.

What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.

checking-understandingcold-callingdocumentationfeedbackformative-assessmentquestioning

The skill itself

A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.

SKILL.md19.2 kB · preview
--- # AGENT SKILLS STANDARD FIELDS (v2) name: checking-for-understanding-protocol-designer disable-model-invocation: false user-invocable: true effort: medium # EXISTING FIELDS skill_id: "explicit-instruction/checking-for-understanding-protocol-designer" skill_name: "Checking for Understanding Protocol Designer" domain: "explicit-instruction" version: "1.0" evidence_strength: "strong" evidence_sources: - "Rosenshine (2012) — Principles of Instruction, Principle 3: ask a large number of questions and check all student responses" - "Wiliam (2011) — Embedded Formative Assessment: practical strategies for checking understanding" - "Lemov (2015) — Teach Like a Champion 2.0: cold call, show call, and other CFU techniques" - "Black & Wiliam (1998) — Assessment and classroom learning: formative assessment effect size ~0.66" - "Christodoulou (2017) — Making Good Progress?: hinge questions and diagnostic assessment" input_schema: required: - field: "lesson_content" type: "string" - field: "lesson_stage" type: "string" - field: "student_level" type: "string" optional: - field: "class_size" type: "integer" - field: "common_misconceptions" type: "array" - field: "student_profiles" type: "array" - field: "available_resources" type: "string" output_schema: type: "object" fields: - field: "cfu_techniques" type: "array" - field: "hinge_question" type: "object" - field: "cold_call_plan" type: "object" - field: "response_decision_tree" type: "string" chains_well_with: - "explicit-instruction-sequence-builder" - "hinge-question-designer" - "formative-assessment-technique-selector" - "retrieval-practice-generator" teacher_time: "3 minutes" tags: ["formative-assessment", "checking-understanding", "questioning", "cold-calling", "feedback"] ---
70# Checking for Understanding Protocol Designer
71
72## What This Skill Does
73
74Generates a set of checking-for-understanding techniques appropriate for a specific lesson stage, including cold-calling scripts, mini-whiteboard prompts, exit tickets, and hinge questions — each with implementation detail and a decision tree for what to do based on results. The output tells the teacher not just *how* to check but *what to do with the information*. AI is specifically valuable here because effective CFU requires matching the right technique to the right moment (you don't use an exit ticket mid-explanation) and designing questions that reveal understanding rather than just confirming that students were listening. Most CFU in practice is "Any questions?" or "Does everyone understand?" — which checks nothing.
75
76## Evidence Foundation
77
78Rosenshine (2012) identified frequent checking for understanding as Principle 3 of effective instruction: "Successful teachers ask a large number of questions, check the responses of all students, and provide systematic feedback and corrections." Black & Wiliam (1998) demonstrated that formative assessment — the use of assessment information to adjust instruction — produces an effect size of approximately 0.66, but only when teachers act on the results. Wiliam (2011) operationalised formative assessment into five key strategies, with "engineering effective classroom discussions, activities, and learning tasks that elicit evidence of learning" at the core. Lemov (2015) provided practical classroom techniques including cold calling (asking students who haven't volunteered, with thinking time), show call (selecting student work for whole-class analysis), and standardised formats that allow quick scanning of all student responses. Christodoulou (2017) advanced the concept of hinge questions — single diagnostic questions whose answers reveal whether students have understood the critical concept well enough to progress.
79
80## Input Schema
81
82The teacher must provide:
83- **Lesson content:** What is being taught. *e.g. "How to calculate the area of a circle using πr²" / "The causes of the English Civil War" / "Writing a balanced argument with counter-claims"*
84- **Lesson stage:** When CFU is needed. *e.g. "During instruction — I want to check before moving on" / "End of lesson — exit ticket" / "All stages — give me a full protocol"*
85- **Student level:** Year group and class characteristics. *e.g. "Year 7, enthusiastic but often overconfident — they say they understand when they don't"*
86
87Optional (injected by context engine if available):
88- **Class size:** Number of students
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md2,893 words
Files1
Licencenot declared
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈740
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
4,060
on trigger
The instruction body, read only when the skill fires.
2.4%
of a 200k window
Ten skills this size would take about 24% of the window before you open a file.
050k100k150k200k context window

4.8k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Heavy. Teams tend to install this one per project rather than globally, and load it only when the job comes up.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

The procedure it runs

The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

Its SKILL.md does not declare which tools it asks the agent for, so what it touches is whatever the instructions themselves ask for — read them before you install it.

What it asks for
Writes filesnot declared
Network accessnot declared

This SKILL.md carries no allowed-tools line, so neither is declared. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

1 file, 19.2 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in.

  • SKILL.md19.2 kB
What is not in it

No dependencies and nothing executable: a skill is text the agent reads, so the bundle is 1 file you can review in full before installing.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# Checking for Understanding Protocol Designer · 4.8k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/garethmanning-checking-for-understanding-protocol/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/checking-for-understanding-protocol-designer" ] && { [ ! -e .claude/skills/checking-for-understanding-protocol-designer ] || { mv .claude/skills/checking-for-understanding-protocol-designer "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/checking-for-understanding-protocol-designer" .claude/skills/ && echo "Installed .claude/skills/checking-for-understanding-protocol-designer"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add garethmanning/checking-for-understanding-protocol-designer

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/checking-for-understanding-protocol-designer/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/garethmanning-checking-for-understanding-protocol/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/checking-for-understanding-protocol-designer" ] && { [ ! -e ~/.claude/skills/checking-for-understanding-protocol-designer ] || { mv ~/.claude/skills/checking-for-understanding-protocol-designer "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/checking-for-understanding-protocol-designer" ~/.claude/skills/ && echo "Installed ~/.claude/skills/checking-for-understanding-protocol-designer" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/checking-for-understanding-protocol-designer/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where.

Which clients pick it up on their own

A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.

Claude Code.claude/skills/
Claude DesktopCustomize › Skills
ChatGPTSkills › Create › Upload
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok Build.grok/skills/
Microsoft CopilotSkills › Upload a skill
PerplexityComputer › Skills › Upload a skill
DeepSeek Harness.dsh/skills/
Zed.agents/skills/
Devin Desktop.devin/skills/
Windsurf (legacy).windsurf/skills/
OpenAI Agents SDKInstructions or sandbox Skills
HTTP / APIa request parameter
This release
Version1.0
Publishedno release date on file
PriceFree
Referencegarethmanning/checking-for-understanding-protocol-designer

Versions

v1.0 is what is on the shelf; no release here carries a date. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

v1.0
  • No earlier releases have been published to the marketplace.
Pinning

The install command always fetches the release that is current the day you run it — v1.0 today — and cannot ask for an earlier one. The copy on your disk does not change until you run it again.

Reviews

—no reviews yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Sign in to review it

A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.

Sign in
Who can post

Anybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.

Publisher
Servers0
Claim this skill