Variation Theory Task Designer Agent Skill

Design a variation theory task using contrast, separation, and fusion to teach critical features of a concept.

Context cost
5.4k tokensestimated from the bundle, loaded when it triggers
Bundle
1 file · 21.5 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 variation theory task using contrast, separation, and fusion to teach critical features of a concept. Use when students confuse similar concepts or fail to discern key distinctions.

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.

contrastcritical-featuresdiscernmenthong-kongmartonmathematics-educationswedenvariation-theory

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.md21.5 kB · preview
--- # AGENT SKILLS STANDARD FIELDS (v2) name: variation-theory-task-designer disable-model-invocation: false user-invocable: true effort: medium # EXISTING FIELDS skill_id: "global-cross-cultural-pedagogies/variation-theory-task-designer" skill_name: "Variation Theory Task Designer" domain: "global-cross-cultural-pedagogies" version: "1.0" evidence_strength: "strong" evidence_sources: - "Marton (2015) — Necessary Conditions of Learning" - "Marton & Booth (1997) — Learning and Awareness" - "Lo (2012) — Variation Theory and the Improvement of Teaching and Learning" - "Kullberg, Runesson Kempe & Marton (2017) — What is made possible to learn when using the variation theory of learning in teaching mathematics?" - "Gu, Huang & Marton (2004) — Teaching with variation: a Chinese way of promoting effective Mathematics learning" input_schema: required: - field: "object_of_learning" type: "string" - field: "common_confusion" type: "string" optional: - field: "student_level" type: "string" - field: "subject_area" type: "string" - field: "current_task" type: "string" - field: "lesson_context" type: "string" output_schema: type: "object" fields: - field: "variation_analysis" type: "object" - field: "task_sequence" type: "array" - field: "teacher_guidance" type: "object" - field: "assessment_check" type: "string" chains_well_with: - "explicit-instruction-sequence-builder" - "worked-example-fading-designer" - "cpa-sequence-designer" - "diagnostic-question-generator" - "curriculum-knowledge-architecture-designer" teacher_time: "3 minutes" tags: ["variation-theory", "Marton", "discernment", "contrast", "critical-features", "Hong-Kong", "Sweden", "mathematics-education"] ---
68# Variation Theory Task Designer
69
70## What This Skill Does
71
72Designs learning tasks using variation theory — a framework developed by Ference Marton and colleagues in Sweden and Hong Kong that explains how learners come to discern critical features of concepts through systematic patterns of variation and invariance. The core principle is deceptively simple: to notice a feature, a learner must experience it VARYING while other features remain constant. If everything changes at once, no single feature becomes salient. The skill analyses the object of learning to identify its critical features (what students must discern), identifies common confusions (what students fail to distinguish), and designs a sequence of examples that systematically vary and hold invariant the right dimensions to make the critical feature visible. The output includes a variation analysis, a task sequence using the four patterns of variation (contrast, separation, generalisation, fusion), teacher guidance for drawing attention to the variation, and an assessment check. AI is specifically valuable here because designing effective variation sequences requires simultaneously considering what varies, what stays the same, and how each example relates to every other example in the sequence — a combinatorial challenge that benefits from systematic design.
73
74## Evidence Foundation
75
76Marton & Booth (1997) established the theoretical foundation: learning is a change in the way a person experiences or understands something, and this change requires the learner to discern features they previously did not notice. Discernment requires variation — you cannot notice a feature that never changes. Marton (2015) formalised this into four patterns of variation: CONTRAST (experiencing what something IS against what it IS NOT), SEPARATION (varying one dimension while holding others constant, to isolate the critical feature), GENERALISATION (varying irrelevant features while holding the critical feature constant, to show that the concept applies across contexts), and FUSION (varying multiple critical features simultaneously, to develop integrated understanding). Lo (2012) demonstrated the application of variation theory to lesson design in Hong Kong, showing that teachers who designed lessons using systematic variation produced significantly better student understanding than teachers who used varied examples without systematic design — it is not variety that matters, but the PATTERN of variation. Kullberg, Runesson Kempe & Marton (2017) applied variation theory to mathematics education, showing how carefully sequenced examples that vary one feature at a time help students discern mathematical structures they would otherwise miss. Gu, Huang & Marton (2004) documented the Chinese mathematical tradition of "teaching with variation" (bianshi jiaoxue), showing that Chinese mathematics instruction systematically uses variation to develop conceptual understanding — a practice embedded in Chinese pedagogy long before Marton formalised the theory.
77
78## Input Schema
79
80The teacher must provide:
81- **Object of learning:** What students need to learn to discern. *e.g. "The difference between area and perimeter — students confuse the two because they both involve measuring shapes" / "When to use 'effect' vs 'affect' — students use them interchangeably" / "The distinction between speed and velocity — students treat them as synonyms"*
82- **Common confusion:** What students get wrong. *e.g. "Students think bigger shapes always have bigger perimeters" / "Students default to 'effect' in all contexts" / "Students don't understand why direction matters in velocity"*
83
84Optional (injected by context engine if available):
85- **Student level:** Year group and prior knowledge
86- **Subject area:** The curriculum subject
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md3,270 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.

≈760
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
4,615
on trigger
The instruction body, read only when the skill fires.
2.7%
of a 200k window
Ten skills this size would take about 27% of the window before you open a file.
050k100k150k200k context window

5.4k 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, 21.5 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in.

  • SKILL.md21.5 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.

# Variation Theory Task Designer · 5.4k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/variation-theory-task-designer/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/variation-theory-task-designer" ] && { [ ! -e .claude/skills/variation-theory-task-designer ] || { mv .claude/skills/variation-theory-task-designer "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/variation-theory-task-designer" .claude/skills/ && echo "Installed .claude/skills/variation-theory-task-designer"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add garethmanning/variation-theory-task-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/variation-theory-task-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/variation-theory-task-designer/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/variation-theory-task-designer" ] && { [ ! -e ~/.claude/skills/variation-theory-task-designer ] || { mv ~/.claude/skills/variation-theory-task-designer "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/variation-theory-task-designer" ~/.claude/skills/ && echo "Installed ~/.claude/skills/variation-theory-task-designer" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/variation-theory-task-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/variation-theory-task-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