Prepared Environment Designer Agent Skill

Redesign a classroom as a prepared environment optimised for independent learning, calm transitions, and material access.

Context cost
7k tokensestimated from the bundle, loaded when it triggers
Bundle
1 file · 28.1 kBtext throughout, nothing executable
Licence
not declarednone named by its author
Last change
—v1.0
Servers it uses
Noneruns standalone

What it does

Redesign a classroom as a prepared environment optimised for independent learning, calm transitions, and material access. Use when classroom layout hinders independence or self-directed work.

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.

accessibilitybeautyclassroom-designcossentinolillardmontessoriorderprepared-environment

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.md28.1 kB · preview
--- # AGENT SKILLS STANDARD FIELDS (v2) name: prepared-environment-designer disable-model-invocation: false user-invocable: true effort: medium # EXISTING FIELDS skill_id: "montessori-alternative-approaches/prepared-environment-designer" skill_name: "Prepared Environment Designer" domain: "montessori-alternative-approaches" version: "1.0" evidence_strength: "moderate" evidence_sources: - "Lillard (2005) — Montessori: The Science Behind the Genius" - "Cossentino (2006) — Big work: goodness, volitional action, and the classroom environment in Montessori method" - "Barrett et al. (2015) — The impact of classroom design on pupils' learning: final results of a holistic, multi-level analysis (HEAD project)" - "Fisher et al. (2014) — Visual environment, attention, and learning in young children: when too much of a good thing may be bad" - "Lillard & Else-Quest (2006) — Evaluating Montessori education (Science)" input_schema: required: - field: "current_environment" type: "string" - field: "improvement_goals" type: "string" optional: - field: "student_level" type: "string" - field: "budget" type: "string" - field: "space_constraints" type: "string" - field: "curriculum_context" type: "string" - field: "time_for_implementation" type: "string" output_schema: type: "object" fields: - field: "environment_audit" type: "object" - field: "redesign_plan" type: "object" - field: "implementation_sequence" type: "array" - field: "maintenance_protocol" type: "object" chains_well_with: - "three-part-lesson-designer" - "uninterrupted-work-cycle-designer" - "mixed-age-learning-task-designer" - "biophilic-learning-environment-designer" teacher_time: "5 minutes" tags: ["Montessori", "prepared-environment", "classroom-design", "Lillard", "Cossentino", "accessibility", "order", "beauty", "materials"] ---
70# Prepared Environment Designer
71
72## What This Skill Does
73
74Evaluates a classroom or learning space against Montessori prepared environment principles and produces a practical redesign plan. The prepared environment is one of Montessori's most distinctive and influential contributions: the idea that the physical space IS the curriculum — that a carefully designed environment invites learning, supports independence, and reduces the need for teacher direction. Lillard (2005) identified the key principles: accessibility (children can reach and choose materials independently), order (everything has a defined place and is returned there after use), beauty (the environment is aesthetically pleasing, using natural materials and careful design), real materials (functional objects, not toys — real glass, real tools, real plants), and child scale (furniture and materials are sized for the children using them). Cossentino (2006) added the concept of "big work" — the environment should invite sustained, meaningful engagement rather than quick, scattered activity. This skill is particularly valuable because environment design is one of the Montessori principles with the most independent supporting evidence: Barrett et al. (2015) found that classroom design factors (light, temperature, air quality, ownership, flexibility, complexity, and colour) explained 16% of variance in student learning progress — a substantial effect for a single variable. Fisher et al. (2014) found that visually cluttered classrooms significantly reduced children's attention and learning, providing direct empirical support for the Montessori emphasis on visual order.
75
76## Evidence Foundation
77
78Lillard (2005) provided the most comprehensive analysis of the prepared environment through a cognitive science lens. She argued that Montessori's environmental design principles align with research on: (a) embodied cognition — children learn through physical interaction with materials, so materials must be accessible and inviting; (b) executive function — an ordered environment with clear routines supports the development of self-regulation; (c) attention — a visually calm environment with purposeful displays reduces distraction and supports sustained focus; and (d) intrinsic motivation — an environment where children choose their own work supports autonomy and engagement. Cossentino (2006) conducted an ethnographic study of Montessori classrooms and identified "big work" as a defining characteristic of the prepared environment. The environment is designed so that the most engaging, challenging, and meaningful activities are the most visible and accessible — children are drawn toward deep work by the design of the space, not by teacher instruction. Cossentino found that the aesthetic quality of the environment communicated respect for children's work and created a culture of care and craftsmanship. Barrett et al. (2015) conducted the HEAD (Holistic Evidence and Design) study — the largest study of classroom design and learning outcomes. They assessed 153 classrooms in 27 UK schools and found that classroom design explained 16% of the variance in pupil learning progress over one year. The most influential factors were naturalness (light, temperature, air quality), individualisation (ownership, flexibility), and stimulation (complexity, colour). The optimal classroom had good natural light, moderate visual complexity (not bare, not cluttered), and evidence of student ownership. These findings independently support several Montessori principles: natural light, visual order (moderate complexity), and student ownership of the space. Fisher et al. (2014) experimentally tested the effect of classroom visual environment on kindergarten children's learning. They found that children in heavily decorated classrooms (walls covered with posters, maps, artwork) spent significantly more time off-task and scored lower on learning assessments than children in sparse classrooms. The effect was substantial: 38.6% time off-task in decorated rooms vs. 28.4% in sparse rooms. This provides direct empirical support for the Montessori principle that the environment should be visually ordered and purposeful, not visually overwhelming.
79
80## Input Schema
81
82The teacher must provide:
83- **Current environment:** What the space looks like now. *e.g. "Year 1 classroom, approximately 60m². Tables arranged in 6 groups of 4. Teacher desk at the front with interactive whiteboard. Walls covered in commercial posters, reward charts, and last term's student work. Materials stored in labelled plastic boxes on high shelves — children need to ask an adult to access most resources. Carpet area in one corner for whole-class teaching. Coat pegs and bags create a cluttered corridor entrance" / "Home learning room for 3 children aged 4, 7, and 10. Small bedroom converted to learning space. IKEA bookshelf, a table, and three chairs. Currently used as a general dumping ground"*
84- **Improvement goals:** What the teacher wants to achieve. *e.g. "Children constantly ask me for materials — I want them to access resources independently. Transitions between activities take 10 minutes. The room feels chaotic and I think it affects behaviour" / "I want a space where all three children can work simultaneously on different things without fighting or needing constant supervision"*
85
86Optional (injected by context engine if available):
87- **Student level:** Age/year group
88- **Budget:** Available resources for changes
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md4,027 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.

≈870
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
6,155
on trigger
The instruction body, read only when the skill fires.
3.5%
of a 200k window
Ten skills this size would take about 35% of the window before you open a file.
050k100k150k200k context window

7k 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, 28.1 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in.

  • SKILL.md28.1 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.

# Prepared Environment Designer · 7k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/prepared-environment-designer/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/prepared-environment-designer" ] && { [ ! -e .claude/skills/prepared-environment-designer ] || { mv .claude/skills/prepared-environment-designer "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/prepared-environment-designer" .claude/skills/ && echo "Installed .claude/skills/prepared-environment-designer"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add garethmanning/prepared-environment-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/prepared-environment-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/prepared-environment-designer/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/prepared-environment-designer" ] && { [ ! -e ~/.claude/skills/prepared-environment-designer ] || { mv ~/.claude/skills/prepared-environment-designer "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/prepared-environment-designer" ~/.claude/skills/ && echo "Installed ~/.claude/skills/prepared-environment-designer" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/prepared-environment-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/prepared-environment-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