Developmental Progression Synthesis Agent Skill

Synthesise completed KUD charts into a developmental progression matrix and per-competency narrative sections.

Context cost
8.3k tokensestimated from the bundle, loaded when it triggers
Bundle
1 file · 33.4 kBtext throughout, nothing executable
Licence
not declarednone named by its author
Last change
—v1.0
Servers it uses
Noneruns standalone

What it does

Synthesise completed KUD charts into a developmental progression matrix and per-competency narrative sections. Use when you need a programme-level view of how knowledge, understanding, and performance develop across bands.

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.

bandscompetencydevelopmental-progressionkudmatrixprogramme-guidescope-and-sequencesynthesis

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.md33.4 kB · preview
--- # AGENT SKILLS STANDARD FIELDS (v2) name: developmental-progression-synthesis disable-model-invocation: true user-invocable: true effort: high # EXISTING FIELDS skill_id: "original-frameworks/developmental-progression-synthesis" skill_name: "Developmental Progression Synthesis" domain: "original-frameworks" version: "1.0" evidence_strength: "emerging" evidence_sources: - "Wiggins & McTighe (2005) — Understanding by Design (backward design; desired results as the basis for programme coherence)" - "Vygotsky (1978) — Mind in society (ZPD; band statements describe the upper edge of capability with support)" - "Bruner (1960) — The Process of Education (spiral curriculum; concepts revisited with increasing sophistication across developmental stages)" - "Hattie & Donoghue (2016) — Learning strategies: a synthesis and conceptual model (surface to deep to transfer as a developmental progression model)" - "Biggs & Collis (1982) — Evaluating the Quality of Learning: the SOLO Taxonomy (structural complexity as a developmental progression lever)" input_schema: required: - field: "kud_charts" type: "string" - field: "competency_structure" type: "string" optional: - field: "output_focus" type: "string" - field: "knowledge_type_filter" type: "string" - field: "audience" type: "string" output_schema: type: "object" fields: - field: "developmental_matrix" type: "object" - field: "competency_chapters" type: "object" - field: "design_notes" type: "object" chains_well_with: - "kud-chart-author" - "learning-target-authoring-guide" - "scope-and-sequence-designer" - "coherent-rubric-logic-builder" - "dispositional-knowledge-assessment-designer" tags: ["developmental-progression", "KUD", "programme-guide", "scope-and-sequence", "matrix", "competency", "bands", "synthesis", "curriculum-design"] ---
61# Developmental Progression Synthesis
62
63## What This Skill Does
64
65This skill takes a completed set of KUD charts and synthesises them into two linked artefacts for a programme guide.
66
67**Output 1 — Developmental matrix:** A competency × band grid showing the key developmental milestone for each LT at each band. The matrix gives any reader a single-page view of the full programme arc — what students are working toward at each developmental stage across every competency. Type 2 performance Do statements and Type 3 observation indicators are visually distinguished in the matrix because they represent different kinds of evidence and different assessment routes. Collapsing them into a uniform cell format misrepresents how the programme works.
68
69**Output 2 — Per-competency developmental sections:** For each competency, a narrative section showing how Know, Understand, and Do develop across bands within that competency's LTs. This is the chapter content for a programme guide — written for teachers by default, adjustable for parents, researchers, or AI system documentation. Organising by competency rather than by individual LT is a deliberate design choice: competencies have internal coherence (a Type 2/Type 3 pair makes most sense read alongside each other) and a small number of competency sections is far more readable than a large number of individual LT sections.
70
71**What this skill is not:** It is not a scope-and-sequence tool. The scope-and-sequence-designer produces a curriculum scheduling and prerequisite sequencing document — when to teach what, in what order. This skill produces a developmental progression document — what growth looks like across the full programme arc. Both are needed; they answer different questions.
72
73**Critical design principle:** The synthesis must surface the progression logic explicitly, not just reproduce the band statements. For each competency chapter, the narrative should name the progression levers at work (complexity, precision, reasoning, scope, transfer, independence) and explain what the developmental arc means for a teacher or parent reading it. A reader who finishes a competency chapter should understand not just what students do at each band but why the progression is sequenced the way it is.
74
75**Type 2 versus Type 3 in the matrix:** Type 2 Do statements describe task performance — what a student produces in a rubric-assessed task. Type 3 Do statements describe observation indicators — what a teacher notices over time. These must be visually distinct in the matrix. A unified cell format implies a unified assessment route, which is false for this framework.
76
77## Evidence Foundation
78
79Wiggins & McTighe (2005) provide the backwards design framework underpinning the synthesis structure: desired results — the end-of-programme developmental picture — must be articulated before curriculum decisions are made. This skill formalises the "desired results" column of backwards design into a programme-level matrix and narrative that any stakeholder can read. Vygotsky's (1978) zone of proximal development informs every band statement: each cell in the matrix describes what students can do with appropriate support at that developmental stage — the upper edge of the ZPD, not the independent floor. Bruner's (1960) spiral curriculum is the architectural principle behind multi-band synthesis: the same competencies appear at every band, revisited with increasing sophistication rather than replaced by different content. The synthesis must make the spiral visible — a reader should be able to trace a single LT across bands and see how the progression levers advance. Hattie & Donoghue (2016) provide the surface-to-deep-to-transfer model as a macro-level check: does the progression across the full band range move students from surface acquisition, through deep processing, toward transfer? Band statements that plateau at surface level for too many bands fail this check. Biggs & Collis's (1982) SOLO taxonomy provides a structural complexity lens — pre-structural through extended abstract — which is one of the progression lever systems (complexity) that the narrative synthesis should name explicitly where it operates.
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md4,513 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.

≈920
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
7,430
on trigger
The instruction body, read only when the skill fires.
4.2%
of a 200k window
Ten skills this size would take about 42% of the window before you open a file.
050k100k150k200k context window

8.3k 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, 33.4 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in.

  • SKILL.md33.4 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.

# Developmental Progression Synthesis · 8.3k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/developmental-progression-synthesis/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/developmental-progression-synthesis" ] && { [ ! -e .claude/skills/developmental-progression-synthesis ] || { mv .claude/skills/developmental-progression-synthesis "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/developmental-progression-synthesis" .claude/skills/ && echo "Installed .claude/skills/developmental-progression-synthesis"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add garethmanning/developmental-progression-synthesis

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/developmental-progression-synthesis/ 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/developmental-progression-synthesis/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/developmental-progression-synthesis" ] && { [ ! -e ~/.claude/skills/developmental-progression-synthesis ] || { mv ~/.claude/skills/developmental-progression-synthesis "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/developmental-progression-synthesis" ~/.claude/skills/ && echo "Installed ~/.claude/skills/developmental-progression-synthesis" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/developmental-progression-synthesis/ 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/developmental-progression-synthesis

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