Publish Sign in

Transfer Bridge Agent Skill

After the learner demonstrates understanding of a concept, present near-transfer and far-transfer challenges.

Install this skill Read the source first Free Written by GarethManning
Context cost
4.2k tokensestimated from the bundle, loaded when it triggers
Bundle
1 file · 16.7 kBtext throughout, nothing executable
Licence
not declarednone named by its author
Last change
—v1.0
Servers it uses
Noneruns standalone

What it does

After the learner demonstrates understanding of a concept, present near-transfer and far-transfer challenges. Use to test whether learning is portable or task-specific — this is what separates understanding from familiarity.

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.

deep-learningdocumentationfar-transfernear-transferportable-understandingtransfer
Filed under

Learning & Documentation

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.md16.7 kB · preview
--- # AGENT SKILLS STANDARD FIELDS (v2) name: transfer-bridge disable-model-invocation: false user-invocable: true effort: medium # DOMAIN 20 FIELDS skill_id: "student-learning/transfer-bridge" skill_name: "Transfer Bridge" domain: "student-learning" domain_number: 20 version: "1.0" audience: "student" evidence_strength: "moderate" evidence_sources: - "Bransford & Schwartz (1999) — Rethinking transfer: a simple proposal with multiple implications" - "Biswas et al. (2016) — Betty's Brain: computer-based learning environment that promotes science reasoning and metacognition" - "Kapur (2016) — Examining productive failure, productive success, unproductive failure, and unproductive success" - "Perkins & Salomon (1992) — Transfer of learning: contribution to the international encyclopaedia of education" - "Gick & Holyoak (1983) — Schema induction and analogical transfer" input_schema: required: - field: "concept_just_learned" type: "string" - field: "original_context" type: "string" optional: - field: "near_transfer_domain" type: "string" - field: "far_transfer_domain" type: "string" - field: "developmental_band" type: "string" evidence_captured: cognitive_gate: "verification" student_attempt_required: true confidence_before: false confidence_after: false hint_level_reached: "not_applicable" error_type: "conceptual | strategic | not_applicable" ai_support_type: "question | warm_start" reflection_captured: true transfer_check: "passed | failed | skipped" unassisted_followup: "not_scheduled" assistance_tag: "scaffolded" chains_well_with: - "student-learning/retrieve-first-gate" - "student-learning/explain-first-interrogator" - "student-learning/productive-failure-protocol" - "student-learning/unassisted-evidence-checkpoint" tags: ["transfer", "deep-learning", "near-transfer", "far-transfer", "portable-understanding"] ---
62# Transfer Bridge
63
64## What This Skill Does
65
66After the learner demonstrates understanding of a concept, presents a near-transfer challenge (same principle, slightly different surface) and a far-transfer challenge (same underlying principle, substantially different domain or context). Asks the learner three questions about each: what is the same, what is different, and what principle travels across the contexts? This tests whether learning is portable — whether the learner has grasped the underlying structure or merely the surface features of the examples they studied. Far-transfer failure after near-transfer success is common and informative: it reveals that the concept was learned contextually rather than abstractly.
67
68## Evidence Foundation
69
70Bransford & Schwartz (1999) proposed a reconceptualisation of transfer as "preparation for future learning" — arguing that the most important measure of understanding is not whether the learner can immediately transfer a concept but whether they can learn a new but related concept more efficiently. Their work showed that students who struggled with novel applications before receiving instruction retained more when instruction came, compared to students who had only practised standard versions. Gick & Holyoak (1983) demonstrated that analogical transfer depends on recognising structural similarity between problems — and that surface similarity is the primary obstacle: learners who see the same problem in a different surface form often fail to transfer their knowledge. They showed that explicitly naming the underlying principle, rather than just solving instances, significantly improves transfer. Perkins & Salomon (1992) distinguish near transfer (same context, similar surface) and far transfer (different context, same deep structure) and note that far transfer requires "high road" transfer — deliberate abstraction of the principle from its original context. Kapur (2016) showed that students who engaged with novel applications before consolidation produced better transfer outcomes than students who consolidated first — suggesting that the struggle of applying a principle to an unfamiliar context is itself a learning mechanism. Biswas et al. (2016) found that students who taught concepts to an AI agent (Betty's Brain) showed better transfer performance than students who studied normally, because the teaching process required abstracting the concept from specific examples.
71
72## System Prompt
73
74```
75You are a learning coach testing whether {{name_or_"the learner"}}'s understanding of {{concept_just_learned}} is portable — whether it works outside the context where they first learned it. The governing principle: if understanding can't transfer, it isn't fully formed yet. This is the transfer bridge session.
76
77CONCEPT JUST LEARNED: {{concept_just_learned}}
78ORIGINAL LEARNING CONTEXT: {{original_context}}
79NEAR TRANSFER DOMAIN: {{near_transfer_domain — if not provided, choose a domain close to the original context}}
80FAR TRANSFER DOMAIN: {{far_transfer_domain — if not provided, choose a substantively different domain that shares the same underlying principle}}
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md2,392 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.

≈670
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
3,505
on trigger
The instruction body, read only when the skill fires.
2.1%
of a 200k window
Ten skills this size would take about 21% of the window before you open a file.
050k100k150k200k context window

4.2k 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, 16.7 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in.

  • SKILL.md16.7 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.

# Transfer Bridge · 4.2k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/transfer-bridge/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/transfer-bridge" ] && { [ ! -e .claude/skills/transfer-bridge ] || { mv .claude/skills/transfer-bridge "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/transfer-bridge" .claude/skills/ && echo "Installed .claude/skills/transfer-bridge"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add garethmanning/transfer-bridge

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

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.

Who wrote it

GA
GarethManning

Publishes on mcprush.

0 servers listed174 skills listednot claimed
Profile
Publisher
Servers0
Claim this skill