Progressive Hint Ladder Agent Skill

Provide graduated assistance from abstract conceptual nudge to concrete procedural step, with reflection required before each escalation.

Context cost
3.9k tokensestimated from the bundle, loaded when it triggers
Bundle
1 file · 15.4 kBtext throughout, nothing executable
Licence
not declarednone named by its author
Last change
—v1.0
Servers it uses
Noneruns standalone

What it does

Provide graduated assistance from abstract conceptual nudge to concrete procedural step, with reflection required before each escalation. Teaches help-seeking as a skill and prevents direct-answer shortcuts.

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.

assistance-dilemmadocumentationhelp-seekinghintsitsscaffolding

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.md15.4 kB · preview
--- # AGENT SKILLS STANDARD FIELDS (v2) name: progressive-hint-ladder disable-model-invocation: false user-invocable: true effort: medium # DOMAIN 20 FIELDS skill_id: "student-learning/progressive-hint-ladder" skill_name: "Progressive Hint Ladder" domain: "student-learning" domain_number: 20 version: "1.0" audience: "student" evidence_strength: "strong" evidence_sources: - "VanLehn (2011) — The relative effectiveness of human tutoring, ITS, and other tutoring systems (d = 0.76 for ITS with step-level help)" - "Aleven & Koedinger (2002) — An effective metacognitive strategy: learning by doing and explaining with a computer-based tutor" - "Koedinger & Aleven (2007) — Exploring the assistance dilemma in experiments with cognitive tutors" - "Karabenick & Berger (2013) — Help seeking as a self-regulated learning strategy" - "Wood et al. (1976) — The role of tutoring in problem solving: scaffolding theory" input_schema: required: - field: "problem_or_task" type: "string" - field: "context" type: "string" optional: - field: "prior_hint_level" type: "integer" - field: "developmental_band" type: "string" evidence_captured: cognitive_gate: "first_attempt" student_attempt_required: true confidence_before: false confidence_after: false hint_level_reached: "0-5" error_type: "conceptual | procedural | strategic | not_applicable" ai_support_type: "question | hint | parallel_example" reflection_captured: true transfer_check: "not_applicable" unassisted_followup: "not_scheduled" assistance_tag: "scaffolded" chains_well_with: - "student-learning/retrieve-first-gate" - "student-learning/stuck-and-error-diagnosis-coach" - "student-learning/productive-failure-protocol" - "student-learning/unassisted-evidence-checkpoint" tags: ["hints", "scaffolding", "help-seeking", "ITS", "assistance-dilemma"] ---
59# Progressive Hint Ladder
60
61## What This Skill Does
62
63Provides graduated assistance across six levels — from a diagnostic question through abstract conceptual nudge, analogy, principle reminder, procedural nudge, and near-complete scaffold — with a reflection requirement at each level before escalation is permitted. The learner never receives the full answer. Before any hint is given, the skill asks what kind of help the learner thinks they need — teaching help-seeking as a skill, not just providing help. The hint level reached becomes evidence about the learner's current support needs.
64
65## Evidence Foundation
66
67VanLehn (2011) synthesised research across human tutors, intelligent tutoring systems (ITS), and other instruction formats, finding effect sizes of d = 0.76 for ITS that provided step-level assistance compared to classroom instruction — comparable to the best human tutors. A critical feature of effective ITS was that hints were graduated and required the student to engage with each level before proceeding. Aleven & Koedinger (2002) studied the Cognitive Tutor and found that students who over-used hints ("hint abuse" — clicking through rapidly without engaging) showed significantly worse learning outcomes than students who engaged with each level; they developed an effective metacognitive intervention where students explained what each hint told them before proceeding. Koedinger & Aleven (2007) formalised the "assistance dilemma": providing too much help too quickly prevents the effortful processing that produces learning; providing too little causes frustration and disengagement. The optimal point is systematically less help than students prefer — but with warmth and a rationale. Karabenick & Berger (2013) showed that adaptive help-seeking — asking targeted questions rather than requesting full answers — is a self-regulation skill that predicts academic success. Wood et al. (1976) introduced scaffolding theory: effective scaffolding reduces the freedom of the task to match the learner's current capability, then gradually restores that freedom as competence develops. The hint ladder operationalises this temporally — each level reduces the degrees of freedom slightly, and the ladder only descends when the learner cannot proceed with the current level.
68
69## System Prompt
70
71```
72You are a learning coach helping {{name_or_"the learner"}} work through a problem. Your job is to help them think — not to think for them. The governing principle: provide the minimum help needed for the learner to make the next step themselves. You have six hint levels available; use them in order, and never give a level the learner doesn't need. You will never provide the full solution.
73
74CONTEXT: {{context}}
75PROBLEM OR TASK: {{problem_or_task}}
76PRIOR HINT LEVEL: {{prior_hint_level — if not provided, start at Level 0}}
77DEVELOPMENTAL BAND: {{developmental_band — if not provided, assume secondary school / undergraduate}}
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md2,406 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.

≈610
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
3,240
on trigger
The instruction body, read only when the skill fires.
1.9%
of a 200k window
Ten skills this size would take about 19% of the window before you open a file.
050k100k150k200k context window

3.9k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Middling. Fine to keep on in a project where you use it weekly, worth unloading in one where you never do.

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

  • SKILL.md15.4 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.

# Progressive Hint Ladder · 3.9k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/progressive-hint-ladder/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/progressive-hint-ladder" ] && { [ ! -e .claude/skills/progressive-hint-ladder ] || { mv .claude/skills/progressive-hint-ladder "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/progressive-hint-ladder" .claude/skills/ && echo "Installed .claude/skills/progressive-hint-ladder"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add garethmanning/progressive-hint-ladder

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

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