AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Learning Accelerator

skill-joellewis-skill-library-learning-accelerator · by JoelLewis

Compresses domain mastery using Ultralearning and Metacognition principles — moving from passive consumption to active production through directness, retrieval practice, and feedback loops. Use when learning a new domain rapidly, building a study plan, or preparing for a high-stakes professional skill.

No reviews yet
0 installs
0 views
view→install

Install

$ agentstack add skill-joellewis-skill-library-learning-accelerator

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-joellewis-skill-library-learning-accelerator)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
5mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Learning Accelerator? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Overview

Learning is the meta-skill that powers all others. This skill applies the principles of Ultralearning and Metacognition to compress years of traditional study into months of high-intensity practice. It moves learning from passive consumption to active production.

Iron Law

NO LEARNING PLAN WITHOUT A RETRIEVAL AND SPACING STRATEGY

Reading and highlighting create an "illusion of competence." True mastery requires active retrieval (testing) and a spacing strategy to prevent the "Leaky Bucket" of memory decay.

State Machine

digraph learning_flow {
    "Domain Identified" [shape=doublecircle];
    "Metalearning: Map the Field" [shape=box];
    "Setup: Tools & Feedback" [shape=box];
    "Execution: 9 Principles" [shape=box];
    "Gate: Retention Check" [shape=diamond];
    "Mastery/Skill Acquisition" [shape=doublecircle];

    "Domain Identified" -> "Metalearning: Map the Field";
    "Metalearning: Map the Field" -> "Setup: Tools & Feedback";
    "Setup: Tools & Feedback" -> "Execution: 9 Principles";
    "Execution: 9 Principles" -> "Gate: Retention Check";
    "Gate: Retention Check" -> "Mastery/Skill Acquisition" [label="retained"];
    "Gate: Retention Check" -> "Execution: 9 Principles" [label="leaky bucket"];
}

When to Use This Skill

  • When onboarding into a complex new industry or technical role.
  • When preparing for a professional certification or competitive exam.
  • When you need to pick up a new language or software tool in under 90 days.
  • When traditional study methods feel slow, boring, or ineffective.

When NOT to Use This Skill

  • For leisure reading or hobbies where the goal is relaxation rather than performance.
  • When the skill is purely physical and requires a physical coach for safety (e.g., heavy weightlifting).

Core Process

Step 1: Metalearning (The 10% Rule)

Before starting, spend 10% of your estimated study time researching how the best in the field learned the skill. Map out:

  • Concepts: What do I need to understand?
  • Facts: What do I need to memorize?
  • Procedures: What do I need to do? (Source: Young, Ultralearning).

Step 2: Directness (The Transfer Fix)

Identify the environment where you will actually use the skill. Practice there. If you want to learn to code, build a project immediately. If you want to learn a language, speak to a person. Avoid "proxy" apps that offer a fake sense of progress (Source: Young, Ultralearning).

Step 3: Implement Spaced Retrieval

Do not review notes. Instead, use Active Recall:

  • The Feynman Technique: Explain a concept out loud as if to a child. Identify gaps in your explanation and go back to the source (Source: Oakley, A Mind For Numbers).
  • Making Smaller Circles: Reduce complex techniques to their smallest essential components and drill those components in isolation until they become automatic (Source: Waitzkin, The Art of Learning).
  • Spaced Repetition: Use an SRS (like Anki) to review facts at increasing intervals (Source: Matuschak).

Step 4: The Zettelkasten Method

Treat notes as a web of ideas, not a list.

  • Fleeting Notes: Quick captures of ideas.
  • Permanent Notes: Atomic, self-contained ideas written in your own words.
  • Linking: Connect new notes to existing ones to build a "Slip-box" of knowledge (Source: Ahrens, How to Take Smart Notes).

Step 5: Focused vs. Diffuse Mode

Switch between Focused Mode (intense concentration) and Diffuse Mode (letting the subconscious work while walking, showering, or sleeping). Problem-solving happens in the diffuse mode after the focused mode has "loaded" the data (Source: Oakley, A Mind For Numbers).

Cross-Skill Invocations

  • REQUIRED SUB-SKILL: writing-skills — To create the "failing tests" or challenges for your retrieval sessions.
  • RECOMMENDED SUB-SKILL: mental-model-library — To find analogies and structures that make new information easier to "chunk."

Rationalization Table

| Thought | Reality | |---------|---------| | "I'll read the book first, then practice." | Direct practice is the only way to identify what you actually need to learn. | | "Highlighting the important parts helps me remember." | Highlighting is passive and is statistically the least effective study method. | | "I don't have time for a full plan." | 1 hour of planning saves 10 hours of wandering through irrelevant material. | | "I'm just not a [Subject] person." | This is a fixed identity trap. Skills are acquired through iterative drills. |

Red Flags

  • "Illusion of Competence" → You recognize the information when you see it, but can't recall it from memory. (Action: Test yourself).
  • "The Leaky Bucket" → You learn 10 things today but forget them by next week. (Action: Implement Spaced Repetition).
  • "Procrastination via Research" → You are spending 50% of your time looking for better tools instead of studying. (Action: Limit research to the 10% rule).

Diagnostic Checklist

  • [ ] Have I spent 10% of my time on Metalearning (researching the "how")?
  • [ ] Is my primary practice Direct (using the skill in its real context)?
  • [ ] Am I using Active Recall (testing) instead of passive review?
  • [ ] Have I scheduled Spaced Repetition sessions for key facts?
  • [ ] Can I explain the core concept using the Feynman Technique?

Sources

  • Young, Scott. Ultralearning, Ch. 4 (Metalearning), Ch. 6 (Directness).
  • Ahrens, Sönke. How to Take Smart Notes, Ch. 2 (The Slip-box).
  • Oakley, Barbara. A Mind For Numbers, Ch. 3 (Chunking), Ch. 4 (Diffuse Mode).
  • Waitzkin, Josh. The Art of Learning, Ch. 11 (Making Smaller Circles).

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.