connector

name	connector
description	Helps users rapidly learn any domain and build cross-domain knowledge connections, becoming a "T-shaped" generalist who can connect experts across fields. Use when users need to quickly understand a new field, find cross-domain connections, or build efficient learning paths.
triggers	["I want to quickly understand XX","Help me learn XX","What is XX","I want to enter the XX field","How to master XX quickly","Help me find connections between XX and other fields","I need to understand XX but don't have time"]
capabilities	["Rapid domain overview (30 minutes)","Cross-domain connection discovery","Personalized learning path generation","Expert conversation preparation","Knowledge archiving with spaced repetition"]

Connector Skill

Help users become connectors who can rapidly learn any domain and build cross-domain knowledge networks.

Core Philosophy: 5% Knowledge + 95% Connection = Unlimited Possibility

"Don't be a specialist. Be a connector."

The goal is NOT to become an expert, but to become someone who can understand any field quickly and connect it to what you already know.

Five Core Modules

1. Domain QuickScan (AI-Enhanced)

What: Get a complete cognitive map of any domain in 30 minutes.

Outputs:

• Domain landscape
• Concept tree
• Key terminology glossary
• Historical timeline
• Key players and thought leaders
• Common misconceptions

AI-assisted capabilities:

• Adaptive content synthesis: Based on user's prior knowledge, learning goals, and time constraints
• Intelligent knowledge graph generation: Automatically discovers core concepts and relationships
• Blind spot identification: Analyzes user's existing knowledge to find learning gaps
• Cognitive load optimization: Progressive information disclosure, chunked delivery
• Personalized examples: Tailors analogies to user's known domains

Student modeling:

• Tracks prior knowledge and learning patterns
• Builds a dynamic knowledge state model
• Adapts difficulty and pace in real-time
• Predicts potential learning difficulties

2. Connection Discovery (AI-Enhanced)

What: Find connections between the new domain and what you already know.

Outputs:

• Cross-domain analogies
• Transferable mental models
• Hidden shared principles
• Innovation opportunities

Core Belief:

• "Your cross-domain knowledge is your superpower"
• "Connections matter more than knowledge"

AI-assisted capabilities:

• Structure-mapping engine: Uses Gentner's theory to find deep structural similarities
• Analogy validation: Checks if analogies are valid and useful
• Connection prediction: Predicts potentially fruitful connections not yet explored
• Network analysis: Maps user's knowledge network and finds connection gaps
• Analogy generation: Creates multi-modal analogies (text, diagrams, metaphors)
• Transfer path optimization: Finds the best path from known to unknown

Mental model library integration:

• Semantic similarity matching
• Application pattern recognition
• Cross-domain principle transfer
• Innovation opportunity scanning

3. Rapid Mastery Path (AI-Enhanced)

What: Get a personalized "just enough" mastery path.

Different from traditional learning:

• NOT "become an expert" → "become someone who can have an intelligent conversation"
• NOT "learn all the basics" → "learn the most important 20% first"
• NOT "systematic study" → "just-in-time learning"

Outputs:

• Domain layer map (Surface / Middle / Deep)
• Prioritized learning path
• Key resource list (1-3 resources per topic)
• Time estimates
• Self-assessment checklist

AI-assisted capabilities:

• Adaptive path optimization: Uses reinforcement learning to optimize sequence
• Dynamic difficulty adjustment: Keeps challenges in "flow state" (Vygotsky's ZPD)
• Desirable difficulties design: Incorporates spaced practice, interleaving, and retrieval
• Progress prediction: Estimates time needed and tracks mastery
• Alternative paths: Generates multiple learning strategies
• Prerequisite analysis: Maps learning dependencies

Intelligent tutoring components:

• Student knowledge tracking (Bayesian Knowledge Tracing)
• Learning state modeling
• Misconception detection
• Personalized feedback generation
• Scaffolding strategy adaptation

4. Expert Talk Prep (AI-Enhanced)

What: Prepare to have effective conversations with domain experts.

Outputs:

• Must-know concepts
• Common terminology
• Right questions to ask
• Questions to avoid (that expose ignorance)
• Credibility-building talking points

Core Belief:

• "You don't need to be an expert, but you need to sound like you get it"
• "5% of the knowledge lets you ask 95% of the good questions"

AI-assisted capabilities:

• Curse-of-knowledge mitigation: Translates expert jargon to novice language
• Intelligent question generation: Based on research on effective expert conversations
• Conversation simulation: Pre-conversation practice with AI
• Credibility scoring: Assesses how prepared you sound
• Adaptation strategies: Helps you adapt based on expert's communication style
• Gap anticipation: Predicts what experts will ask you to test your understanding

Conversation support:

• Dynamic question bank generation
• Context-aware follow-up suggestions
• Social intelligence cues
• Active listening prompts

5. Knowledge Archive (AI-Enhanced)

What: Continuously build your cross-domain knowledge card system.

Outputs:

• Domain cards library
• Connection notes
• Curiosity queue
• Spaced repetition reminders

AI-assisted capabilities:

• Adaptive spaced repetition: Personalized review schedule based on memory strength modeling
• Intelligent card generation: Extracts key concepts from learning sessions automatically
• Knowledge graph maintenance: Suggests connections between new and existing knowledge
• Retrieval practice design: Generates active recall questions automatically
• Forgetting prediction: Estimates when knowledge needs review
• Learning analytics: Provides insights into learning patterns and optimizes learning strategy

Enhanced features:

• Auto-generation of test questions
• Difficulty progression tracking
• Knowledge decay modeling
• Connection reinforcement suggestions
• Mastery tracking dashboard

Usage Guide

When to Use

Trigger scenarios:

• User wants to quickly understand a new field
• User needs to evaluate whether to enter a domain
• User wants to find connections between fields
• User needs to prepare for expert conversations
• User wants to build systematic learning habits

How to Use

Quick Start (5 minutes):

User: "I want to quickly understand quantum computing"
AI: "Let's start your quantum computing overview journey.
     I'll generate for you:
     1. 30-minute domain landscape
     2. Connections to what you already know
     3. Minimum necessary knowledge path
     4. Expert conversation knowledge package

     Ready to begin?"

Full Workflow:

1. QuickScan (5 min) → Generate domain overview
2. Connection Discovery (10 min) → Find cross-domain links
3. Mastery Path (10 min) → Generate personalized learning path
4. Expert Prep (5 min) → Generate conversation package
5. Archive → Save to knowledge card system

Module-Specific Workflows

Domain QuickScan Workflow

1. Context Gathering (2 min)
   • Ask user's background and learning goals
   • Identify user's existing knowledge domains
   • Assess time constraints
2. Content Synthesis (3 min)
   • Generate concept tree with 3 layers
   • Create terminology glossary
   • Identify key players and misconceptions
3. Cognitive Load Optimization (ongoing)
   • Progressive disclosure of information
   • Chunk related concepts together
   • Use personalized analogies

Connection Discovery Workflow

1. Deep Structure Analysis (5 min)
   • Identify core principles in new domain
   • Compare with known domain structures
   • Find common underlying patterns
2. Analogy Generation (3 min)
   • Generate multiple cross-domain analogies
   • Validate structural similarity
   • Score and prioritize connections
3. Innovation Scanning (2 min)
   • Identify unique combination opportunities
   • Suggest novel applications
   • Highlight potential breakthroughs

Rapid Mastery Path Workflow

1. Goal Assessment (2 min)
   • Determine target mastery level (Surface/Middle/Deep)
   • Assess available time
   • Identify project context
2. Path Generation (5 min)
   • Create layered learning sequence
   • Insert desirable difficulties
   • Schedule spaced practice
3. Resource Matching (3 min)
   • Select 1-3 high-quality resources per topic
   • Match to user's learning style
   • Include practice exercises

Expert Talk Prep Workflow

1. Knowledge Translation (3 min)
   • Convert jargon to plain language
   • Create must-know concept cards
   • Build credibility talking points
2. Question Generation (2 min)
   • Create understanding questions
   • Generate insight questions
   • Prepare challenge questions
3. Simulation (optional, 5 min)
   • Practice conversation with AI
   • Get feedback on delivery
   • Refine talking points

Knowledge Archive Workflow

1. Card Generation (2 min)
   • Extract key concepts from session
   • Create active recall questions
   • Add connection notes
2. Schedule Planning (1 min)
   • Set initial review date (Day 1)
   • Schedule spaced repetition intervals
   • Link to existing knowledge cards
3. Analytics Update (ongoing)
   • Track review performance
   • Update mastery levels
   • Suggest reinforcement needs

Key Principles

Cognitive Load Management

• Work memory is limited (7±2 chunks)
• Provide structured knowledge compression
• Build high-level framework first, then details

Generation Effect

• Active generation > passive reading
• Ask users to recall and summarize
• Provide fill-in-the-blank learning

Spaced Repetition

• Combat forgetting with intervals
• "Desirable difficulties" for better long-term retention
• Progressive review schedules

Transfer Learning

• Look for deep structural similarities
• Cross-domain analogies as bridges
• Mental models enable transfer

Cognitive Science Foundation

This skill is built on research in cognitive science:

Theory	Key Insight	Application
Cognitive Load (Sweller, 1988)	Working memory is limited	Layered information delivery
Generation Effect (Slamecka & Graf, 1978)	Active > passive	Active recall exercises
Spaced Repetition (Ebbinghaus, 1885)	Forgetting curve	Review reminders
Situated Learning (Lave & Wenger, 1991)	Context matters	Real-world project scenarios
Transfer Learning (Thorndike, 1901)	Deep structure > surface	Cross-domain analogies
Metacognition (Flavell, 1979)	Know what you don't know	Self-assessment checklists
Desirable Difficulties (Bjork, 1994)	Moderate difficulty helps	Active learning design
Curse of Knowledge (Camerer et al., 1989)	Experts forget newbie view	Analogies & explanations

Complete literature review: LITERATURE-REVIEW.md

Formal execution document: EXECUTION-DOCUMENT.md

Workflow

User inputs domain
    ↓
[QuickScan] → Generate overview + core concepts
    ↓
[Connection Discovery] → Find links to existing knowledge
    ↓
[Mastery Path] → Generate personalized learning path
    ↓
[Expert Prep] → Generate conversation package
    ↓
[Archive] → Save to knowledge card system

Output Templates

Domain QuickScan Report

# [Domain] QuickScan Report

## One-Sentence Definition
[Explain in terms a non-expert would understand]

## Concept Tree

[Visual concept hierarchy]

## Key Terminology
| Term | Definition | Importance |
|------|------------|------------|
| ... | ... | ... |

## Connections to Your Knowledge
[Found connection points]

## Learning Path
- Surface (2 hours): ...
- Middle (1 day): ...
- Deep (1 week): ...

## Expert Conversation Package
[Must-know + good questions]

Integration with Other Skills

• With mental-models: Uses 45+ mental models as bridges for cross-domain connections
• With research-integration: Leverages research synthesis for rapid literature review
• With landing: Both emphasize first principles and quick validation

References

• Cognitive Science Foundations
• Rapid Learning Methods
• Domain Templates
• Connection Patterns
• AI-Assisted Learning Research

AI Learning Enhancement

This skill integrates research on AI-assisted learning and intelligent tutoring systems:

Research Area	Key Application
Intelligent Tutoring Systems	Personalized path optimization, scaffolding
Adaptive Learning	Dynamic difficulty adjustment
Student Modeling	Bayesian knowledge tracking
Learning Analytics	Progress prediction and optimization
Scaffolding Theory	Gradual support removal
Flow Theory	Optimal challenge design
Desirable Difficulties	Spaced practice, interleaving

Complete AI learning research: AI-ASSISTED-LEARNING-REVIEW.md

Philosophy

"Don't become a PhD in a field—become someone who can connect PhDs."

"Knowledge is cheap; connections are valuable."

"5% knowledge + 95% connections = infinite possibilities."

Notes

• Prioritize deep understanding of connections over breadth
• Encourage active recall over passive reading
• Build systematic review habits
• Celebrate cross-domain insights

---

Interface Definition

Metadata

{
  "name": "connector",
  "version": "2.0.0",
  "description": "Rapid domain learning and cross-domain knowledge connection builder",
  "author": "SOLO CORN SKILLS",
  "category": ["learning", "connection"],
  "tags": ["rapid-learning", "cross-domain", "knowledge-connection", "t-shaped"]
}

Input Schema

{
  "inputs": [
    {
      "name": "domain",
      "type": "string",
      "required": true,
      "description": "Domain or topic to learn about"
    },
    {
      "name": "goal",
      "type": "string",
      "required": false,
      "description": "Learning goal (overview, expert-prep, deep-dive)",
      "default": "overview"
    },
    {
      "name": "timeAvailable",
      "type": "string",
      "required": false,
      "description": "Time available for learning (30min, 2hr, 1day, etc)"
    }
  ]
}

Output Schema

{
  "outputs": [
    {
      "name": "quickscan",
      "type": "object",
      "description": "Domain quickscan report with concept tree"
    },
    {
      "name": "connections",
      "type": "array",
      "description": "Cross-domain connection discoveries"
    },
    {
      "name": "learningPath",
      "type": "object",
      "description": "Personalized learning path"
    },
    {
      "name": "expertPrep",
      "type": "object",
      "description": "Expert conversation preparation package"
    }
  ]
}

Invoke Method

async invoke(params: InvocationParams): Promise<SkillResult> {
  // Execute rapid learning workflow
  // 1. Domain QuickScan - generate overview and concept tree
  // 2. Connection Discovery - find cross-domain links
  // 3. Rapid Mastery Path - personalized learning sequence
  // 4. Expert Talk Prep - conversation preparation
  // 5. Return results
}

---

Usage via CLI

# Basic invocation
scs invoke connector --input '{"domain": "quantum computing"}'

# Interactive mode
scs invoke connector --interactive