socratic-teaching-scaffolds
$
npx mdskill add lyndonkl/claude/socratic-teaching-scaffoldsGuide learners through discovery using Socratic questioning and scaffolding.
- Enables complex concept teaching and misconception correction.
- Depends on natural language understanding to detect learning intent.
- Decides actions by matching keywords like teach me or explain like I'm.
- Delivers progressive scaffolding through question ladders and fading examples.
SKILL.md
.github/skills/socratic-teaching-scaffoldsView on GitHub ↗
--- name: socratic-teaching-scaffolds description: Guides learners to discover knowledge through strategic Socratic questioning and progressive scaffolding removal. Combines question ladders, misconception detectors, Feynman explanations, and worked-example fading to build durable understanding. Use when teaching complex concepts, correcting misconceptions, onboarding team members, mentoring problem-solving, or designing self-paced learning. Use when user mentions "teach me", "help me understand", "explain like I'm", "learning path", "guided discovery", or "Socratic method". --- # Socratic Teaching Scaffolds ## Table of Contents 1. [Workflow](#workflow) 2. [Socratic Question Types](#socratic-question-types) 3. [Scaffolding Levels](#scaffolding-levels) 4. [Common Patterns](#common-patterns) 5. [Guardrails](#guardrails) 6. [Quick Reference](#quick-reference) **Core components:** 1. **Question Ladders**: Sequences from simple to complex that build understanding incrementally 2. **Misconception Detectors**: Questions that reveal faulty mental models through contradiction 3. **Feynman Explanations**: Build-up from simple analogies to technical precision 4. **Worked Examples with Fading**: Full solutions → partial solutions → independent practice 5. **Cognitive Apprenticeship**: Model thinking process explicitly, then transfer to learner **Quick example (Teaching Recursion):** **Question Ladder:** 1. "Can you break this problem into a smaller version of itself?" (problem decomposition) 2. "What would happen if we had only one item?" (base case discovery) 3. "If we could solve the small version, how would we use it for the big version?" (recursive case) 4. "What prevents this from running forever?" (termination reasoning) **Misconception Detector:** - "Will this recursion ever stop? Trace it with 3 items." (reveals infinite recursion misunderstanding) **Feynman Progression:** - Level 1: "Like Russian nesting dolls--each contains a smaller version" - Level 2: "Function calls itself with simpler input until base case" - Level 3: "Recursive definition: f(n) = g(f(n-1), n) with f(0) = base" ## Workflow Copy this checklist and track your progress: ``` Socratic Teaching Progress: - [ ] Step 1: Diagnose learner's current understanding - [ ] Step 2: Design question ladder and scaffolding plan - [ ] Step 3: Guide discovery through questioning - [ ] Step 4: Fade scaffolding as competence grows - [ ] Step 5: Validate understanding and transfer ``` **Step 1: Diagnose learner's current understanding** Ask probing questions to identify current knowledge level, misconceptions, and learning goals. See [Socratic Question Types](#socratic-question-types) for diagnostic question categories. **Step 2: Design question ladder and scaffolding plan** Build progression from learner's current state to target understanding. For straightforward teaching → Use [resources/template.md](resources/template.md). For complex topics with multiple misconceptions → Study [resources/methodology.md](resources/methodology.md). **Step 3: Guide discovery through questioning** Ask questions in sequence, provide scaffolding (hints, worked examples, analogies) as needed. See [Scaffolding Levels](#scaffolding-levels) for support gradations. Adjust based on learner responses. **Step 4: Fade scaffolding as competence grows** Progressively remove hints, provide less complete examples, ask more open-ended questions. Monitor for struggle (optimal challenge) vs frustration (too hard). See [resources/methodology.md](resources/methodology.md) for fading strategies. **Step 5: Validate understanding and transfer** Test with novel problems, ask for explanations in learner's words, check for misconception elimination. Self-check using [resources/evaluators/rubric_socratic_teaching_scaffolds.json](resources/evaluators/rubric_socratic_teaching_scaffolds.json). Minimum standard: Average score ≥ 3.5. ## Socratic Question Types **1. Clarifying Questions** (Understand current thinking) - "What do you mean by [term]?" - "Can you give me an example?" - "How does this relate to [known concept]?" **2. Probing Assumptions** (Surface hidden beliefs) - "What are we assuming here?" - "Why would that be true?" - "Is that always the case?" **3. Probing Reasons/Evidence** (Justify claims) - "Why do you think that?" - "What evidence supports that?" - "How would we test that?" **4. Exploring Implications** (Think through consequences) - "What would happen if [change]?" - "What follows from that?" - "What are the edge cases?" **5. Questioning the Question** (Meta-cognition) - "Why is this question important?" - "What are we really trying to understand?" - "How would we know if we understood?" **6. Revealing Contradictions** (Bust misconceptions) - "Earlier you said [X], but now [Y]. How do these fit?" - "If that's true, why does [counterexample] happen?" - "What would this predict for [test case]?" ## Scaffolding Levels Provide support that matches current need, then fade: **Level 5: Full Modeling** (I do, you watch) - Complete worked example with thinking aloud - Explicit strategy articulation - All steps shown with rationale **Level 4: Guided Practice** (I do, you help) - Partial worked example - Ask learner to complete steps - Provide hints before errors **Level 3: Coached Practice** (You do, I help) - Learner attempts independently - Intervene with questions when stuck - Guide without giving answers **Level 2: Independent with Feedback** (You do, I watch) - Learner solves alone - Review and discuss afterwards - Identify gaps for next iteration **Level 1: Transfer** (You teach someone else) - Learner explains to others - Learner creates examples - Learner identifies misconceptions in others **Fading strategy:** Start at level matching current competence (not Level 5 by default). Move down one level when learner demonstrates success. Move up one level if learner struggles repeatedly. ## Common Patterns **Pattern 1: Concept Introduction (Concrete → Abstract)** - Start: Real-world analogy or example - Middle: Formalize with terminology - End: Abstract definition with edge cases - Example: Teaching pointers (address on envelope → memory location → pointer arithmetic) **Pattern 2: Misconception Correction (Prediction → Surprise → Explanation)** - Ask learner to predict outcome - Show actual result (contradicts misconception) - Guide discovery of correct mental model - Example: "Will this float? [test with 0.1 + 0.2 in programming] Why not exactly 0.3?" **Pattern 3: Problem-Solving Strategy (Model → Practice → Reflect)** - Model strategy on simple problem (think aloud) - Learner applies to similar problem (with coaching) - Reflect on when strategy applies/fails - Example: Teaching debugging (print statements → breakpoints → hypothesis testing) **Pattern 4: Depth Ladder (ELI5 → Undergraduate → Expert)** - Build multiple explanations at different depths - Let learner choose starting point - Provide "go deeper" option at each level - Example: Teaching neural networks (pattern matching → weighted sums → backpropagation → optimization theory) **Pattern 5: Discovery Learning (Puzzle → Hints → Insight)** - Present puzzling phenomenon or problem - Provide graduated hints if stuck - Guide to "aha" moment of discovery - Example: Teaching recursion (Towers of Hanoi → break into subproblems → recursive solution) ## Guardrails **Zone of proximal development:** - Too easy = boredom, too hard = frustration - Optimal: Can't do alone, but can with guidance - Adjust scaffolding level based on struggle signals **Don't fish for specific answers:** - Socratic questioning isn't a guessing game - If learner's reasoning is sound but reaches different conclusion, explore their path - Multiple valid approaches often exist **Avoid pseudo-teaching:** - Don't just ask questions without purpose - Each question should advance understanding or reveal misconception - If question doesn't help, provide direct explanation **Misconception resistance:** - Deep misconceptions resist single corrections - Need multiple exposures to contradictions - May require building correct model from scratch before dismantling wrong one **Expertise blind spots:** - Experts forget what was hard as beginners - Make implicit knowledge explicit - Slow down automated processes to show thinking **Individual differences:** - Some learners prefer exploration, others prefer structure - Adjust scaffolding style to learner preferences - Monitor for frustration vs productive struggle ## Quick Reference **Resources:** - **Quick teaching session**: [resources/template.md](resources/template.md) - **Complex topics/misconceptions**: [resources/methodology.md](resources/methodology.md) - **Quality rubric**: [resources/evaluators/rubric_socratic_teaching_scaffolds.json](resources/evaluators/rubric_socratic_teaching_scaffolds.json) **5-Step Process**: Diagnose → Design Ladder → Guide Discovery → Fade Scaffolding → Validate Transfer **Question Types**: Clarifying, Probing Assumptions, Probing Evidence, Exploring Implications, Meta-cognition, Revealing Contradictions **Scaffolding Levels**: Full Modeling → Guided Practice → Coached Practice → Independent Feedback → Transfer (fade progressively) **Patterns**: Concrete→Abstract, Prediction→Surprise→Explanation, Model→Practice→Reflect, ELI5→Expert, Puzzle→Hints→Insight **Guardrails**: Zone of proximal development, purposeful questions, avoid pseudo-teaching, resist misconceptions, make implicit explicit
More from lyndonkl/claude
- abstraction-concrete-examplesBuilds structured abstraction ladders that translate high-level principles into concrete, actionable examples across 3-5 levels. Bridges communication gaps, reveals hidden assumptions, and tests whether abstract ideas work in practice. Use when explaining concepts at different expertise levels, moving between abstract principles and concrete implementation, identifying edge cases by testing ideas against scenarios, designing layered documentation, decomposing complex problems into actionable steps, or bridging strategy-execution gaps.
- academic-letter-architectGuides the creation of evidence-based academic recommendation letters, reference letters, and award nominations that combine concrete examples, meaningful comparisons, and genuine enthusiasm. Use when writing recommendation letters for students, postdocs, or colleagues, or when user mentions recommendation letter, reference, nomination, letter of support, endorsement, or needs help with strong advocacy and comparative statements.
- adr-architectureDocuments significant architectural and technical decisions with full context, alternatives considered, trade-offs analyzed, and consequences understood. Creates a decision trail that helps teams understand why decisions were made. Use when choosing between technology options, making infrastructure decisions, establishing standards, migrating systems, or when user mentions ADR, architecture decision, technical decision record, or decision documentation.
- adverse-selection-priorProduces a Bayesian prior probability that an offered transaction is +EV for the recipient, given that the counterparty chose to propose it. Applies Akerlof market-for-lemons logic -- if they offered it, they believe it is +EV for them, so the prior that it is +EV for us is materially below 50%. Reusable across trade evaluation, waiver drops (another team dropping a player is also adverse selection), job-offer analysis, M&A, and any "someone offered me this" situation. Use when you receive an unsolicited trade/offer/proposal, analyzing incoming trade prior, evaluating why a counterparty proposed a deal, or when user mentions adverse selection, market for lemons, why did they offer this, incoming trade prior, they proposed it, Bayesian adjustment on received offer.
- alignment-values-north-starCreates actionable alignment frameworks that give teams a shared North Star (direction), values (guardrails), and decision tenets (behavioral standards). Enables autonomous decision-making while maintaining organizational coherence. Use when starting new teams, scaling organizations, defining culture, establishing product vision, resolving misalignment, creating strategic clarity, or when user mentions North Star, team values, mission, principles, guardrails, decision framework, or cultural alignment.
- analogy-weight-checkFor every analogy in a substacker draft, verifies it carries mechanical weight — the analogy does real work explaining the mechanism, not merely decorates it. Cross-references analogy-catalog.md for novelty (is this analogy reused from a prior post?) and domain fit (biology > organizational > sports preferred; physics/military disfavored). Use whenever an analogy appears in the draft. Trigger keywords: analogy weight, decorative, mechanical weight, reused analogy, catalog check, metaphor check.
- answer-uncomfortable-questionTakes one strategic question about substacker ("should we launch paid?", "is this section dead?", "are we writing for the wrong audience?") and produces the mandatory evidence + reasoning + downside triad plus a recommendation. Used 3 times per Growth Strategist review. Trigger keywords: uncomfortable question, strategic question, evidence reasoning downside, triad.
- attribute-performanceFor each substacker post that materially over- or under-performs the rolling baseline (|z| ≥ 1.0), produces a plain-English attribution paragraph with calibrated confidence (high / medium / low / unexplained). Considers subject-line effect, topic zeitgeist, external share, day-of-week, length effect, and audience-notes signals. Labels unexplained outliers explicitly rather than fabricating a story. Use after compute-baseline when outlier posts exist. Trigger keywords: attribution, why did this post work, outlier explanation, performance analysis.
- auction-first-price-shadingComputes the optimal shaded bid for a first-price sealed-bid auction given a true private value, an estimate of the number of competing bidders N, and a value-distribution assumption. Implements the `(N-1)/N` equilibrium shading rule for uniform private values, adjusts for log-normal or empirical value distributions, layers a risk-aversion adjustment, and caps output against the bidder's remaining budget. Domain-neutral auction theory reusable across fantasy sports (baseball FAAB, NBA/NHL waiver auctions), prediction-market limit sizing, sealed procurement bids, and any blind-bid context. Use when user mentions "first-price auction bid", "sealed bid shading", "(N-1)/N", "FAAB bid amount", "auction shading", "optimal bid first-price", "bid for sealed-bid", "blind bid sizing", or when downstream logic needs a principled shade factor rather than an ad-hoc heuristic.
- auction-winners-curse-haircutApplies a Bayesian haircut to a bid valuation for common-value auctions where winning is itself evidence the bidder over-estimated. Takes a raw valuation, a value-type classification (common_value / private_value / mixed), the number of informed bidders N, and a signal-dispersion estimate, and returns an adjusted valuation. Domain-neutral and reusable across fantasy FAAB, prediction markets, M&A bids, ad-auction budgets, and any generic bidding context. Use when user mentions "winner's curse", "common value auction", "valuation haircut", "adverse valuation", "Bayesian bid adjustment", or "over-paying in auction".