skills/socratic-teaching-scaffolds/SKILL.md
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".
npx skillsauth add lyndonkl/claude socratic-teaching-scaffoldsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Core components:
Quick example (Teaching Recursion):
Question Ladder:
Misconception Detector:
Feynman Progression:
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 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. For complex topics with multiple misconceptions → Study resources/methodology.md.
Step 3: Guide discovery through questioning
Ask questions in sequence, provide scaffolding (hints, worked examples, analogies) as needed. See 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 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. Minimum standard: Average score ≥ 3.5.
1. Clarifying Questions (Understand current thinking)
2. Probing Assumptions (Surface hidden beliefs)
3. Probing Reasons/Evidence (Justify claims)
4. Exploring Implications (Think through consequences)
5. Questioning the Question (Meta-cognition)
6. Revealing Contradictions (Bust misconceptions)
Provide support that matches current need, then fade:
Level 5: Full Modeling (I do, you watch)
Level 4: Guided Practice (I do, you help)
Level 3: Coached Practice (You do, I help)
Level 2: Independent with Feedback (You do, I watch)
Level 1: Transfer (You teach someone else)
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.
Pattern 1: Concept Introduction (Concrete → Abstract)
Pattern 2: Misconception Correction (Prediction → Surprise → Explanation)
Pattern 3: Problem-Solving Strategy (Model → Practice → Reflect)
Pattern 4: Depth Ladder (ELI5 → Undergraduate → Expert)
Pattern 5: Discovery Learning (Puzzle → Hints → Insight)
Zone of proximal development:
Don't fish for specific answers:
Avoid pseudo-teaching:
Misconception resistance:
Expertise blind spots:
Individual differences:
Resources:
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
testing
Cluster a conference's event records into a small set of coarse themes with finer sub-clusters, an explicit outlier bucket, and soft (multi-membership) affinities — using the hybrid embed-then-label pipeline (embed abstracts, reduce, density-cluster, then LLM-label the clusters) when embedding libraries are available, and an LLM-reasoned hierarchical fallback when they are not. Embeddings do the grouping; the LLM only names the groups. Conference-agnostic. Use when turning structured event records into a navigable theme map for preference elicitation and scheduling, when you need 6-8 reasonable themes rather than 20 muddy ones, or when overlapping talks must belong to more than one theme. Trigger keywords - theme clustering, cluster talks, embed then label, soft membership, outlier talks, conference themes, topic map.
development
Build a personal conference schedule as a constraint-optimization problem — hard constraints (no time overlap, room-to-room travel time, capacity/registration, the attendee's own must-attends and blackouts) plus a user-owned weighted objective trading interest against breadth, pacing (maximize contiguous free time), and serendipity. Surfaces unbreakable conflicts (two high-value overlapping talks the model cannot rank) as decisions for the human rather than silently picking, and reports what each choice traded away. Conference-agnostic. Use to turn a preference profile plus a theme map into a day-by-day plan, to resolve overlapping sessions, or to balance a packed vs paced schedule. Trigger keywords - schedule optimization, conference schedule, constraint optimization, overlapping talks, contiguous free time, conflict surfacing, packed vs paced.
development
Parse a heterogeneous conference program (markdown, HTML, PDF-derived text, or JSON) into normalized event records with per-field confidence scores and independent classification axes (topic, depth, format, prerequisites, recorded, capacity). Detects the program's format before extracting, treats every inferred field as uncertain (present vs inferred vs missing), and flags thin or missing abstracts so downstream enrichment can target them. Conference-agnostic. Use when ingesting a conference or event schedule into a structured store, normalizing a talk/session list, or extracting per-session metadata with calibrated confidence. Trigger keywords - program ingestion, parse schedule, session extraction, event records, conference program, talk metadata, per-field confidence.
development
Build a personalized preference profile from a small number of well-chosen, cluster-grounded questions instead of a long survey. Represents the person's interests as an uncertainty region over the theme map, picks the single highest-information-gain choice-based question (contrasting real talks from different clusters), balances exploiting known interests against exploring uncertain ones, deliberately injects outlier probes to fight selection bias, and stops as soon as the schedule would be stable. Also elicits the user-owned objective weights and hard constraints. Interactive — runs where it can actually ask the person. Conference-agnostic. Use to turn a theme map into a preference profile, to decide what to ask a conference attendee, or to elicit scheduling priorities. Trigger keywords - preference elicitation, ask few questions, information gain, choice-based questions, selection bias probe, objective weights, attendee preferences.