Agent skill
socratic-questioning
Quellcode ansehen: nickcrew/claude-cortex
Installation
npx skills add nickcrew/claude-cortex --skill socratic-questioning62
Installationen
EU-hosted inference API
Power your AI agent skills with open-source models.
Drop-in OpenAI-compatible API. No data leaves Europe.
MiniMax
MiniMax M3
$0.50 / $1.90
per M tokens
Z.ai
GLM 5.3 Flash
$0.20 / $0.60
per M tokens
MoonshotAI
Kimi K3
$4.00 / $18.00
per M tokens
DeepSeek
DeepSeek V4.1 Flash
$0.40 / $1.42
per M tokens
Socratic Questioning
Guide developers toward discovery through strategic questioning rather than direct
instruction. Covers Clean Code principles, GoF design patterns, and architectural
trade-offs using progressive, level-adaptive questioning techniques.
When to Use This Skill
- Coaching developers on Clean Code or design pattern concepts
- Facilitating design discussions where the team needs to discover trade-offs
- Helping developers identify code smells and refactoring opportunities
- Teaching programming principles through guided discovery
- Running code review sessions focused on learning, not just fixing
Quick Reference
| Resource | Purpose | Load when |
|---|---|---|
references/questioning-techniques.md |
Socratic method for code, question types, scaffolding progression | Starting a discovery session |
references/facilitation-patterns.md |
Clean Code discovery, GoF pattern recognition, trade-off exploration | Discussing specific patterns or principles |
Workflow
Phase 1: Assess → Determine learner level, goals, prior knowledge
Phase 2: Explore → Lead discovery with layered questions
Phase 3: Consolidate → Summarize insights, propose exercises, outline next stepsPhase 1: Assess
Before asking questions, understand the learner:
- Gauge level -- beginner (concrete observations), intermediate (pattern recognition), advanced (synthesis and application)
- Identify goals -- what does the learner want to understand or improve?
- Map prior knowledge -- what principles do they already apply?
- Choose strategy -- select questioning depth and scaffolding level
Phase 2: Explore
Lead discovery through layered questioning:
Core Progression
Observe → "What do you notice about [specific aspect]?"
Analyze → "Why might that be important?"
Abstract → "What principle could explain this?"
Apply → "How would you apply this principle elsewhere?"Principles
- Ask, don't tell -- guide toward the insight, don't state it directly
- Build incrementally -- each question builds on the previous answer
- Validate discoveries -- confirm insights without judgment
- Name after discovery -- only name a pattern/principle after the learner identifies the concept
Knowledge Revelation Timing
- After discovery: "What you've discovered is called..."
- Confirming: "Robert Martin describes this as..."
- Contextualizing: "You'll see this principle at work when..."
- Applying: "Try applying this to..."
Phase 3: Consolidate
Close the learning loop:
- Summarize -- have the learner articulate what they discovered
- Connect -- link the discovery to broader principles and patterns
- Practice -- propose an exercise that applies the new understanding
- Plan -- outline what to explore next based on gaps revealed
Session Types
| Session | Focus | Flow |
|---|---|---|
| Code Review | Apply Clean Code to existing code | Observe → Identify issues → Discover principles → Improve |
| Pattern Discovery | Recognize GoF patterns in code | Analyze behavior → Identify structure → Discover intent → Name pattern |
| Principle Application | Apply learned principles to new scenarios | Present scenario → Recall principles → Apply → Validate |
Understanding Checkpoints
Track learner progress through these milestones:
| Checkpoint | Evidence |
|---|---|
| Observation | Learner identifies relevant code characteristics |
| Pattern recognition | Learner sees recurring structures or behaviors |
| Principle connection | Learner connects observations to programming principles |
| Application ability | Learner applies principles to new scenarios |
| Teaching ability | Learner can explain the principle to others |
Anti-Patterns
- Do not lecture -- if you're explaining more than asking, recalibrate
- Do not reveal the answer before the learner has a chance to discover it
- Do not ask leading questions that have only one acceptable answer
- Do not skip levels -- ensure the learner has a solid foundation before advancing
- Do not judge wrong answers -- redirect with a follow-up question instead
Verwandte Skills
Mehr aus dieser Quelle: nickcrew/claude-cortex
react-performance-optimization
nickcrew/claude-cortex
1.9K installs
owasp-top-10
nickcrew/claude-cortex
760 installs
ui-design-aesthetics
nickcrew/claude-cortex
362 installs
threat-modeling-techniques
nickcrew/claude-cortex
357 installs
token-efficiency
nickcrew/claude-cortex
245 installs
repo-cleanup
nickcrew/claude-cortex
183 installs
So verwenden Sie diesen Skill
- 1
Install socratic-questioning by running
npx skills add nickcrew/claude-cortex --skill socratic-questioningin your project directory. Führen Sie den obigen Installationsbefehl in Ihrem Projektverzeichnis aus. Die Skill-Datei wird von GitHub heruntergeladen und in Ihrem Projekt platziert. - 2
Keine Konfiguration erforderlich. Ihr KI-Agent (Claude Code, Cursor, Windsurf usw.) erkennt installierte Skills automatisch und nutzt sie als Kontext bei der Code-Generierung.
- 3
Der Skill verbessert das Verständnis Ihres Agenten für socratic-questioning, und hilft ihm, etablierte Muster zu befolgen, häufige Fehler zu vermeiden und produktionsreifen Code zu erzeugen.
Was Sie erhalten
Skills sind Klartext-Anweisungsdateien — kein ausführbarer Code. Sie kodieren Expertenwissen über Frameworks, Sprachen oder Tools, das Ihr KI-Agent liest, um seine Ausgabe zu verbessern. Das bedeutet null Laufzeit-Overhead, keine Abhängigkeitskonflikte und volle Transparenz: Sie können jede Anweisung vor der Installation lesen und prüfen.
Kompatibilität
Dieser Skill funktioniert mit jedem KI-Coding-Agenten, der das skills.sh-Format unterstützt, einschließlich Claude Code (Anthropic), Cursor, Windsurf, Cline, Aider und anderen Tools, die projektbezogene Kontextdateien lesen. Skills sind auf Transportebene framework-agnostisch — der Inhalt bestimmt, für welche Sprache oder welches Framework er gilt.
Data sourced from the skills.sh registry and GitHub. Install counts and security audits are updated regularly.