Enterprise AI-powered user expertise detection with behavioral analysis, communication pattern recognition, code complexity assessment, Context7 integration, and adaptive response calibration; activates for personalized guidance generation, complexity adjustment, tutorial depth selection, and communication style matching
Standardmäßig ist der Prompt ausgewählt, der zuerst die Quelle prüft. Sie können zu einem direkten Befehl wechseln oder eine lokale Kopie herunterladen.
Quelldateien prüfen
Lesen Sie SKILL.md und alle von SkillsMP angezeigten Begleitdateien, bevor Sie sich für eine Installation entscheiden.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Ein direkter Befehl überspringt den Prüf-Prompt. Prüfen Sie die Quelle, bevor Sie ihn ausführen.
Enterprise AI-powered user expertise detection with behavioral analysis, communication pattern recognition, code complexity assessment, Context7 integration, and adaptive response calibration; activates for personalized guidance generation, complexity adjustment, tutorial depth selection, and communication style matching
Continuously detects and adapts to user expertise level based on behavioral signals, communication patterns, code examples, and interaction history. Enables Alfred to calibrate complexity, example selection, and communication style dynamically.
Expertise Level Framework
Level 1: Beginner
Characteristics:
First interaction with tool/framework
Asks about basic concepts
Needs step-by-step guidance
Values examples and analogies
Detection Signals:
Questions about fundamentals ("What is a hook?")
Copy-paste behavior (not understanding code)
Struggles with terminology
Prefers verbose, explicit examples
First project in technology
Adaptation:
✓ Provide high-level analogies
✓ Explain concepts before showing code
✓ Include step-by-step examples
✓ Link to beginner tutorials
✓ Avoid advanced jargon
✓ Provide working examples
Level 2: Intermediate
Characteristics:
Understands fundamentals
Works with code confidently
Asks about patterns and best practices
Wants to improve and learn
Detection Signals:
Questions about patterns ("How should I structure this?")
Can read and understand code
Familiar with core concepts
Interested in optimization
Has completed several projects
Adaptation:
✓ Provide architectural guidance
✓ Explain trade-offs and decisions
✓ Show best practices and patterns
✓ Include edge cases
✓ Use technical terminology correctly
✓ Suggest optimizations
Level 3: Advanced
Characteristics:
Deep framework/language knowledge
Works with complex architectures
Asks about edge cases and optimization
Contributes to open source
Detection Signals:
Questions about performance ("How to optimize this?")
Writes complex code confidently
Familiar with framework internals
Interested in implementation details
Contributing to frameworks/libraries
Adaptation:
✓ Focus on nuanced details
✓ Discuss implementation trade-offs
✓ Reference RFC documents
✓ Show performance implications
✓ Discuss advanced patterns
✓ Link to source code
Level 4: Expert
Characteristics:
Framework/language maintainer or deep contributor
Authors best practices and patterns
Advises others on architecture
Contributes to language/framework development
Detection Signals:
Questions about specific implementation choices
Discusses language/framework internals
Suggests optimizations based on IL/bytecode
Participates in language design discussions
Adaptation:
✓ Assume deep knowledge
✓ Focus on bleeding-edge details
✓ Link to implementation source
✓ Discuss language design decisions
✓ No hand-holding required
Continuous Detection Signals
Signal 1: Terminology Usage
"How do I use useState?"
→ Beginner (basic concept)
"What's the best pattern for managing state?"
→ Intermediate (pattern awareness)
"How does React's useState closure capture work?"
→ Advanced (implementation detail)
"Can we optimize useState with useMemo patterns in concurrent rendering?"
→ Expert (deep architectural knowledge)
Signal 2: Code Complexity
# Beginner: Simple, linear logicdefgreet(name):
returnf"Hello, {name}!"# Intermediate: Using patternsclassUserService:
def__init__(self, repo):
self.repo = repo
defget_user(self, user_id):
returnself.repo.find(user_id)
# Advanced: Complex architectureasyncdefget_user_with_cache(user_id, cache, repo):
try:
cached = await cache.get(f"user:{user_id}")
if cached:
return json.loads(cached)
except CacheError:
pass
user = await repo.find(user_id)
await cache.set(f"user:{user_id}", json.dumps(user))
return user
# Expert: Framework internalsasyncdefget_user_with_prefetch(user_id, cache, repo, query_planner):
# Uses query optimization, connection pooling, prefetch logic
plan = query_planner.optimize(f"SELECT * FROM users WHERE id={user_id}")
# Custom execution with monitoring and fallback strategies
Signal 3: Question Type Patterns
"How do I...?" → Beginner
"What's the best way to...?" → Intermediate
"Why does X work like Y?" → Advanced
"How does the implementation..." → Expert
moai-alfred-practices (Pattern examples at all levels)
For detailed detection patterns: reference.md For real-world examples: examples.md Last Updated: 2025-11-12 Status: Production Ready (Enterprise v4.0.0)
