measurement-analysis
Analyze web measurement data with Python/pandas/SQL. Use when user mentions 'analyze data', 'traffic analysis', 'statistics', 'pandas', 'SQL query', or 'plot results'.
wa-performance-review
Conduct a focused performance analysis based on the Well-Architected Framework Performance Efficiency pillar. Use when user says "performance review", "wa performance", or "check performance". Analyzes scalability, data access, caching, algorithm efficiency, network I/O, and resource management.
deep-research
Extended investigation for technology evaluation, competitive analysis, architectural exploration, and best practices research. Unlike spike (time-boxed hours), deep-research supports multi-day comprehensive investigation producing reports for major decisions. Triggers on "research X solutions", "compare frameworks for our use case", "evaluate vendors for X", "what are best practices for Y", "how do competitors handle Z", or any investigation requiring comprehensive analysis across multiple sources.
bezaleel-architect
Provides expert architectural analysis and strategic recommendations for software projects. Use for architecture reviews, system design evaluation, tech stack assessment, scalability/modernization strategy, or when asked to analyze a codebase architecturally. Produces consultant-style reports with prioritized recommendations — does NOT write implementation code.
root-cause-investigation
Systematic investigation of metric changes and anomalies. Use when a metric unexpectedly changes, investigating business metric drops, explaining performance variations, or drilling into aggregated metric drivers.
establishing-benchmark-baseline
[PHASE 1] Creates benchmark suite and performance expectations. Entry: No BENCHMARK_BASELINE.md exists. Outputs: BENCHMARK_BASELINE.md, benchmark files. Next: PHASE 2 (generating-performance-theories).
profiling-practices
Performance profiling best practices using py-spy and other Python profiling tools. Activated when profiling code, analyzing bottlenecks, or optimizing performance.
hydration-performance
Measure SSR hydration timing and issues. Use when tracking hydration performance, debugging hydration mismatches, or optimizing SSR/SSG applications.
performance-engineering
Systems-level performance engineering for Rust, C/C++, and Python codebases. Use when profiling, debugging performance bottlenecks, analyzing CPU/memory usage, finding slow code paths, optimizing hot loops, investigating cache misses, analyzing compile times, or improving runtime performance. Triggers on queries about flamegraphs, perf, valgrind, profilers, benchmarking, or "why is this slow".
performance
Apply performance optimization patterns for game loop, rendering, and state updates. Use when discussing frame rate, optimization, profiling, or when editing core game loop code. Auto-apply when user mentions "slow", "fps", "lag", or "performance".
android-motion-specialist
Expert Android developer for the Motion Detector project. Use this skill when working on Camera2 API integration, motion detection algorithms, Android networking (LAN sockets + Supabase Realtime), debugging crashes, or any Android/Kotlin development tasks specific to this sprint timing application.
screen-analyzer
Comprehensive React Native screen analysis tool that systematically extracts every feature, component, interaction, and detail from existing screens. Use BEFORE recreating ANY screen to ensure 100% feature parity. Triggers when user says "analyze screen", "analyze [filename]", "extract features from", or before screen recreation.
data-profiler
Profile datasets to understand schema, quality, and characteristics. Use when analyzing data files (CSV, JSON, Parquet), discovering dataset properties, assessing data quality, or when user mentions data profiling, schema detection, data analysis, or quality metrics. Provides basic and intermediate profiling including distributions, uniqueness, and pattern detection.
mobile-perf
Optimizes React Native Expo applications for speed, responsiveness, and battery efficiency. Use when fixing lag, optimizing lists, or reducing bundle size.
fitness-evaluation-logic
Use this skill when evaluating system performance and determining if optimizations are successful. This skill covers fitness functions, metric collection, and improvement validation.
performance
Performance & React Optimization Engineer that makes the app feel instant. Use when optimizing load times, fixing re-renders, or reviewing component efficiency.
interpret-curves
Analyze training logs and explain what's happening. Use when reviewing training runs, understanding loss curves, or diagnosing completed training.
debug-specialist
디버깅, 디버그, 버그, 에러, 오류, 버그 수정 - Specialized in identifying root causes of bugs, analyzing error logs, and providing robust fixes. Use this when the user reports an error, unexpected behavior, or needs performance troubleshooting.
ios-accessibility-audit
Audit iOS accessibility for screens and flows. Use to check Dynamic Type, VoiceOver, touch targets, contrast, focus order, and reduced motion (platform guidance, not implementation).
react-best-practices
Performance optimization guide for React and Next.js. Use when writing, reviewing, or refactoring React code, optimizing performance, or asking about React best practices.
responsive-design-planner
Plans responsive design breakpoints, mobile-first approaches, and adaptive layouts. Defines how designs adapt across different screen sizes and devices. Considers touch vs mouse interactions.
