debug-deep
Tree-of-thoughts reasoning for elusive, intermittent bugs. Use when standard debugging fails or the bug is hard to reproduce.
Tree-of-thoughts reasoning for elusive, intermittent bugs. Use when standard debugging fails or the bug is hard to reproduce.
Expert UX review and analysis of web applications with 10+ years of professional experience in SaaS, enterprise systems, and complex interfaces. Use when user requests UX feedback, web app review, or interface analysis. Triggers include "Give me UX feedback on this page", "Review this web app", "Analyze the UX of [URL]", or similar requests. Provides systematic analysis covering usability, accessibility, information architecture, and interaction design. Works with both live URLs and screenshots.
Track website and app analytics with Google Analytics 4's comprehensive platform.
Analiza el estilo de escritura del usuario y genera un perfil con metricas y ejemplos citados.
Reviews panel visual appeal and layout quality for LCDPossible LCD displays. Use when: validating panel layout, checking visual quality, reviewing panel design, ensuring style compliance, auditing panel appearance, fixing layout issues. Analyzes HTML/CSS and screenshots against visual appeal rules.
GA4 event tracking patterns and taxonomy. Use when: implementing analytics, tracking user events, e-commerce tracking. Do not use for: general performance optimization (use performance-patterns skill). Workflow: Set up after core features are built.
Specialized agent for auditing and optimizing Next.js applications for Core Web Vitals, SEO, and performance. Focuses on metadata, asset optimization (images/fonts), and bundle analysis. Trigger: "Optimize Next.js", "Next.js SEO", "Improve performance", "Core Web Vitals", "Lighthouse check", "Reduce bundle size".
Run accessibility and SEO audits in cloud sandboxes, generate remediation specs, and implement fixes. Use when optimizing a website for accessibility (a11y, WCAG) or SEO, or when the user says "optimize", "audit", or "fix accessibility issues".
Analyzes performance benchmarks from CUDA, CPU, memory tests. Parses output, identifies bottlenecks, tracks metrics over time, generates optimization insights.
[PHASE 3] Proves theories with profiling tools. Entry: PERFORMANCE_THEORIES.md has unverified theories. Outputs: Theory marked verified/falsified. Next: PHASE 4 (implementing-performance-fixes) when one theory is verified.
Collects, analyzes, and reports software metrics for data-driven decision making and continuous improvement
Compare local codebase capabilities against competitor products by researching competitor features via web search and documentation, analyzing local code patterns, and generating an interactive HTML comparison report.
Performance monitoring and optimization. Use when user needs N+1 detection, slow query analysis, memory profiling, or says "performance issue", "slow queries", "N+1 problem", "optimize performance", "memory leak".
Provides quantitative rubrics and criteria for scoring code quality on a 1-10 scale. Use when reviewing code, performing code audits, establishing quality baselines, comparing implementations, or providing objective code feedback.
[31] ANALYZE. Universal deep thinking methodology for any situation requiring quality reasoning. Use when solving problems, debugging, making decisions, analyzing code, planning, reviewing, or anytime you need thorough thinking instead of surface-level responses. Triggers on "think deeply", "analyze thoroughly", "reason carefully", "deep thinking", "understand completely", or any task requiring careful thought.
An internal cognitive engine for quantitative root cause analysis. Use this autonomously when you need to weigh competing hypotheses, prevent anchoring bias, or determine the most efficient next diagnostic step.
Diagnose ClickHouse INSERT performance, batch sizing, part creation patterns, and ingestion bottlenecks. Use for slow inserts and data pipeline issues.
Analyze and improve database performance through safe, measurable query, index, and configuration optimizations.
Analyze code performance, detect bottlenecks, suggest optimizations for algorithms, queries, and resource usage. Use when improving application performance or investigating slow code.
Diagnose ClickHouse disk usage, compression efficiency, part sizes, and storage bottlenecks. Use for disk space issues and slow IO.
Optimizes Grafana Jsonnet dashboard content for observability and SRE best practices (RED/USE/Golden Signals). Use when auditing dashboard quality, improving monitoring effectiveness, enhancing diagnostic capabilities, or reviewing observability coverage. Focuses on content-level improvements without code structure refactoring.
Comprehensive health audit for design documentation. Use when performing thorough quality checks, preparing for releases, or ensuring documentation compliance.