Loading...
Loading...
Found 17 Skills
Profile CPU usage to identify hot spots and bottlenecks. Optimize code paths consuming most CPU time for better performance and resource efficiency.
Agent skill for performance-monitor - invoke with $agent-performance-monitor
Analyze story dependencies, detect issues, and generate visual dependency graphs
Analyze performance metrics and identify slow transactions in Sentry
Agent skill for performance-analyzer - invoke with $agent-performance-analyzer
Profile a target (script, process, GPU, memory, interconnect) using external tools and code instrumentation. Produces structured performance reports with actionable recommendations. Use when user says "profile", "benchmark", "bottleneck", or wants performance analysis.
Comprehensive performance analysis, bottleneck detection, and optimization recommendations for Claude Flow swarms
Correlates performance targets with actual profiling results. Identifies bottlenecks and validates against non-functional requirements.
Analyze code performance, detect bottlenecks, suggest optimizations for algorithms, queries, and resource usage. Use when improving application performance or investigating slow code.
Designs and implements state transition analysis systems for tracking time spent in different states. Use when analyzing workflows with state changes (Jira, GitHub PRs, deployments, support tickets, etc.). Covers state machine fundamentals, temporal calculations, bottleneck detection, and business metrics. Trigger keywords: "state analysis", "duration tracking", "workflow metrics", "bottleneck", "cycle time", "state transitions", "time in status", "how long", "state duration", "workflow performance", "state machine", "changelog analysis", "SLA tracking", "process metrics".
GPU kernel profiling workflow across supported kernel implementation languages. Provides commands for all 4 profiling modes (annotation, event, ncu, nsys), metric interpretation tables, bottleneck identification rules, and the output contract for returning compact results to the orchestrator. Use when: (1) profiling a kernel version, (2) interpreting profiling artifacts/reports, (3) comparing kernel versions, (4) identifying bottlenecks and optimization opportunities, (5) documenting performance in the development log.
Load tests API endpoints with progressive concurrency. Measures response times, error rates, throughput, and identifies breaking points. Generates a detailed report with latency percentiles, throughput curves, bottleneck analysis, and optimization recommendations.