Loading...
Loading...
Found 197 Skills
Analyzes Perfetto traces to find the root cause of latency, memory, or jank issues in Android apps. Use when the user provides a Perfetto trace file and asks any question, ongoing investigation, or open-ended request to analyze its contents.
Expert in observing, benchmarking, and optimizing AI agents. Specializes in token usage tracking, latency analysis, and quality evaluation metrics. Use when optimizing agent costs, measuring performance, or implementing evals. Triggers include "agent performance", "token usage", "latency optimization", "eval", "agent metrics", "cost optimization", "agent benchmarking".
Benchmark a model served on MAX with the `max benchmark` command: measure throughput (tokens/sec), latency (TTFT, TPOT, inter-token latency), and GPU utilization by driving load against a running `max serve` endpoint. Use this whenever the user wants to benchmark, load-test, or measure the performance of a MAX model, get tokens-per-second / TTFT / TPOT numbers, run a concurrency or request-rate sweep, compare latency vs throughput, size a deployment, or produce benchmark JSON, even if they don't say "benchmark" by name. Also use when a `max benchmark` run fails to connect or reports zero/garbage numbers.
Identify, validate, and ship production-safe Node.js optimizations with execution time as the primary objective. Use when users ask to reduce latency (p50/p95/p99), improve throughput, and then reduce CPU/memory/event-loop lag/FD pressure or retry amplification, using one-PR-per-improvement workflows with benchmarks.
Debug MCP server communication. Use for troubleshooting MCP integrations, viewing traffic, and analyzing latency.
Performance optimization specialist for profiling, caching, and latency optimizationUse when "performance, latency, slow query, profiling, caching, optimization, N+1, connection pool, p99, performance, profiling, caching, latency, optimization, async, database, load-testing, ml-memory" mentioned.
Voice agents represent the frontier of AI interaction - humans speaking naturally with AI systems. The challenge isn't just speech recognition and synthesis, it's achieving natural conversation flow with sub-800ms latency while handling interruptions, background noise, and emotional nuance. This skill covers two architectures: speech-to-speech (OpenAI Realtime API, lowest latency, most natural) and pipeline (STT→LLM→TTS, more control, easier to debug). Key insight: latency is the constraint. Hu
The definitive skill for building and deploying high-performance, distributed systems using Cloud Native standards (Dapr, Redis, Microservices). Use when a project requires professional-grade architecture, cross-service communication, elastic scaling, and sub-second agentic latency. Mandatory for flawless deployments on Kubernetes (Local or Cloud).
Network Latency Tester - Auto-activating skill for Performance Testing. Triggers on: network latency tester, network latency tester Part of the Performance Testing skill category.
When throughput or latency is pipeline-limited, identify the single binding constraint and exploit, subordinate, elevate, then recheck—ignore non-constraints.
Identifies API latency hotspots and bottlenecks with profiling tools, slow endpoint detection, suspected causes, and fix roadmap. Use for "latency profiling", "performance bottlenecks", "slow APIs", or "backend performance".
Investigate Bedrock AgentCore runtime sessions via CloudWatch Logs Insights — resolve session/trace IDs, query OTEL spans, filter noise, build timelines. Use when debugging AgentCore agent sessions, tracing tool calls, or analyzing latency.