Results for “low latency”

Use this skill when the user is tuning a live or captured `doca-flow` pipeline with `doca_flow_tune` — snapshotting pipe / counter / KPI state, picking a tuning axis (rule placement, resource hints / table sizing, HW-offload mode) and a matching measurement (rule-install rate, lookup latency, hardware-counter delta), running offline or online (read-only or state-changing) modes, reading the dumper CSV / analyze JSON / visualize mermaid, or applying a recommendation back into the Flow program. Trigger even when the user does not explicitly mention "doca_flow_tune" — typical implicit phrasings include "Flow rule-install rate is low on BlueField", "table sizing looks wrong for this pipe", "tune visualize step is empty", "before/after counters don't move", or "which doca-flow knob does this recommendation hit". Refuse and route elsewhere for measuring baseline numbers (doca-flow-perf, doca-flow-dpa-perf), writing the doca-flow application, DOCA install, or streaming Flow telemetry — those belong to other skills.

The English summary is being prepared. Showing the original description.

Investigate Google Cloud network problems using traffic logs, performance metrics, and connection path tests. Identify blocked traffic, packet loss, and latency, summarize traffic volumes, or estimate VPC Flow Logs costs.

• Investigate blocked traffic and packet loss
• Check latency and throughput trends
• Analyze Cloud NAT port exhaustion

Use this skill when the user is measuring the host or DPU-CPU control-plane rate of a DOCA Flow pipeline with doca_flow_perf — picking a JSON policy from configs/, choosing the DPDK or DOCA backend, running the single-iteration smoke then the iterative eval loop, interpreting per-iteration CPU cycles and num_pushed / num_failed, or capturing the four-tuple (DOCA version, BlueField/firmware, JSON policy, worker/queue/burst config) that makes a Kops/sec number defensible. Trigger even when the user does not explicitly mention "doca-flow-perf" — typical implicit phrasings include "how many rules per second can my BlueField insert", "5-tuple hairpin rule rate", "Kops/sec for steering", "flow-perf number does not match release notes", "DPDK vs DOCA benchmark", or "rule-install variance too high". Refuse and route elsewhere for optimizing a live Flow app (doca-flow-tune), the DPA-offloaded path (doca-flow-dpa-perf), dataplane throughput or latency, or library-internal pipe semantics — those belong to other skills.

The English summary is being prepared. Showing the original description.

Improve the MCP server that connects claude-flow v3 to tools. It guides connection reuse, faster tool lookup, request distribution, and communication changes, with monitoring to evaluate response times, errors, memory use, and cache performance.

• Analyze slow MCP startup and tool responses
• Reuse connections and clean up idle ones
• Improve tool lookup and distribute requests

Improve the MCP server that connects claude-flow v3 to tools. It guides connection reuse, faster tool lookup, request distribution, and communication changes, with monitoring to evaluate response times, errors, memory use, and cache performance.

• Analyze slow MCP startup and tool responses
• Reuse connections and clean up idle ones
• Improve tool lookup and distribute requests

Investigate slow OpenClaw flows by counting operations and measuring performance. Use it to remove unnecessary work, evaluate whether caching is justified, and prepare or review performance changes with clear before-and-after evidence.

• Investigating slow startup or chat responses
• Reducing repeated SQL queries and file reads
• Reviewing performance changes with measurement evidence

Measure denoising latency in SGLang diffusion models and identify slow operations with profiler traces. Compare performance and output quality on the same GPUs, check existing optimizations, and gather evidence before starting low-level kernel work.

• Measuring diffusion denoising latency
• Ranking slow operations from profiler traces
• Checking whether existing optimizations address a bottleneck

Design systems where multiple AI agents share work, generate tool schemas that define tool inputs for Anthropic and OpenAI, and analyze execution logs. Outputs include role assignments, communication diagrams, and recommendations for addressing cost, latency, and failures.

• Designing agent roles for research automation
• Choosing how multiple agents coordinate work
• Generating and validating tool schemas

Investigate slow or failing requests in Google Cloud using Cloud Trace. Filter traces by duration or error status, inspect spans representing individual operations, and retrieve related Cloud Logging entries to investigate bottlenecks and exceptions.

• Find requests exceeding a latency threshold
• Inspect operation hierarchies within a trace
• Investigate failures using related application logs

ネットワーク品質を総合的に診断し、ボトルネックの特定と根本原因の深堀りまで行うスキル。 接続情報、レイテンシ、ダウンロード速度、HTTP接続タイミング、経路解析を自動実行し、 品質閾値に基づく総合評価を日本語レポートとして出力する。 外部依存なし（OS標準ツールのみ使用）、macOSおよびLinux対応。 Use when diagnosing network quality, troubleshooting slow connections, identifying network bottlenecks, measuring latency/bandwidth/jitter, or generating network health reports. 「ネットワーク診断」「network diagnostics」「ネットワークが遅い」 「latency check」「bandwidth test」「traceroute analysis」

The English summary is being prepared. Showing the original description.

Investigate performance bottlenecks in REA analysis workflows and improve caching, queries, or shared processing. Compare completed tasks before and after changes while preserving correct results, examined coverage, and access to supporting evidence.

• Investigating slow analysis workflows
• Reviewing cache keys and invalidation
• Reducing CPU and memory use

Review Caveman Cloud spending, latency, errors, and potential improvements using current reports and traces, or individual execution records. Produce findings tied to time windows and trace IDs, while keeping measured costs, estimated opportunities, and verified savings separate.

• Understanding which workflows drive LLM spending
• Investigating slow responses and errors
• Reviewing measured costs and verified savings separately

Plan voice AI systems by comparing direct speech processing with separate transcription, language generation, and speech synthesis stages. Covers response delays, detecting when people speak, interruptions, and noise handling to guide conversational interface design.

• Compare architectures for a voice AI system
• Review delays across conversation processing stages
• Design handling for interruptions during speech

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 English summary is being prepared. Showing the original description.

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".

The English summary is being prepared. Showing the original description.

Coordinate background tasks with specialized agents for research, optimization, audits, and more. Use execution history, quality scores, success rates, and latency to guide agent selection, track performance, and check benchmark compliance.

• Choose specialized agents for different task types
• Review agent quality, success rates, and latency
• Record execution feedback to inform future assignments

Build cryptocurrency exchange integrations in Rust with CCXT. Follow examples for fetching prices and order books, placing orders, streaming live updates through WebSocket connections, and handling authentication and errors with typed results.

• Fetching exchange prices and order books in Rust
• Building order placement and cancellation workflows
• Streaming live prices through WebSocket connections

Build search and recommendation features with Pinecone, a managed database for numerical representations of content. Covers data loading, combined meaning and keyword search, filtering by attributes, and separating data by user.

• Build document retrieval for AI answers
• Combine meaning and keyword search
• Separate search data by user

Configure LLM inference and serving on NVIDIA GPUs with TensorRT-LLM. Covers quantization, which reduces numerical precision, batching requests during generation, and distributing models across GPUs to improve processing capacity and response times.

• Setting up an LLM server on NVIDIA GPUs
• Configuring FP8 or INT4 quantization
• Distributing large models across multiple GPUs

Investigate cmux interface and runtime problems using debug logs, profiling, and the Debug menu. It guides changes to terminal rendering and tab lists, with checks for typing latency, SwiftUI state handling, and differences between macOS versions.

• Investigating focus and tab switching problems
• Checking typing latency after rendering changes
• Tuning layout and colors through Debug windows

Plan and troubleshoot large language and vision model training and inference. This guide uses hardware measurements to identify bottlenecks, address memory shortages and unstable training, and improve checkpointing, recovery, and performance across multiple GPUs and machines.

• Diagnosing slow training and GPU memory shortages
• Investigating loss spikes and invalid numerical values
• Debugging communication hangs across GPUs and machines

Configure LLM inference and serving on NVIDIA GPUs with TensorRT-LLM. Covers quantization, which reduces numerical precision, batching requests during generation, and distributing models across GPUs to improve processing capacity and response times.

• Setting up an LLM server on NVIDIA GPUs
• Configuring FP8 or INT4 quantization
• Distributing large models across multiple GPUs

Deploy language model APIs and run batch generation with vLLM. Configure GPU memory use, quantization—lower precision model storage—and distribution across GPUs, then test response times and monitor how many requests the server handles.

• Deploying an OpenAI-compatible language model API
• Generating responses for a large set of prompts
• Fitting a large model into limited GPU memory

Build search and recommendation features with Pinecone, a managed database for numerical representations of content. Covers data loading, combined meaning and keyword search, filtering by attributes, and separating data by user.

• Build document retrieval for AI answers
• Combine meaning and keyword search
• Separate search data by user