333 skills · sorted by relevance
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.
Reduces LLM costs and improves response times through caching, model selection, batching, and prompt optimization. Provides cost breakdowns, latency hotspots, and configuration recommendations. Use for "cost reduction", "performance optimization", "latency improvement", or "efficiency".
The English summary is being prepared. Showing the original description.
Turn speedup requests into a measured optimization process with limits on time, cost, and variants. Compare each change against a baseline and correctness checks, then retain the fastest safe option with reproducible commands and measurements.
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.
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.
Tune vector indexes, which organize data for similarity searches, to balance speed, memory use, and missed matches. Choose index types, adjust HNSW settings, and assess compression options using benchmarks with real queries.
Set up monitoring for communication between services in Istio or Linkerd environments. Combine metrics, logs, and distributed traces, which follow requests across services, to investigate delays and errors, visualize dependencies, and define service quality targets.
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.
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.
Investigate stalled TPU training across multiple slices on GKE using hang reports, logs, and latency metrics. Separate compilation inconsistencies and data input stalls from hardware or network faults, and identify the relevant nodes for further investigation.
Create and validate Terraform alerts for GKE using PromQL, a monitoring query language. Cover response times, errors, traffic, memory usage, and cluster health, with checks for alert timing, duplicate signals, and metric ingestion costs.
Improve code, prompts, skills, or agent definitions through repeated changes and evaluation. Measure numerical targets such as latency or size, or use an LLM to judge pass-or-fail criteria, keeping changes that improve the result.
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.
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.
Reduce LLM generation delays with speculative decoding, which proposes tokens ahead of verification. This skill compares small draft models, Medusa, and Lookahead Decoding, with implementation examples, tuning guidance, and deployment using vLLM.
Set up monitoring for deployed agents to inspect execution paths, latency, and model interactions. It explains Cloud Trace, prompt and response logging, BigQuery analytics, and external monitoring integrations, with checks for missing data and unwanted content capture.
Use this skill when the user runs doca_dpa_hl_tracer to capture/decode DPA-side traces at the programming-events layer (kernel entry/exit, sync points, comm primitive calls, RDMA WR submission, completion drain) — picking TRACE vs CRIT, tuning the JSON config (file-size limits + file_size_limit_policy, thread priorities/cores), decoding against the matching DPA-side ELF, or diagnosing empty/noisy captures. Trigger even when the user does not explicitly mention "DOCA DPA tracer" or "high-level tracer" — typical implicit phrasings include "DPA kernel returns wrong result but host completions look clean", "kernel-entry to first-comm latency is huge", "RDMA WR to drain gap on the DPA", "trace file truncated mid-run", "TRACE doubled my DPA latency", or "tracer wrote a file but parser shows zero events". Refuse and route elsewhere for writing DPA kernels, DPA-Comms/DPA-Verbs programming, raw per-cycle DPA profiling, host-side doca-dpa debugging, or production DPA telemetry — those belong to other skills.
The English summary is being prepared. Showing the original description.
Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI service that detects whether operators perform assembly-line steps in order via event boundary detection (GEBD) plus VLM classification. Trigger even if the user does not name it: verify operator step sequence, detect missing or out-of-order SOP steps, score factory/work-cell video for procedure compliance, run VLM-based SOP checking on industrial cameras, or call /v1/chat/completions with a file, RTSP, or Basler camera. Also trigger for its internals: SOPVideoProcessor, DeepStream GEBD model (e.g. DDM) via Triton CAPI, nvds_custom_postprocess, Cosmos Reason 1/2 vLLM, SSE streaming, Kafka NvProto/JSON output, Basler/Pylon camera + emulation, Docker compose, chunk-level latency. Do NOT trigger for generic DeepStream pipelines, object detection/tracking, NIM imports, or video summarization.
The English summary is being prepared. Showing the original description.
[omh] Tracking cost, tokens, latency, or service health: prepare an operations command-board for wrapper-safe token, cost, latency, run history, queue, failure-mode, external metric-provider, and service-quality evidence boundaries. Use when the user says: ops-observability-card, observability card, operations command board, ops command board, service quality board, service quality, external metric provider, metric provider.
The English summary is being prepared. Showing the original description.
Activate when developers have latent caching needs: slow API responses, database read bottlenecks, DynamoDB throttling or cost, RDS/Aurora scaling pressure, Bedrock latency or cost, or adding a cache; activate when working with Redis, Valkey, Memcached, or any in-memory data store, cache-aside patterns, session stores, rate limiting, leaderboards, counters, streams, queues, pub/sub, distributed locks, feature flags, shopping carts, or other caching strategies. Activate for GenAI and ML retrieval: vector similarity search for low-latency retrieval, semantic caching, RAG, LLM response caching, embedding stores, AI agent memory, recommendation, personalization. Activate for ElastiCache lifecycle: provisioning (serverless or node-based), engine selection, CloudFormation/CDK/Terraform IaC, VPC connectivity, TLS, RBAC, IAM auth, Global Datastore, monitoring, troubleshooting, cost optimization, and migration from self-managed Redis. Do not trigger for browser caches, CDN/CloudFront, HTTP Cache-Control, CPU caches.
The English summary is being prepared. Showing the original description.
Analyze and tune AssemblyAI model choice, audio delivery, polling, Streaming v3 turns, concurrency, and downstream work. Use when pursuing measured latency or throughput goals. Trigger with "tune AssemblyAI" or "AssemblyAI latency".
The English summary is being prepared. Showing the original description.
Optimize Apollo.io API performance. Use when improving API response times, reducing latency, or optimizing bulk operations. Trigger with phrases like "apollo performance", "optimize apollo", "apollo slow", "apollo latency", "speed up apollo".
The English summary is being prepared. Showing the original description.
Optimize Claude API performance with prompt caching, model selection, streaming, and latency reduction techniques. Use when experiencing slow responses, optimizing token usage, or reducing time-to-first-token in production. Trigger with phrases like "anthropic performance", "claude speed", "optimize claude latency", "anthropic caching", "faster claude responses".
The English summary is being prepared. Showing the original description.
Analyze and optimize an Algolia search path using repository and production evidence instead of universal latency targets. Use when search feels slow, payloads are large, or rendering regresses. Trigger with "tune Algolia performance", "slow Algolia search", or "search latency".
The English summary is being prepared. Showing the original description.