366 skills · sorted by relevance
Switch the vision-language model, which handles images and text, in VSS Alerts Blueprint. Configure alert generation, verification, and agent queries separately, choose an external endpoint or bundled vLLM deployment, and verify an actual inference response.
Choose containers and Python package sources that match a Jetson device's GPU architecture, JetPack, and CUDA environment. Get compatibility hints for PyTorch, vLLM, and related stacks before installation, using NVIDIA catalogs and Jetson AI Lab indexes.
LLM agent 基础设施 (LLM agent infra) Master OS — automated mastery of LLM agent infra: top builders' mental models, tool stack, current workflows, jargon, and where to keep up. Trigger this skill when the user works on LLM agent infra problems and wants industry-grade thinking, tool selection, or workflow guidance. 触发词：「agent framework」「LLM agent」「agent infra」「multi-agent orchestration」「agent runtime」
The English summary is being prepared. Showing the original description.
Develop incident response procedures for LLM outages, declining answer quality, spending spikes, and unsafe outputs. Use example monitoring alerts, severity levels, recovery playbooks, and postmortem guidance to organize detection, response, and follow-up work.
Design scheduled AI workflows for document ingestion, batch processing, and model training using Prefect, Airflow, or Dagster. Compare orchestration tools and plan task dependencies, retries, caching, and monitoring through implementation fragments.
Guides setup and operation of Lambda Labs GPU instances for machine learning training and inference. Covers SSH access, persistent storage, API automation, and multi-GPU or multi-node training, including how to retain checkpoints and terminate idle instances.
Deploy AI models on GKE with suitable GPUs or TPUs and model servers. Generate deployment configuration, adjust automatic scaling, and tune inference—the process of producing model responses—for memory use, throughput, and response time.
Build repeatable DeepEval tests for AI agents, chatbots, and applications that retrieve documents to answer questions. Reuse or generate evaluation datasets, inspect failures, and improve prompts, tools, or retrieval through repeated evaluation runs.
Guides setup and operation of Lambda Labs GPU instances for machine learning training and inference. Covers SSH access, persistent storage, API automation, and multi-GPU or multi-node training, including how to retain checkpoints and terminate idle instances.
Deploy and manage vLLM for high-throughput LLM inference. Configure continuous batching, tensor parallelism, quantization, and OpenAI-compatible API endpoints for production LLM serving.
The English summary is being prepared. Showing the original description.
Build production LLMOps platforms with CI/CD, model promotion workflows, evaluation gates, rollback, and governance across cloud and self-hosted inference.
The English summary is being prepared. Showing the original description.
LLM and AI application security testing — prompt injection, jailbreak resistance, OWASP LLM Top 10 (2025), RAG and agent/tool-use security, model supply chain, and AI red teaming for authorized assessments
The English summary is being prepared. Showing the original description.
Redpanda's Agentic Data Plane: governance infrastructure for building, running, and governing AI agents and MCP servers, plus a proxying AI Gateway for LLM providers, operated via `rpk ai` and the ADP API. Use when creating or managing AI agents (managed or self-managed) via `rpk ai agent` or `AgentRegistryService`; configuring MCP servers (remote or managed catalog, code mode, auth); setting up LLM providers or querying models via `rpk ai llm`/`rpk ai model` or the AI Gateway proxy; or configuring budgets, guardrails, or Cedar access-control policies through the governance APIs. Also covers reading agent transcripts and spending insights, and wiring OAuth clients or providers to the aigw Authorization Server. For the separate rpk cloud mcp control-plane MCP server, see `/redpanda:rpk-cloud`.
The English summary is being prepared. Showing the original description.
Expert guide for AI FinOps, dynamic model routing (LiteLLM, Portkey, RouteLLM), cost optimization, budget enforcement, semantic caching, and latency-based fallback architectures / Panduan ahli untuk AI FinOps, routing model dinamis, optimasi biaya, penegakan anggaran, semantic caching, dan arsitektur fallback berbasis latensi.
The English summary is being prepared. Showing the original description.
LLMOps Architect: Run LLM features in production: model routing, evals, observability, caching, cost, safety.
The English summary is being prepared. Showing the original description.
Pick the right serving container for a SageMaker model deployment and find its current image URI. Use this skill whenever about to deploy a model to a SageMaker endpoint and an image URI needs to be chosen — including when the user says "deploy this LLM", "host this HuggingFace model", "serve this fine-tuned model", "deploy this embedding model", "host a reranker", "serve a sentence-transformers model", or when about to hardcode any container URI in deployment code. HuggingFace-curated Deep Learning Containers are ALWAYS preferred: HuggingFace vLLM (LLMs and generative rerankers), HuggingFace vLLM-Omni (multimodal), TEI (embeddings/cross-encoder rerankers), HF Inference Toolkit (other transformers). Generic images (AWS vLLM, DJL-LMI, SGLang) are used only when no HuggingFace image is compatible — never merely because they carry a newer version. Never hardcode a container URI from memory and never default to TGI. Prevents stale-image failures and wrong-region URIs.
The English summary is being prepared. Showing the original description.
Expert in Langfuse - the open-source LLM observability platform. Covers tracing, prompt management, evaluation, datasets, and integration with LangChain, LlamaIndex, and OpenAI. Essential for debugging, monitoring, and improving LLM applications in production. Use when: langfuse, llm observability, llm tracing, prompt management, llm evaluation.
The English summary is being prepared. Showing the original description.
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.
The English summary is being prepared. Showing the original description.
Expert in Langfuse - the open-source LLM observability platform. Covers tracing, prompt management, evaluation, datasets, and integration with LangChain, LlamaIndex, and OpenAI. Essential for debugging, monitoring, and improving LLM applications in production. Use when: langfuse, llm observability, llm tracing, prompt management, llm evaluation.
The English summary is being prepared. Showing the original description.
Look up Ant Design React components in official documentation to find available settings, default values, and usage examples. Check subcomponents and methods, and consult type definitions in the antd package when TypeScript details are needed.
Builds an Apigee proxy that inspects an agent’s model requests and responses through Google Cloud Agent Gateway. It measures token usage by model, identifies callers, and can add prompt screening or a cache for similar prompts.
Guides iterative improvement of AI agent prompts, skills, and memory using A-Evolve. It explains how to evaluate agents against benchmark tasks, apply changes, validate results, and track or roll back revisions with Git.
Manage Ouroboros settings through a browser interface or chat commands. Choose agents and models globally or for individual stages, change the LLM backend, review saved settings, and restore the configuration from before the last change.
Operate a live AWS workload with AWS DevOps Agent — incident investigation, root-cause analysis, and release-readiness review — for startups with no dedicated DevOps or SRE engineer. Use when a live AWS workload is misbehaving (production is down, 5xx errors, latency spike, timeouts, it broke after the last deploy, an alarm fired, a pasted CloudWatch alarm or stack trace, find the root cause, write a postmortem, no one on call), for pre-merge review (is this PR safe to ship, blast radius), or to set up, pause, stop, or check the cost of AWS DevOps Agent. Detects existing setup first and never re-onboards. Asks one explicit Yes/No covering cost (two-month trial, Activate credits) and account access before any setup; code egress stays off unless asked. Do not use for: new architecture (architect-for-startups), scaffolding (start-building-for-startups), migrations (gcp-to-aws, azure-to-aws, heroku-to-aws, llm-to-bedrock), or general Activate and credits questions (knowledge-base-for-startups).
The English summary is being prepared. Showing the original description.