「llm ops」の検索結果

Add file-based observability, tracing, and run analysis to LLM/agent experiments — per-turn transcripts, tool calls and results, reasoning traces, token/cost accounting, per-episode artifacts, plus terminal viewers and a run-comparison report. Platform-agnostic: one small adapter covers OpenAI, Gemini/Vertex, Anthropic, LiteLLM, Tinker, vLLM, or any custom inference stack, and the same tooling then works unchanged. Use this skill whenever the user wants observability, tracing, logging, or run tracking for model experiments; asks why an agent failed a task or wants to replay/debug/diff an episode; wants to compare models, arms, or ablations; wants to instrument a new folder, repo, or platform ("add observability here", "do the same for Tinker/Gemini/OpenAI"); wants to import or tie in existing experiment results so old runs show up alongside new ones; or wants eval runner scripts where many models share one protocol. Reach for this even when they only say "log what the model is doing", "I can't tell what happened in this run", or "set up traces for this experiment".

日本語の概要は準備中です。原文の説明を表示しています。

Deploy an API gateway for LLM traffic with load balancing, rate limiting, key management, semantic caching, fallback routing, and cost tracking. Covers LiteLLM Proxy, OpenRouter-compatible setup, and custom Nginx/Traefik patterns.

日本語の概要は準備中です。原文の説明を表示しています。

Run local LLM workloads with Ollama, Open WebUI, and GPU-aware tuning for private development environments. Use when setting up private inference, local AI dev environments, or air-gapped LLM deployments.

日本語の概要は準備中です。原文の説明を表示しています。

Think and work like an expert Machine Learning Engineer. Use when a task calls for Machine Learning Engineer judgment. Reasons from decision-policy framing, Google's Rules of ML, point-in-time data, and prefill/decode inference physics through GBDT/PyTorch baselines, vLLM/SGLang/KServe serving with FP8/AWQ quantization, hybrid-retrieval RAG, RAGAS and human-validated LLM judges, OpenTelemetry GenAI tracing, and post-Omnibus EU AI Act obligations while treating train-serve skew, temporal leakage, prompt injection, LLM nondeterminism, and degenerate feedback loops as first-class failure modes.

日本語の概要は準備中です。原文の説明を表示しています。

Internal — for Boundless team members only. Cross-reference Boundless indexer API data, broker telemetry, and service logs to investigate production and staging operational issues. Use when the user wants to understand why slashings happened on prod/staging, diagnose prover or service failures in deployed environments, correlate market events with broker behavior, investigate fulfillment rate drops, look at prover/service logs, or perform any analysis that requires combining on-chain indexer data with off-chain broker telemetry and CloudWatch logs. Also use when the user asks to "investigate", "diagnose", or "find root cause" for prover, service, or market issues on live networks. Do NOT use for debugging local code changes, reviewing PRs, or investigating issues in the codebase itself.

日本語の概要は準備中です。原文の説明を表示しています。

Production-grade TypeScript reference for React & Next.js frontend development. Covers type narrowing, component Props, generic hooks, discriminated unions, as const, satisfies, Zod validation, TanStack Query, server/client boundaries, forms, state management, performance, accessibility, debugging, and code review. Use when the user works with TypeScript in React or Next.js: type errors, Props design, generics, API typing, SSR/CSR boundaries, hydration issues, form validation, state management, performance, or code review. Also use for "how should I type this?", "why does this type error happen?", or any architectural decision involving TypeScript in a frontend context.

日本語の概要は準備中です。原文の説明を表示しています。

Set up the Graphsignal Profiler for inference workloads — vLLM, SGLang, PyTorch, and dstack services. Use when the user wants GPU profiling, tracing, or monitoring for inference, asks about `graphsignal-run` or `graphsignal.watch()`, or asks about CUPTI / Prometheus / OTLP setup.

日本語の概要は準備中です。原文の説明を表示しています。

Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - Implementing self-critique and reflection loops - Building evaluator-optimizer pipelines for quality-critical generation - Creating test-driven code refinement workflows - Designing rubric-based or LLM-as-judge evaluation systems - Adding iterative improvement to agent outputs (code, reports, analysis) - Measuring and improving agent response quality

日本語の概要は準備中です。原文の説明を表示しています。

Arize is an AI observability platform, and Phoenix is its open-source tracing and evaluation tool for LLM applications. Use this skill when the user wants to trace OpenAI or LangChain calls, run a local Phoenix server, score RAG answers for faithfulness, debug slow or wrong LLM responses, or send OpenTelemetry traces to Arize for production monitoring.

日本語の概要は準備中です。原文の説明を表示しています。

Design an LLM eval — task schema, scoring rubric, dataset composition, and pass/fail thresholds. Use when asked to "design an LLM eval", "write a scoring rubric", or "how do we measure this model".

日本語の概要は準備中です。原文の説明を表示しています。

Expert guide for LLM observability in production — token cost tracking, hallucination rate monitoring, latency analysis, prompt/completion logging, model comparison dashboards, and AI-specific tracing (Langfuse, Helicone, Lunary, OpenTelemetry GenAI) / Panduan ahli observabilitas LLM di produksi — pelacakan biaya token, pemantauan tingkat halusinasi, analisis latensi, logging prompt/completion, dashboard perbandingan model, dan tracing khusus AI.

日本語の概要は準備中です。原文の説明を表示しています。

Comprehensive L&D framework for upskilling DevOps/IaC/Automation teams to become AI Agent Engineers. Covers LLM literacy, RAG, agent frameworks, multi-agent systems, and LLMOps. Designed to help traditional automation teams compete with OpenAI and Anthropic.

日本語の概要は準備中です。原文の説明を表示しています。

Analyze credential-free public website monitoring evidence from server access logs, HTTP fetches, robots/llms/sitemap checks, and exported summaries while protecting raw IP and private query data. Use this skill when the user asks whether crawlers or AI bots reached a site, whether public SEO/LLM discovery files respond, or how to separate observed facts from unknown Search Console, rank, analytics, or citation claims.

日本語の概要は準備中です。原文の説明を表示しています。

Agentic workflow patterns for autonomous LLM reasoning. Use when building ReAct agents, implementing reasoning loops, or creating LLMs that plan and execute multi-step tasks.

日本語の概要は準備中です。原文の説明を表示しています。

Education Cloud (EDA — Education Data Architecture) setup: student success hub, advisor workflows, enrollment management, academic data model. NOT for the EDA object model in depth (Affiliations, Course_Connection__c) — use data/eda-data-model-and-patterns. NOT for SIS enrollment sync — use integration/sis-integration-patterns.

日本語の概要は準備中です。原文の説明を表示しています。

Set up and run local LLMs with Harbor. Use when the user wants to run models locally, install Harbor, start Open WebUI, llama.cpp, Ollama, vLLM, Docker Model Runner, MLX, or oMLX, pull GGUF or HuggingFace models, add SearXNG web search, Speaches TTS/STT, or Open Terminal code execution, launch Codex/Claude/Grok/OpenCode against a Harbor backend, or troubleshoot GPU, VRAM, and service startup.

日本語の概要は準備中です。原文の説明を表示しています。

Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature.

日本語の概要は準備中です。原文の説明を表示しています。

环境安装与准备：把部署环境从零安装就绪——mindiesd 编译安装（本地昇腾直装 / SSH 推远端容器 / Docker 镜像直装）与三方推理框架全栈安装（vLLM-Omni 源码构建、DiffSynth-Engine 部署、 LightX2V editable 部署），并负责模型权重确认与下载（下载前先确认远端是否已存在）。不含特性使能与验证 （framework-integration）与 profiling（profiling-collect）；SSH 工具由 remote-access 提供。 当用户需要安装 MindIE-SD、源码构建/直装 vLLM-Omni 或 LightX2V（editable + PLATFORM=ascend_npu）、 或确认/下载模型权重时使用此技能； 即使用户只提到"把代码推到服务器""在容器里装 vllm 全栈""准备 lightx2v 调优环境"而未说昇腾， 只要上下文涉及环境安装与准备都应触发。由 model-auto-optimization S0 与 dev-workflow 部署阶段指引加载。

日本語の概要は準備中です。原文の説明を表示しています。

Tracks cumulative LLM costs across DAG execution and makes real-time decisions to stay within budget. Downgrades models, skips optional nodes, or stops early when cost exceeds thresholds. Use when managing execution budgets, analyzing cost breakdowns, or optimizing model routing for cost. Activate on "cost budget", "too expensive", "reduce cost", "cost optimization", "model downgrade", "budget exceeded". NOT for LLM model selection logic (use llm-router), pricing comparisons across providers, or billing/invoicing.

日本語の概要は準備中です。原文の説明を表示しています。

Erstellt einen portablen KI-Arbeitsbereich auf einem USB-Stick oder beliebigen Laufwerk. RAG-Pipeline mit lokalen LLM-Modellen (Ollama), Vektordatenbank (ChromaDB) und vorkonfigurierten Prompts.

日本語の概要は準備中です。原文の説明を表示しています。

Erstellt und verwendet einen anbieterneutralen semantischen Routing-Graphen aus Personas, koordinierenden Rollen, Experten und aktiven Skill-Endpunkten. Verwenden, wenn ein LLM eine Anfrage von einer Leitrolle über einen Experten zu einem Skill routen, aus einem vorhandenen Agentensystem einen portablen Persona-Router extrahieren, eine semantische Domänenkarte mit einer lexikalischen Skill-Registry kombinieren oder fehlende Verbindungen zwischen Rolle und Skill sichtbar machen soll, statt still auf einen Ersatz zurückzufallen. Auslöser sind unter anderem semantisches Persona-Routing, Persona-Umbrella, Rollen-Router, Boss-Agent-Experten-Skill-Routing, Agentenrollen-Export oder die Wiederverwendung von Personas über mehrere LLM-Anbieter hinweg.

日本語の概要は準備中です。原文の説明を表示しています。

Deploy a new LLM model via LiteLLM (GitOps) and/or Azure (Terraform + node backend), add it to the ai toolkit, create the required pull requests, and verify end-to-end. Use when rolling out a model to any environment, adding a model to the toolkit, troubleshooting "model not available" errors, or finding pricing/token limits/model ids for any provider.

日本語の概要は準備中です。原文の説明を表示しています。

Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production AI systems with real-time insights.

日本語の概要は準備中です。原文の説明を表示しています。

Tracks cumulative LLM costs across DAG execution and makes real-time decisions to stay within budget. Downgrades models, skips optional nodes, or stops early when cost exceeds thresholds. Use when managing execution budgets, analyzing cost breakdowns, or optimizing model routing for cost. Activate on "cost budget", "too expensive", "reduce cost", "cost optimization", "model downgrade", "budget exceeded". NOT for LLM model selection logic (use llm-router), pricing comparisons across providers, or billing/invoicing.

日本語の概要は準備中です。原文の説明を表示しています。