33 件 ・ 関連度順
概要と使いどころ
Cost modeling and ROI analysis for specialized LLM development. Use when deciding whether to train a custom model, estimating total cost, or calculating break-even vs frontier APIs. Covers training costs, inference costs, and time-to-ROI projections.
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。
Diagnose Day-2 AKS GPU and KAITO incidents using profile-aware, read-only evidence. WHEN: 'Insufficient nvidia.com/gpu', GPU pod Pending, model-load OOM, DCGM/VRAM, KAITO Workspace not ready, or GPU autoscaling. DO NOT USE FOR: setup (airunway-aks-setup), non-GPU incidents (aks-troubleshooting), standalone VM quota (azure-quotas), or generic cost (cost-analysis or cost-optimization from the optional azure-cost plugin).
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。
Train and run models on Tinker (Thinking Machines) — LoRA and full fine-tuning, SFT with correct loss masking, RL/RFT with group-relative advantages and importance sampling, agentic RL over multi-turn tool-using agents, inference via the SamplingClient or the OpenAI-compatible endpoint, checkpoint management and export, every hyperparameter, and cost estimation from the live price table. Use this skill whenever the user mentions Tinker, tinker://, TINKER_API_KEY, console.tinker.ai, or the tinker CLI; wants to fine-tune, SFT, RFT, or RL a model on Tinker; asks about Tinker models, context windows, LoRA rank, sampling params, loss functions (cross_entropy, importance_sampling, ppo, cispo, dro), Datum construction, forward_backward or optim_step; wants to sample from, download, resume, merge, or export a Tinker checkpoint; or asks what a Tinker run will cost. Whenever Tinker work is initialized in a project, this skill also creates a TINKER_PRICING.md there so prices sit next to the training code. Reach for it even on vague asks like "train a model on this data" or "get inference working" when Tinker is the platform in play.
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。
Diagnose Day-2 AKS GPU and KAITO incidents using profile-aware, read-only evidence. WHEN: 'Insufficient nvidia.com/gpu', GPU pod Pending, model-load OOM, DCGM/VRAM, KAITO Workspace not ready, or GPU autoscaling. DO NOT USE FOR: setup (airunway-aks-setup), non-GPU incidents (aks-troubleshooting), standalone VM quota (azure-quotas), or generic cost (cost-analysis or cost-optimization from the optional azure-cost plugin).
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。
Project-kickoff rubric for the self-host vs managed-cloud decision — when is running your own inference engine / LLM platform worth the ops cost vs paying per-token for a managed API? Decide on two axes — VOLUME (a cost-crossover slider) and COMPLIANCE (a hard gate). Use at kickoff when choosing where to run inference, or when cost / data-residency pressure forces a re-evaluation.
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。
[omh] Software slowness, memory leaks, or cost spikes: find where a system is actually slow, leaking, or expensive across runtime, memory, token cost, storage, rendering, inference, CI, and query domains, then fix one measured hot path at a time behind a regression budget. Use when the user says: ultraperf, ulw-perf, performance audit, performance bottleneck, find the bottleneck, profile the hot path, memory leak investigation, token cost hotspot.
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。
Debug live Azure Kubernetes Service (AKS) incidents with a read-only, evidence-first investigation. WHEN: pod crashes or Pending, CrashLoopBackOff, OOMKilled, ImagePullBackOff, node NotReady, DNS or ingress failure, connectivity timeout, network policy, SNAT exhaustion, node-pool scaling blocked by QuotaExceeded or InsufficientVCPUQuota, upgrade stuck, spot or zone disruption, a bare VMExtensionProvisioningError or AllocationFailed wrapper, an uncataloged capacity symptom, or 'investigate my AKS cluster'. DO NOT USE FOR: packet capture (use aks-network-capture); GPU or model-serving issues (use aks-gpu-inference); cluster creation or provisioning (use azure-kubernetes); cost (use cost-analysis from the optional azure-cost plugin); pod rightsizing (use azure-kubernetes); a fully qualified documented AKS signature with every required nested qualifier (use aks-known-issues); standalone failures on non-AKS Azure resources (use azure-diagnostics). Unqualified errors and open-ended incidents stay here only for AKS.
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 inference on Fireworks AI — direct, through the Leanmcp AI Gateway proxy (aigateway.leanmcp.com) for observability, or via LiteLLM / the OpenAI SDK / raw HTTP. Covers the endpoint-and-key matrix for each route, serverless vs dedicated deployments and their cold starts, browsing and filtering the model catalogue, reasoning models that return content:null with the answer in reasoning_content, function calling, concurrency and load testing, and runner scripts where many models share one protocol with a --use-proxy toggle. Use this skill whenever the user mentions Fireworks, FIREWORKS_API_KEY, api.fireworks.ai, fireworks_ai/ model ids, accounts/fireworks/models/..., a Fireworks deployment id, the Leanmcp gateway or LEANMCP_API_KEY, app.leanmcp.com observability, or gpt-oss / kimi / glm / qwen / deepseek served on Fireworks; wants to route LLM calls through a proxy for logging or cost tracking; is debugging empty responses, 404s, scope errors, cold starts, or "the gateway isn't working"; wants to pick a Fireworks model with tool calling; or wants to sweep several models over one benchmark. Reach for it even on vague asks like "why is this model returning nothing" or "set up inference for these models" when Fireworks is in play.
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。
Debug live Azure Kubernetes Service (AKS) incidents with a read-only, evidence-first investigation. WHEN: pod crashes or Pending, CrashLoopBackOff, OOMKilled, ImagePullBackOff, node NotReady, DNS or ingress failure, connectivity timeout, network policy, SNAT exhaustion, node-pool scaling blocked by QuotaExceeded or InsufficientVCPUQuota, upgrade stuck, spot or zone disruption, a bare VMExtensionProvisioningError or AllocationFailed wrapper, an uncataloged capacity symptom, or 'investigate my AKS cluster'. DO NOT USE FOR: packet capture (use aks-network-capture); GPU or model-serving issues (use aks-gpu-inference); cluster creation or provisioning (use azure-kubernetes); cost (use cost-analysis from the optional azure-cost plugin); pod rightsizing (use azure-kubernetes); a fully qualified documented AKS signature with every required nested qualifier (use aks-known-issues); standalone failures on non-AKS Azure resources (use azure-diagnostics). Unqualified errors and open-ended incidents stay here only for AKS.
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 cost reduction strategies — model tiering, prompt compression, caching, batch inference. Use when asked to "reduce our AI costs", "set up model tiering", or "cut LLM spend".
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 FinOps guidance for cloud, AI, and SaaS technology spend. Covers AI cost management, agentic FinOps, GenAI capacity planning, self-hosted vs managed inference, Anthropic billing, open-weight vendor APIs (DeepSeek, Qwen, Kimi, GLM), AWS (EC2, Bedrock, SageMaker, Savings Plans, CUR), Azure (reservations, AHB, OpenAI PTUs), GCP (Vertex AI, BigQuery), OCI, Kubernetes cost allocation, data platforms (Databricks, Fabric F-SKUs, Snowflake), tagging governance, SaaS management (SAM, shadow IT), AI coding tools (Cursor, Claude Code, Copilot, Codex), ITAM, allocation, showback, chargeback, anomaly management, KPIs and benchmarking, waste detection playbooks, workload onboarding and M&A, and GreenOps (cloud carbon, CSRD). Use for any question about technology cost or waste in your estate - expiring commitments or RIs, NAT gateway bills, idle VMs, snapshot sprawl - and for commitment sizing, rightsizing, allocation, SaaS sprawl, AI dev tool spend, or connecting spend to business value. Built by OptimNow.
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。
Plan, create, and configure production-ready Google Kubernetes Engine (GKE) clusters using the golden path Autopilot configuration. Covers Day-0 checklist, Autopilot vs Standard, networking (private clusters, VPC-native, Gateway API), security (Workload Identity, Secret Manager, RBAC hardening), observability, scaling, cost optimization, and AI/ML inference. WHEN: create GKE cluster, provision GKE environment, design GKE networking, secure GKE, optimize GKE cost, GKE autoscaling, GKE inference, GKE upgrade, GKE observability, GKE multi-tenancy, GKE batch, GKE HPC, GKE compute class.
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。
Claude API (platform.claude.com) の組織管理・Admin API (sk-ant-admin) リファレンス。 users, invites, workspaces, API keys, service accounts, RBAC (groups / roles), Workload Identity Federation (WIF, federation issuers / rules), Usage & Cost API, rate limits / spend limits, Analytics API, Compliance API, CMEK, zero data retention (ZDR), data residency, inference hooks。
Auto-scale LLM inference clusters on Kubernetes using KEDA, custom GPU metrics, and horizontal pod autoscaling. Handle traffic spikes, implement queue-based scaling, and optimize cost with spot instances for AI workloads.
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。
Audit a codebase for LLM calls that are really classifications in disguise, then produce a costed swap plan for a System One model. Use when asked to cut AI inference cost or latency, when scoping a performance engagement for a client, when reviewing an agent loop that feels slow, or when asked "where could we use Jev here". Produces a ranked table of candidates with measured latency and dollar deltas.
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。
Profile and debug Hermes sessions from their JSONL transcripts. Find a session and its subagents, build a queryable event table, summarize the work as a hierarchical table of contents, break down wall time, inference, tools, tokens, and estimated cost per agent, identify errors and improvement opportunities, and export a shareable Perfetto trace. Use when a user wants to inspect what a Hermes session did, debug agent or subagent activity, understand session cost or latency, create a session timeline, generate a trace, or learn how to improve the next agent run.
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 machine learning models to edge devices using Google AI Edge Gallery, TensorFlow Lite, ONNX Runtime, and MediaPipe. Covers model quantization (INT8/INT4), on-device inference with Gemma 4 models, Android/iOS deployment via AI Edge Gallery, hardware delegate selection (GPU/NPU/DSP), and performance benchmarking on constrained devices. Use when deploying models to mobile phones, IoT devices, or embedded systems where cloud inference is impractical due to latency, cost, or connectivity constraints.
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。
Instrument a shipped product's AI agents with tracing and observability so you can see what they did, why outputs happened, and what each run cost. Plain-language primer plus free-tier-first backend selection (Langfuse, Phoenix, LangSmith, Braintrust) and OpenTelemetry/OpenInference instrumentation. Load when the user asks to add observability, add tracing, instrument my agents, see what my agent is doing in production, set up Langfuse or Phoenix or LangSmith, debug why my agent gave a bad answer, or track LLM cost per request. Also fires when agent-system-architecture or setup-evaluation requires an observability plan for an agent-chain product. NOT for tracing the coding agent itself — that is run-trace. Precondition for runtime-learning-loop.
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。
Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.
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。
Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source models, or reducing inference costs. Covers temperature scaling, soft targets, reverse KLD, logit distillation, and MiniLLM training strategies.
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。
Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source models, or reducing inference costs. Covers temperature scaling, soft targets, reverse KLD, logit distillation, and MiniLLM training strategies.
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。
Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.
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。
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。
WASM-based instant code transforms for simple tasks, achieving 352x speedup over LLM inference with zero cost.
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。