360 skills · sorted by relevance
Connect an application's LLM calls through the Caveman Cloud gateway to measure usage and cost without changing request content. The skill updates connection settings and verifies the integration with one small, real provider request.
Choose a serving container for models deployed on SageMaker. Match the model type to a compatible image, retrieve its address from the AWS catalog, and check regional availability, CPU or GPU variants, and required host settings.
Use LangSmith to record LLM application inputs, outputs, and timing, investigate failures, evaluate answers against test datasets, and monitor production usage. It also guides automated quality checks and analysis of token usage and costs.
Build and operate LLM applications with guidance on RAG, which uses retrieved documents to inform answers. Covers document indexing, vector database selection, prompt improvement, response evaluation, caching, and estimates of model usage costs.
Design LLM applications using patterns for answers grounded in documents, agents that use tools, and prompt testing. Implementation examples also cover monitoring response quality, latency, costs, and failures during operation.
Use LangSmith to record LLM application inputs, outputs, and timing, investigate failures, evaluate answers against test datasets, and monitor production usage. It also guides automated quality checks and analysis of token usage and costs.
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.
Prepare trained machine learning models for production with deployment, monitoring, and retraining workflows. Build RAG systems that retrieve documents for answers, and integrate language model APIs with retries, fallback providers, and cost tracking.
Launch a new OpenClaw, PicoClaw, or Ottie deployment through Cloud Claw using the local CLI. Configure the agent type, deployment name, model, and Telegram settings according to the supported launch options and requirements.
Evaluate LLM application quality using automated scores, human reviews, and another language model as a judge. Compare models or prompts, establish baseline results, and detect quality drops through repeatable tests and statistical comparisons.
Diagnose failed model requests from OpenShell sandboxes to hosted APIs or local servers such as Ollama and vLLM. Check provider attachment, access rules, credentials, network layout, and client settings to identify the narrowest configuration change needed.
Manage AltLLM Portal API keys for external agents and applications through the local CLI. Covers creation, model access limits, disabling, and revocation, while documenting production failures that currently restrict working operations to listing and creating keys.
Use Phoenix to record execution traces, detailed records of an AI application's operations, and investigate problems. Evaluate answers on datasets, compare prompts and models, and set up monitoring through a self-hosted server.
Use Phoenix to record execution traces, detailed records of an AI application's operations, and investigate problems. Evaluate answers on datasets, compare prompts and models, and set up monitoring through a self-hosted server.
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, monitor llm, debug llm, langfuse, observability, tracing, llm-monitoring, evaluation, prompt-management, debugging, analytics" mentioned.
The English summary is being prepared. Showing the original description.
Erstellt oder überarbeitet einen Skill FÜR DIESES ÖKOSYSTEM: delegiert die generische Interview-/Entwurfs-/Eval-Schleife an das offizielle skill-creator-Plugin (Anthropic, Apache-2.0), setzt aber zusätzlich die ellmos-Anforderungen durch, die das offizielle Plugin nicht kennt — Haus-Frontmatter (9 Felder), Kategorie/Sichtbarkeits-Regeln, anbieter-/nutzer-/ellmos-neutrale aber ellmos-sensitive Erkennung via grounding-seed, mitgelieferte config.json (inkl. Lernvertrag) + connections.json, Anbieter-/Vendor-Bewusstsein (State-of-the-Art-Alternativen inkl. eigener ellmos-Komponenten vorschlagen), einen Selbstaktualisierungs-Abschnitt UND einen wiederverwendbaren Lern-/Abdeckungs-Dateisatz (user-usecases.json, usecase-gaps.json, known-providers-and-abilities.json, gap-closing-analysis.json — an skill-creators evals.json und A2A/AgentSkill angelehnt, kein Parallelstandard). IMMER nutzen, wenn ein NEUER Skill für dieses System entstehen oder ein bestehender auf ellmos-Konformität nachgerüstet werden soll — auch bei "erstelle einen Skill", "bau mir einen Skill für X", "skill-creator nutzen", "neuen Skill anlegen", "diesen Skill ellmos-konform machen", "Lernvertrag/Verhaltenscodex für einen Skill anlegen", "Usecase-Abdeckung eines Skills prüfen". Für reines Skill-FINDEN/ROUTEN stattdessen skill-finder, für Landschafts-Audit skill-explorer.
The English summary is being prepared. Showing the original description.
AI基础设施实战——从GPU集群调度到模型推理部署的全栈实操指南。覆盖：昇腾/GPU统一调度、PyTorch分布式训练、vLLM推理部署、模型量化实战、LLMOps、GPU故障诊断、HuggingFace生态、MLOps流水线。触发词：AI基础设施、GPU、昇腾、训练、推理、vLLM、PyTorch分布式、模型部署、LLMOps、MLOps、集群调度、HuggingFace
The English summary is being prepared. Showing the original description.
Plan AI application development by selecting relevant phases and companion skills. The workflow covers language model integration, retrieval from documents, agents, machine learning pipelines, monitoring, and security, with prompts and quality checklists.
Investigate unreliable AI agents across 12 layers, including instructions, memory, tool execution, and display. Use code and logs to trace failures, rank findings by severity, and produce an ordered repair plan that prioritizes code changes.
Design workflows that evaluate and refine AI outputs through self-review, separate generation and evaluation roles, tests, or weighted scoring criteria. Includes patterns for structured feedback, iteration limits, and stopping when quality stops improving.
Plan how to serve a model on Amazon SageMaker AI. The skill uses model type, traffic, response time, and cost constraints to recommend a deployment route, check instance quotas, and coordinate specialized setup and deployment skills.
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.
Set up ruvector@0.3.3 with supporting packages, register its MCP server for agent access, and verify installation with diagnostic commands and smoke tests. Helps prepare the dependencies needed for initial use of /vector subcommands.
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.