AI tools for “llm”

Pick the right LLM model for an Output SDK prompt file. Use when writing a new .prompt file, reviewing a model choice, or upgrading a stale model. Walks through priority (reasoning/balance/speed/cost), provider…

Design effective LLM judge .prompt files for evaluators. Use when creating judgeVerdict/judgeScore/judgeLabel prompts, or when existing judges produce unreliable results.

…guide to Output.ai Framework for building durable, LLM-powered workflows orchestrated by Temporal. Covers project structure, workflow patterns, steps, LLM integration, HTTP clients, CLI commands, and the full…

Validate LLM judges against human labels using TPR/TNR metrics and train/dev/test splits. Use after writing a judge prompt to verify it agrees with human judgment.

Migrate to Langfuse from another LLM observability/evals platform (LangSmith, Arize AX, Phoenix, Braintrust, Helicone, Promptfoo, ...). A one-off vendor switch: live tracing cutover plus transfer of historical traces,…

Plan and coordinate the deployment of a model to Amazon SageMaker AI. Use this skill whenever the user wants to deploy, host, serve, or expose a model on SageMaker or AWS — including phrases like "deploy a model", "host…

Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF…

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…

…the user asks about finding the best, top, or recommended model for a task, wants to know what AI model to use, or wants to compare models by benchmark scores. Triggers on: "best model for X", "what model should I use…

Use this skill when an application owns tool or LLM/provider call sites and needs to wrap them with NeMo Relay scopes and managed execution APIs for lifecycle events, middleware, or guardrails.

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

…add or update notes, organize docs/notes for an agent or LLM to consume, build an index of notes, or run a cleanup/maintenance pass on an existing MD knowledge base. Triggers include "knowledge base", "KB", "notes…

…or department", "where are we wasting GPU cycles?", "is llm-serving actually busy? its GPU memory is full", "is project X actually using its GPUs?", "which workloads in project X are idle?", "which node pool wastes…

…reranking, image generation, or working with any LLM…

Corrects outdated LLM knowledge about the Vercel platform and introduces new products. Injected at session start.

…needs something MySQL lacks: UUIDv7 or 16-byte UUID keys, LLM calls or embeddings in SQL, password hashing or encryption in SQL, IP/CIDR/MAC columns, HTTP calls from SQL, fuzzy or phonetic text matching, a strict…

…(MCQ, binary, open-ended) with reasoning traces, via VLM/LLM distillation. Use when the user wants to "create video training data", "generate video QA datasets", "build CoT reasoning traces from videos", "auto-label…

…algorithm selection (bayesian, hyperband, asha, bohb, llm, hybrid, autoresearch), WandB experiment tracking, job execution on any TAO SDK platform, result interpretation, and per-rec custom evaluation hooks. Use…

Fine-tune any HuggingFace CV / VLM / LLM model on local NVIDIA GPUs inside an NGC PyTorch container when no dedicated TAO model skill matches. Use when the user wants to fine-tune a HuggingFace model (full or LoRA),…

…report over an Informatica export — no cluster, no LLM call, no cost. Use before migrating anything, to know what's in an export, how complex it is, and which pieces this tool cannot convert. Accepts a…