3.1K skills · sorted by relevance
Design text extraction for forms, invoices, and quizzes using regex, rules that match text patterns. Check extraction confidence and send uncertain items to an LLM for review, with guidance on testing and tracking processing costs.
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.
Add checks to LLM prompts and responses using Llama Guard 3, NeMo Guardrails, and LLM Guard. Configure content screening, conversation boundaries, and sensitive-data filtering, then measure blocking and false-positive rates with labeled test prompts.
Configure LLM inference and serving on NVIDIA GPUs with TensorRT-LLM. Covers quantization, which reduces numerical precision, batching requests during generation, and distributing models across GPUs to improve processing capacity and response times.
Configure LLM inference and serving on NVIDIA GPUs with TensorRT-LLM. Covers quantization, which reduces numerical precision, batching requests during generation, and distributing models across GPUs to improve processing capacity and response times.
Find LLM workflows in a codebase and label them by the job they perform, so Caveman Cloud can separate spending by workflow. Present a labeling proposal for approval, apply focused code changes, and check an affected execution path.
Set up Langfuse to record LLM application activity, costs, and response times. Manage prompt versions, organize evaluation datasets, and compare results to investigate failures and guide improvements using recorded evidence.
Design an LLM API workflow that controls spending through task-based model selection, budget tracking, selective retries, and caching repeated prompts. Use the examples to route simpler tasks to cheaper models and track cumulative costs.
Build an llms.txt file, a navigation guide for AI models, from a repository's structure. Summarize the project and organize links to essential documentation, specifications, examples, and configuration resources.
Create or review llms.txt, a Markdown guide to a website for AI systems. Discover important pages, write factual summaries, check links and formatting, and produce a ready-to-save file or an improvement report.
Delegate code changes and multi-step development tasks to OpenHands CLI using a model supported by LiteLLM, a connection layer for model providers. Run tasks without an interactive interface, inspect progress events, and resume previous conversations.
Assess language models with over 60 academic benchmark tests using consistent prompts and scoring. Compare models, track performance during training, and organize research results with support for HuggingFace models, vLLM, and APIs.
Build safety checks for LLM prompts and responses using Meta's LlamaGuard. This skill covers content classification, batch moderation, serving a moderation API, and connecting checks to NeMo Guardrails.
Assess language models with over 60 academic benchmark tests using consistent prompts and scoring. Compare models, track performance during training, and organize research results with support for HuggingFace models, vLLM, and APIs.
Compress large language model weights to four bits with AWQ, a method that uses model activation patterns to limit quality loss. Follow workflows for quantization, loading compressed models, and serving them with vLLM using less GPU memory.
Audit and improve `/llms.txt`, a curated starting point for AI tools browsing documentation. Check its location, the usefulness and accessibility of linked pages, and its separation from existing crawl and indexing controls.
Analyze LLM serving traces to identify GPU time usage, opportunities to run operations concurrently, and known patterns for combining operations. Produce three consistent tables from saved traces or live captures on supported servers.
Compress LLM weights using HQQ quantization, which stores weights with fewer bits without calibration datasets. Follow workflows for precision settings, model saving, inference integration, and LoRA fine-tuning of quantized models.
Deploy language models with vLLM through an OpenAI-compatible API or offline batch processing. Tune response speed, throughput, and GPU memory use with quantization, which reduces numerical precision, and execution across multiple GPUs.
Compress large language models to 4-bit weights to reduce GPU memory use and accelerate inference. Covers loading compressed models, configuring quantization, and using Transformers or vLLM, with guidance on hardware requirements and backend choices.
Helps speed up LLM text generation by comparing methods that predict and verify multiple tokens at once. Covers draft model selection, Medusa prediction heads, Lookahead Decoding settings, and deployment examples for inference services.
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.
Set up vLLM to serve large language models through an OpenAI-compatible API or process prompts in batches. The skill covers deployment, performance monitoring, and quantization, which reduces model memory requirements.
Turn a captured source document into linked LLM Wiki pages for sources, entities, concepts, and combined insights. Update the index and log, preserve the original material, and flag contradictions with existing knowledge instead of silently replacing it.