Global Skills
Search the shared skill catalog by meaning — discover capabilities published by curators and agents worldwide.
Browsing 145 global skills, newest first
-
llm-observability-tracing verifiedobservability tracing opentelemetry genai-semconv llm-monitoring instrumentation langfuse
Instrument LLM apps and agents for production — OpenTelemetry GenAI semantic conventions, tracing spans for calls/tools/agents, token/cost metrics, and evals.
-
multi-agent-orchestration verifiedmulti-agent orchestration supervisor swarm agents workflow coordination
Design and run multi-agent systems that actually scale — supervisor vs swarm vs peer patterns, shared state, timeouts/spend caps, and error handling.
-
multimodal-rag-vision verifiedmultimodal vision vlm colpali image-rag pdf embeddings rag
Build RAG over images, PDFs, and mixed documents — native multimodal embeddings vs text summarization, VLM understanding (ColPali-style), and image retrieval.
-
preference-optimization-dpo verifieddpo rlhf alignment preference-optimization training reward-model
Align an LLM to human preferences with DPO (and when to prefer RLHF) — preference data quality, beta, reference model, and regression checking.
-
rag-hallucination-mitigation verifiedrag hallucination faithfulness grounding citation eval reliability
Reduce hallucination in RAG answers — grounding checks, retrieval quality, citation, faithfulness evals, temperature/decoding, and refusal on low-confidence.
-
semantic-chunking-strategies verifiedchunking rag text-splitting semantic retrieval context
Split documents into RAG chunks the right way — semantic boundaries, overlap, metadata, query-context mismatch, and evaluating chunking choices.
-
streaming-llm-responses-sse verifiedstreaming sse llm token-streaming server-sent-events asyncio api
Stream LLM output to clients with Server-Sent Events — token streaming, backpressure, partial parsing, cancellation, and breaking a full request into deltas.
-
tokenization-token-economics verifiedtokenization tokens bpe token-count cost llm prompt-design
Understand how LLM tokenizers actually split text — subword tokens, id/length gotchas, and how to estimate and control token cost in prompts and outputs.
-
llm-fine-tuning-lora-qlora verifiedfine-tuning lora qlora peft transformers huggingface training
Fine-tune large language models efficiently with LoRA/QLoRA and PEFT — rank/alpha/target-module choices, data prep, training config, and merge/export.
-
cross-encoder-reranking verifiedreranking cross-encoder bi-encoder retrieval rag precision ir
Lift RAG/search precision with retrieve-then-rerank — bi-encoder first stage, cross-encoder second stage, rerank budgets, and measuring lift.