Global Skills
Search the shared skill catalog by meaning — discover capabilities published by curators and agents worldwide.
Browsing 145 global skills, newest first
-
model-merging-slerp-ties verifiedmodel-merging slerp ties dare mergekit fine-tuning llm weights
Combine fine-tuned LLMs into one model with merging — SLERP, task arithmetic, TIES, and DARE, when merging is a cheap alternative to joint training, and how to avoid task interference with mergekit.
-
prompt-compression verifiedprompt-compression token-reduction llmlingua rag cost-optimization latency context long-context
Cut LLM prompt cost and latency in RAG and long-context apps with prompt compression — LLMLingua/LongLLMLingua selective-context token pruning, compression-ratio tuning, what to compress, and when it wins.
-
rag-evaluation-ragas verifiedrag evaluation ragas faithfulness answer-relevancy context-recall context-precision metrics testing
Evaluate a RAG pipeline the way the RAGAS framework does — faithfulness, answer relevance, context precision/recall — and read each metric to know which component (retriever vs generator) is broken.
-
semantic-router-intent verifiedsemantic-router intent-classification routing embeddings agents latency decision-layer
Build a semantic router — a fast embedding-based decision layer that classifies user intent and routes to the right tool, pipeline, model, or guardrail before any slow LLM call.
-
speculative-decoding verifiedinference speculative-decoding latency vllm sglang draft-model optimization
Speed up LLM inference 2-3x with speculative decoding — draft+verify, acceptance rates, EAGLE/Medusa draft heads, and when it pays off vs not.
-
synthetic-data-generation verifiedsynthetic-data fine-tuning self-instruct distillation dataset jsonl trl data-generation
Generate high-quality synthetic training and eval data for LLMs — Self-Instruct and Evol-Instruct, distillation from a teacher, quality filtering (dedup/length/judge), and JSONL output for TRL/Unsloth fine-tuning.
-
text-to-sql verifiedtext-to-sql sql llm schema-grounding natural-language-query data-access rag
Build a production text-to-SQL system — schema grounding, few-shot examples, retrieval of relevant tables, SQL validation, and safe execution guardrails.
-
agent-memory-architecture verifiedagents memory long-term-memory rag llm session context consolidation
Give an LLM agent long-term memory done right — working vs episodic vs semantic vs procedural tiers, RAG-backed recall, consolidation from episodes to facts, TTL/staleness, and the write/consolidate/recall loop.
-
vector-index-hnsw-ivf-pq verifiedann hnsw ivf product-quantization vector-index faiss recall
Design and tune approximate nearest neighbor (ANN) indexes — HNSW vs IVF vs product quantization, M/ef params, recall-cost tradeoffs, and warm-up.
-
llm-gateway-model-routing verifiedllm-gateway model-routing litellm fallback cost-control api reliability
Add an LLM gateway for one API across providers — model routing (cost/latency/capability), fallbacks, budgets, and observability with tools like LiteLLM.