Loading...
Loading...
Found 40 Skills
Comprehensive prompt and context engineering for any AI system. Four modes: (1) Craft new prompts from scratch, (2) Analyze existing prompts with diagnostic scoring and optional improvement, (3) Convert prompts between model families (Claude/GPT/Gemini/Llama), (4) Evaluate prompts with test suites and rubrics. Adapts all recommendations to model class (instruction-following vs reasoning). Validates findings against current documentation. Use for system prompts, agent prompts, RAG pipelines, tool definitions, or any LLM context design. NOT for running prompts, generating content, or building agents.
A prompt repetition technique for improving LLM accuracy. Achieves significant performance gains in 67% (47/70) of 70 benchmarks. Automatically applied on lightweight models (haiku, flash, mini).
Expert guide on prompt engineering patterns, best practices, and optimization techniques. Use when user wants to improve prompts, learn prompting strategies, or debug agent behavior.
Framework for automated search over task-specific model harnesses — the code around a fixed base model that decides what to store, retrieve, and show while the model works.
Retrieval-Augmented Generation patterns including chunking, embeddings, vector stores, and retrieval optimizationUse when "rag, retrieval augmented, vector search, embeddings, semantic search, document qa, rag, retrieval, embeddings, vector, search, llm" mentioned.
Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications. Use when "building RAG, vector search, embeddings, semantic search, document retrieval, context retrieval, knowledge base, LLM with documents, chunking strategy, pinecone, weaviate, chromadb, pgvector, rag, embeddings, vector-database, retrieval, semantic-search, llm, ai, langchain, llamaindex" mentioned.
You are an expert prompt engineer specializing in crafting effective prompts for LLMs through advanced techniques including constitutional AI, chain-of-thought reasoning, and model-specific optimizati
AI/LLM: Use when crafting system prompts, optimizing LLM outputs, or improving agent instructions. NOT for general coding.
Add EAGLE-3 or draft-model speculative decoding to a Jetson vLLM server when TPOT is the bottleneck.
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot learning, creating system prompts with personas and guardrails, building JSON/function-calling schemas, or developing prompt evaluation frameworks to measure and improve model performance.
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
Run an autonomous Humanize-governed vLLM SOTA performance loop for one LLM model: first perform the fixed fair vLLM/SGLang/TensorRT-LLM deployment search and benchmark, then start one RLCR loop that repeatedly decides the gap, profiles the current bottleneck, runs layer/kernel pipeline analysis, patches vLLM code, optionally uses ncu-report-skill for kernel evidence, and revalidates until vLLM matches or beats the best observed framework under the same workload and SLA.