Loading...
Loading...
Found 66 Skills
Build production RAG systems with semantic chunking, incremental indexing, and filtered retrieval. Use when implementing document ingestion pipelines, vector search with Qdrant, or context-aware retrieval. Covers chunking strategies, change detection, payload indexing, and context expansion. NOT when doing simple similarity search without production requirements.
Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector stores), and the cognitive architectures that organize them. Key insight: Memory isn't just storage - it's retrieval. A million stored facts mean nothing if you can't find the right one. Chunking, embedding, and retrieval strategies determine whether your agent remembers or forgets. The field is fragm
Amazon Bedrock Knowledge Bases for RAG (Retrieval-Augmented Generation). Create knowledge bases with vector stores, ingest data from S3/web/Confluence/SharePoint, configure chunking strategies, query with retrieve and generate APIs, manage sessions. Use when building RAG applications, implementing semantic search, creating document Q&A systems, integrating knowledge bases with agents, optimizing chunking for accuracy, or querying enterprise knowledge.
Use when you need legal PDF to markdown extraction plus clause chunking and embedding prep; pair with addon-rag-ingestion-pipeline and architect-python-uv-batch.
Guides evaluation of RAG pipeline retrieval and generation quality. Use when evaluating a retrieval-augmented generation system, measuring retrieval quality, assessing generation faithfulness or relevance, generating synthetic QA pairs for retrieval testing, or optimizing chunking strategies.
Build timeout-resistant Claude Code workflows with chunking strategies, checkpoint patterns, progress tracking, and resume mechanisms to handle 2-minute tool timeouts and ensure reliable completion of long-running operations.
Designs production-grade RAG pipelines with chunking optimization, retrieval evaluation, and pipeline architecture. Use when building a RAG system, selecting a chunking strategy, choosing a vector database, optimizing retrieval quality, designing embedding pipelines, or evaluating RAG performance with RAGAS metrics.
Builds generative AI applications on Amazon Bedrock. Covers model invocation (Converse API, InvokeModel), RAG with Knowledge Bases, Bedrock Agents, Guardrails, and AgentCore. Use when invoking models, setting up Knowledge Bases, creating agents, applying guardrails, deploying to AgentCore, troubleshooting Bedrock errors (ThrottlingException, AccessDeniedException), or choosing models (Claude, Llama, Nova, Titan). ALSO USE for prompt caching setup and debugging, quota health checks and throttling diagnosis, cost attribution and tracking, migrating between Claude model generations (4.5 to 4.6 to 4.7), chunking strategies, API selection (Converse vs InvokeModel), guardrail capabilities, and model selection. NOT for custom model training, Rekognition, or Comprehend.
Iterate on RAG systems with structured evals instead of eyeballing. This skill should be used when the user is tuning a RAG pipeline — changing retrieval prompts, swapping models, adjusting chunking, or debugging poor answers — and wants a cheap, ranked set of experiments with cost tracking and structured feedback on the stack. Also use when the user asks "how do I know if my RAG is working?", "this RAG eval is burning money", or "what should I try next on retrieval?".
Review, design, and refactor TensorRT-LLM PyTorch MoE code for architecture fit, clean code, maintainability, and testability. Always use for any modification, review, refactor, or design planning that touches MoE modules, including tensorrt_llm/_torch/modules/fused_moe, ConfigurableMoE, MoE backends, MoEScheduler/moe_scheduler.py, forward execution/chunking, communication strategies, EPLB, quantization/weight handling, routing, factories, MoE docs, or MoE tests. Also use when the user asks whether a MoE design follows the current architecture or whether a MoE refactor is reasonable.
Vite build tool configuration and ecosystem. Covers vite.config.ts setup, plugin authoring and popular plugins, dev server configuration (proxy, HMR, HTTPS), build optimization (chunking, tree-shaking, manual chunks, rollupOptions), library mode for publishing packages, SSR configuration, environment variables (.env handling), multi-page apps, CSS handling (PostCSS, CSS modules, preprocessors), and asset handling. Use when configuring Vite projects, authoring Vite plugins, optimizing builds, setting up dev server proxies, configuring SSR, handling environment variables, or troubleshooting Vite issues.
Data pipelines, feature stores, and embedding generation for AI/ML systems. Use when building RAG pipelines, ML feature serving, or data transformations. Covers feature stores (Feast, Tecton), embedding pipelines, chunking strategies, orchestration (Dagster, Prefect, Airflow), dbt transformations, data versioning (LakeFS), and experiment tracking (MLflow, W&B).