向量嵌入
向量检索与嵌入工作流
用途与选择建议
这类技能帮助你把模型能力接入可重复的 agent 工作流。选择时核对模型或工具要求、上下文输入和评估示例，优先采用能够覆盖实际任务的简单流程。
chroma
NousResearch
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source projects.
agent-memory-mcp
sickn33
"A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions)."
agent-memory-systems
sickn33
"Memory is the cornerstone of intelligent agents. Without it, every
rag-architect
Jeffallan
Designs and implements production-grade RAG systems by chunking documents, generating embeddings, configuring vector stores, building hybrid search pipelines, applying reranking, and evaluating retrieval quality. Use when building RAG systems, vector databases, or knowledge-grounded AI applications requiring semantic search, document retrieval, context augmentation, similarity search, or embedding-based indexing.
faiss
NousResearch
Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance applications.
gpu-document-processing
langchain-ai
Use when processing large PDFs, document collections, or bulk text extraction tasks that benefit from GPU-accelerated processing. Triggers when the user provides large documents or needs bulk document analysis.
generate-rag-dataset
langwatch
Generate a synthetic evaluation dataset from your RAG knowledge base. Creates diverse Q&A pairs with expected answers and relevant context, ready for LangWatch experiments and platform import. Use when you need test data for your RAG pipeline.
rag-chatbot
elastic
Guide for building RAG (retrieval-augmented generation) chatbots and Q&A systems with Elasticsearch. Use when a developer wants to build a chatbot, Q&A system, or AI assistant that answers questions from their own data.
elasticsearch-onboarding
elastic
Primary guided playbook for Elasticsearch search in Kibana Agent Builder: intent → data → mapping → Dev Tools API snippets (SENSE), with one question at a time. Load this skill whenever the user wants to learn Elasticsearch search, get started, begin building, take first steps, onboard, follow a walkthrough or tutorial, go from zero to a working query, or get structured help setting up indices and search — including casual openers like hi, help, getting started, new to Elasticsearch, how do I build search, or I want to try search. Use when they need end-to-end onboarding, not a single narrow API answer. If they only ask what they can build with Elastic (exploration without the full playbook), prefer invoking /use-case-library first; you can still load this skill afterward for the guided build.
use-case-library
elastic
Elasticsearch use case library — the full map of what you can build, with industry examples and technologies. Use when a developer asks "what can Elastic do?", "what can I build?", "what use cases does Elasticsearch support?", or needs help choosing what to build.
vector-hybrid-search
elastic
Guide for building vector search, hybrid search, and using Elasticsearch as a vector database. Covers semantic_text, dense_vector, embedding strategies, hybrid BM25+kNN via RRF, reranking, and production optimization. Use when a developer wants semantic search, hybrid search, kNN, embeddings, or Elasticsearch as a vector store.
sage-brinewick
BryanHarrisScripts
Guide writers through PlotPickle curriculum and story questions as Sage Brinewick. Use for LEARN Creative Room conversation, curriculum explanations, lesson application, and ordinary follow-up conversation where Sage is the visible mentor.
code-graph-rag
DoubleNode
Interact with Code-Graph-RAG engine for source code indexing, symbol querying, call graph analysis, and code-aware retrieval. SKELETON — awaiting package installation.
tooluniverse-binder-discovery
mims-harvard
Discover novel small molecule binders for protein targets using structure-based and ligand-based approaches. Creates actionable reports with candidate compounds, ADMET profiles, and synthesis feasibility. Use when users ask to find small molecules for a target, identify novel binders, perform virtual screening, or need hit-to-lead compound identification.
databricks-vector-search
databricks-solutions
"Patterns for Databricks Vector Search: create endpoints and indexes, query with filters, manage embeddings. Use when building RAG applications, semantic search, or similarity matching. Covers both storage-optimized and standard endpoints."
bulktrajblend-trajectory-interpolation
Starlitnightly
Extend scRNA-seq developmental trajectories with BulkTrajBlend by generating intermediate cells from bulk RNA-seq, training beta-VAE and GNN models, and interpolating missing states.
phoenix-design
Arize-ai
BEM CSS naming conventions for the Phoenix frontend. Use when naming new CSS classes or className assignments in app/src/.
image-video-gen
bytedance
"根据文字描述生成视频，一个生成图片和视频的工作流技能。依赖 skills: web-search, image-generate, video-generate。注意：此 workflow 没有执行脚本，只是一个描述性的文档。"
block-inventory
adobe
Survey available blocks from local AEM Edge Delivery Services project and Block Collection to understand the block palette available for authoring. Returns block inventory with purposes to inform content modeling decisions.
block-collection-and-party
adobe
The Block Collection and Block Party are repositories for existing AEM blocks, build tools, code snippets, integration patterns, plugins, and more. Use this skill anytime you are developing something and want to find a reference to use as a starting point.
pinecone
NousResearch
Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for production RAG, recommendation systems, or semantic search at scale. Best for serverless, managed infrastructure.
pinecone
NousResearch
Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for production RAG, recommendation systems, or semantic search at scale. Best for serverless, managed infrastructure.
faiss
NousResearch
Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance applications.
qdrant-vector-search
NousResearch
High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.