“RAG”

Use when a medical AI paper should be found and cited by AI search engines and RAG tools.

Test RAG vector stores (Pinecone, Qdrant, Weaviate, Chroma, pgvector, FAISS) for embedding inversion, cross-tenant data leakage, and data poisoning per OWASP…

将 PDF/PPT/Excel/Word 等多格式文档解析为结构化 Markdown，并输出元数据与解析置信度，作为 RAG 与四色卡片的数据底座。

Build, review, or harden AI agents, LLM apps, RAG, tool-calling, coding agents, and agentic workflows with secure-by-default controls.

Evaluate Anvia agents and retrieval — deterministic metrics, semantic similarity, LLM judges, RAG quality, and CLI eval runs.

Build RAG / unstructured-document evaluation datasets and demo documents (e.g.

Use when implementing GPT chat, streaming, function calling, embeddings for RAG, images, audio or batch jobs, or troubleshooting 429 rate limits and API or…

Complete Open WebUI API integration for managing LLM models, chat completions, Ollama proxy operations, file uploads, knowledge bases (RAG), image generation…

Use AdalFlow to build, debug, evaluate, optimize, trace, and operate LLM task pipelines, RAG systems, agents, tools, and structured-output workflows.

AgentScope repo skill for building agents, provider connectors, RAG and memory workflows, service deployments, and local or sandboxed workspaces.

Routes agents using or contributing to CrewAI, including crews, flows, CLI projects, tools, MCP, memory, RAG, LLM providers, observability, files, multimodal…

Route DeepSearcher workflows for provider setup, data ingestion, RAG querying, CLI and service operation, and evaluation.

Comprehensive book editing system with RAG memory for Hermes.

Query Indian Constitution articles and BNS 2023 (Bharatiya Nyaya Sanhita) criminal law sections using RAG with semantic search.

Router for modern AI research workflows including model architecture, fine-tuning, evaluation, agents, RAG, observability, multimodal systems, and ML-paper…

Deep-crawl any website from start URLs, return per-page LLM-ready text/markdown/HTML plus metadata (title, description, author, language, canonical URL, OG)…

Pre-ingestion verification for epistemic quality in RAG systems.

Tra cứu quy định, văn bản pháp lý, tiền lệ từ kho tài liệu nội bộ sử dụng RAG (Retrieval-Augmented Generation).

Use when reviewing TOPdesk exports, REST snapshots, field catalogs, Power BI datasets, AI prompts, RAG sources, reports, or demos for PII exposure, privacy…

Local-first RAG memory system for AI agents.

使用 Crawl4AI 对指定 URL 进行联网抓取，并将结果（Markdown、元数据）保存到本地指定路径。适用于需要把网页内容转为可读 Markdown 并落盘、RAG 或离线分析的场景。当用户要求“联网搜索并保存”“爬取网页保存到某路径”或使用 crawl4ai 抓取并保存时使用本 skill。

知识库查询引擎 - 支持合同审核、制度查询、合规检查。使用向量检索和重排序技术，精准定位相关知识片段。子 Agent 使用 qwen3.5-flash 模型，降低主 Agent 算力消耗。关键词：知识库、合同审核、制度查询、合规检查、向量检索、RAG

向量语义知识库 - 中文优化 RAG，支持增量同步和自动监控

Covers everything about search in MongoDB: Atlas Search (full-text), Vector Search (semantic), and Hybrid Search.