“RAG”

Discovers requirements, and generates architectural, design, and deployment guidance for a retrieval-augmented generation (RAG)-capable enterprise search…

RAG (Retrieval-Augmented Generation) system for affidavit workflows.

Detect persistent-memory poisoning and RAG/knowledge-base contamination via dialogue testing.

Use for RAG, vector search, semantic search, embeddings, knowledge bases, long-term agent memory, and grounding answers in the project's own documentation.

Long-term memory via Hermes workspace RAG — ingest notes, index, search, family cards, digests, reports.

Runs checklists and workflows for designing, layering, evaluating, and operating production RAG and AI search — hybrid retrieval, agentic context tools…

对话时的角色 system prompt（问答与选定文章摘要共用；引用硬性规则由系统在问答时自动追加）

当用户询问工业设备维修、故障排查、故障代码、操作规范、设备型号、异常报警等问题时使用。必须调用企业内网 RAG 知识库获取权威答案，严禁凭预训练记忆编造故障代码或维修步骤。

Runs workflows for AIEWF 2024 RAG talks — layout-aware ingest, GraphRAG, eval-driven tuning, Pydantic structured IO, MongoDB vectors, EMT memory, construction…

RAG setup with Elasticsearch as the retrieval backend

Acts as the verification and grounding layer in Retrieval-Augmented Generation (RAG) pipelines.

Use when Codex needs to build or query a local RAG knowledge base for academic papers, literature matrices, public author guidelines, GB/T7714 rules, CSL…

Use this skill for requests about RAG design, chunking, retrieval, reranking, and related implementation trade-offs.

Build RAG (Retrieval Augmented Generation) pipelines with web search and LLMs.

Guides evaluation of RAG pipeline retrieval and generation quality.

Grounded knowledge retrieval, multi-source synthesis, and citation verification

Search the hybrid RAG (BM25 + vector, RRF-merged) over 17.6M chunks of historical sell-side research (Nomura, JPM, MS, BofA and hundreds more, 1982–2026).

Optional local retrieval (M9-OPT / ADR-003): use retrieve_knowledge_snippets when present to ground notes in files under knowledge/; map source_id to existing…

Efficiently perform web searches using the mcp-local-rag server with semantic similarity ranking.

Expert in building Retrieval-Augmented Generation systems.

Patterns for RAG pipelines, vector databases, embedding strategies, context-window management, and LLM orchestration.

Use when ingesting, searching, citing, or auditing local project knowledge for a heavy-reasoning agent, especially markdown, text, JSON, and other documents…

Chunking strategies, embedding model selection, hybrid search, reranking, eval metrics

Ejecuta flujos RAG en Obsidian para responder, resumir, reorganizar o crear notas nuevas con citas trazables.