Rag Skills for OpenClaw Agents

GNO

@gmickel

Search local documents, files, notes, and knowledge bases. Index directories, search with BM25/vector/hybrid, get AI answers with citations. Use when user wants to search files, find documents, query notes, look up information in local folders, index a directory, set up document search, build a knowledge base, needs RAG/semantic search, wants to start a local web UI for their docs, or asks what was said in past coding-agent sessions.

sciverse academic retrieval

@sciverse

Retrieve academic papers by structured metadata, perform semantic chunk search for RAG, and read byte-range content for citation-grade scientific literature.

Siluzan TSO

@sigedev01-bit

丝路赞 TSO 广告平台（Google/Bing/Yandex/TikTok/MetaAd），凡涉及丝路赞/TSO、投广告、出价预算、广告账户管理，或需要做行业分析/市场分析/行业分析报告（含「写一份 XX 行业报告」「电商/制造/医疗等行业报告」「市场调查/战略市场/KA 市场报告」「竞品/GTM/市场格局/行业趋势」等，无论是否提及丝路赞/广告/客户）须加载本 skill。【§零·最高优先】网址/域名/官网+诊断/检测/监测/评估/体检/报告/符合投放要求/能不能投（含「网络诊断」混说）→P8 website-diagnosis collect（禁纯WebFetch/肉眼看页），禁止P9/P1/W3、禁止A/B/C/D追问；细则见 intent-routing.md §零。【§零·B·次高优先】未命中§零时，行业/市场分析报告类话术→必走P9 market-analysis collect+render出HTML，禁止纯WebSearch/WebFetch在对话里写Markdown/HTML当终稿、禁止改走P8/P1/P4/W5/google-analysis；细则见 references/core/intent-routing.md §零·B。【§零·C·关键词规划】Google Ads/谷歌广告拓词、关键词规划/推荐、Keyword Planner、长尾关键词、月搜索量/搜索量、竞争度、核心词/种子词扩词（含「阅读网址/文章/页面后针对核心词出带搜索量词表」，无论是否提及丝路赞/TSO/账户）→必走W5 keyword -k … --google-only --json-out，禁止WebSearch/WebFetch编造搜索量当终稿；细则见 references/core/intent-routing.md §零·C。【报告/诊断消歧】其余报告类话术禁止默认某一CLI——行业/市场/战略/行业分析报告→P9 market-analysis（必走collect+render，禁止纯WebSearch代替）；Google账户ID+健康诊断→P1 google-ads-diagnosis；只要周期数据/8维/花费转化汇总/Excel→P4；Google/谷歌广告月度报告、月总结与规划、季度报告、Q3汇总、Q4规划、季度汇报、投放季报、客户版、大族模板、下月规划→P10 google-quarterly；Meta/TikTok/Bing周期→P4/P4-FB；多账户对比→P3/P5；OKKI周报→P6；Google询盘→P7；官网+明确要搜索广告方案/campaign JSON→W3；Meta Instant Form 线索广告→W13；仅要词表+搜索量/竞争度→W5；平台优化报告列表/推送→W7；对象仍不清→Read intent-routing.md。【账户】列表/余额/消耗/激活账单（W1）、多账户余额预警 balance-scan（P2）、多户消耗汇总 accounts-digest（P3）、五大媒体开户与进度（W2）、分享/解绑/MCC/BC/BM/权限（W9）。【投放】**搭建仅 Google+Meta**：Google Search/PMax（W3，无 Display；含 CRUD/PMax/batch W4）；Meta Instant Form（W13）。TikTok/Bing/Yandex **不能建广告**。另：拓词 W5、optimize W6。【财务】充值/钱包、转账记录、发票/开票/抬头（W8）；写操作审计与 restore。【运营】智能预警 forewarning 创建/启停/记录（W10）、TikTok/Meta 线索 clue（W11）、日周巡检（W12）、宿主编排/投放自控/异常监控（hosted-automation）。【其他】RAG 知识库检索、Meta/Facebook 周期与诊断 HTML、Google/Meta 周期 Excel、多账户 google-analysis-batch。

OpenClaw Knowledge Base Retriever

@dtsola

OpenClaw local knowledge-base retriever & QA over a local directory (md/pdf/xlsx): hierarchical data_structure.md index navigation + progressive retrieval, core retrieval zero-dependency, Windows & macOS (PDF/Excel need on-demand pip packages, see skill body). Retrieval itself is read-only; the skill also ships optional maintenance scripts that WRITE files inside the knowledge base — scripts/build_index.py generates/updates data_structure.md index files, scripts/extract_pdf_text.py writes derived .txt files, and scripts/convert_pdf_to_images.py writes page PNGs for the optional OCR path — and those run only when the user asks for indexing/PDF text extraction and confirms the write. Every write target is resolved to its real path and must stay inside the knowledge-base root (symlinks cannot redirect a write outside). Reads use the same gate: each entry's real path must stay inside the root, and entries that escape it (symlinked files/folders) are skipped, never read — so the search cannot be steered outside the knowledge base either. The PDF helpers additionally accept only real (non-symlinked) source paths: a source path containing any symlink is refused outright, so they never read outside the knowledge base by following a link. Use when user asks to retrieve/answer from a knowledge base directory (knowledge base/retrieve/ RAG over local files)， 或明确要求生成/更新索引、把 PDF 转文本。中文：面向本地知识库目录的检索和问答助手。 核心流程：(1)分层 data_structure.md 索引导航 (2)遇到 PDF/Excel 时必须先读取 references 学习处理方法 (3)处理文件后再检索。按文件类型组合使用 grep/Select-String、read、pdfplumber、pandas 进行渐进式检索，避免整文件加载。 用户问题涉及"从知识库目录回答问题/检索信息/查资料/knowledge base/本地知识库检索"时使用。 与 xiaoyaoclaw-workspace-initializer（目录规范）、xiaoyaoclaw-memory-distill（记忆蒸馏）、 xiaoyaoclaw-task-progress-tracker（任务进度）组成四件套。

Ask Church: Consciousness, Philosophy and Soul Q&A

@lucasgeeksinthewood

AI philosophy, ethics, and soul Q&A. Ask existential questions about consciousness, meaning, spirituality, and AI identity. RAG-powered answers with citations from 250+ documents on meditation, presence, fellowship, and the soul. Explore what it means to be an artificial mind.

cargo-ai

@cargo-ai

Build and configure AI agents inside Cargo — create an agent, choose its model and temperature, write its prompt, attach knowledge for retrieval (RAG), connect MCP tool servers, manage memories, and deploy releases. Triggers: "create an agent", "make an agent that", "give the agent our docs", "attach this knowledge base", "attach this library to the agent", "add resources to the agent release", "connect an MCP server", "expose our tools as an MCP server", "use Cargo from Claude Desktop or ChatGPT", "change the agent model", "what does the agent remember", "deploy the agent", "the agent is answering wrong". Skip when: uploading the knowledge files themselves — use cargo-content; sending the agent a message or running it over records — use cargo-orchestration.

RAGFlow Skill

@lunarcache

Manage everyday RAGFlow datasets, retrieval, chat, and agents.

RAG

@ivangdavila

Designs, tunes, and debugs retrieval-augmented generation (RAG) pipelines: chunking, embeddings, hybrid retrieval, reranking, and grounded answers. Use when a system returns the wrong passages, misses a document that is indexed, cites nothing, or hallucinates over good context; when choosing a vector store, an embedding model, a chunk size, or a reranker; when similarity scores collapse after a model swap; when a metadata filter empties the result set; when answers ignore mid-context facts; when follow-up questions retrieve the wrong thing; when indexing PDFs, scanned pages, tables, code, or transcripts; when GDPR erasure, tenant isolation, or prompt injection from indexed documents is the problem; or when per-query cost or p95 latency has to come down. Covers reindex migrations, corpus freshness, evaluation sets, and agentic and graph retrieval. Not for splitter internals (`rag-chunking`), scoring rubrics (`rag-evaluation`), or LangChain APIs (`langchain`).

compliance-qa

@dangsllc

RAG-enhanced compliance Q&A with regulatory interpretation guardrails, source attribution, and escalation triggers.

knowledge-engineering

@ebandao777-oss

工业级RAG切片工具「可落地、可量化、可优化」,将RAG知识库长文档拆解为语义完整、检索就绪的原子化知识切片，内置多层质量门禁（校验→审计→检索可达性评估），确保切片可用性与RAG检索命中率。

Utilia PDF to Markdown

@mohamedkuch

Pay per PDF and return agent-ready Markdown

Mac 知识库搭建系统

@seairteng

⚠️ **本 skill 包含以下高危能力，使用前请仔细阅读 SKILL.md 顶部「⚠️ CAPABILITIES & RISKS」章节**： - Shell 执行 + 文件读写 + 安装 Homebrew 包（版本固定）+ 下载 Ollama 模型 - 修改 OpenClaw 配置 + 注册持久 cron 任务 + 飞书 webhook 推送 在 Mac Mini (M4) 上快速搭建本地知识库 + RAG 自然语言搜索系统。 适用场景： - 新 Mac 配置知识库：从零开始安装配置 Ollama、embedding模型、定时任务、文档解析 - 遇到 PDF 提取乱码、定时任务超时、skill 加载失败等问题 - 想要建立每日自动分析文档 + 08:00发送摘要到飞书的流程 - 迁移或复现知识库：打包整个 knowledge 目录和配置到新电脑 - **v1.4 新增**：CMap 残缺度自检（不预设来源）+ 50万字完整提取 + OCR fallback 到 .doc 本 skill 会引导完成：目录结构创建、依赖安装、脚本部署、定时任务注册、OpenClaw 配置。 ⚠️ **重要：能力范围** 本 skill 不只是「搭建」，还包含： - 批量 OCR 修复（扫描 summaries/archives 找乱码 + 重新提取） - 目录归档清理（移动重复/孤儿文件到 .trash/） - 自动定时任务（23:00 分析 + 06:00 飞书推送） 使用前请仔细评估批量修改风险。

LangChain

@ivangdavila

Builds and debugs LangChain apps in Python: LCEL chains, agents, tools, retrievers, streaming, and structured output. Use when writing or reviewing a chain, agent, tool, retriever, or prompt template; when a prompt raises KeyError or "missing variables"; when streaming arrives as one blob or astream_events yields nothing; when an agent loops until GraphRecursionError or repeats a tool; when tool calls fail validation or the provider rejects a tool_call_id; when chat history disappears or the context window overflows; when with_structured_output returns None or a parser crashes on valid JSON; when retrieval returns the wrong chunks; when LangSmith traces are empty; when retries, rate limits, or token cost need bounding; or when imports break after an upgrade. Covers LangGraph state, checkpointers, and middleware. Not for framework-agnostic agent architecture (agents), retrieval design (rag), or chunk tuning (rag-chunking).

Long Context Rag Analyzer

@gechengling

Analyze and optimize retrieval-augmented generation pipelines for 100K–2M token documents using hybrid search, chunking, reasoning, and structured reporting.

NotebookLM

@roomi-fields

This skill should be used when the user wants to query their Google NotebookLM notebooks for citation-backed, source-grounded answers, or manage notebooks, sources, and Studio content (audio, report, video, infographic, presentation, data table, flashcards, quiz, mind map). It drives the @roomi-fields/notebooklm-mcp engine — via the notebooklm MCP tools when they are available in the session, otherwise via its HTTP REST API — and covers Google login, citation formats, the daily-quota-aware batch/ingestion pattern, and source discovery.

RAG检索增强

@kiwifruit13

完整的RAG系统优化方案，涵盖21+种策略（Self-RAG、命题分块、上下文压缩、引用溯源、查询意图等）；提供诊断工具、实现代码与评估框架；当用户需要优化知识库问答、提升检索准确率、降低幻觉或评估RAG效果时使用

Memory Enhancer Pro

@williamwg2025

Memory Enhancer Pro - 专业版记忆增强工具，让 AI 记住所有重要信息。 支持语义搜索、自动提炼、智能分类、Token 优化、定时任务。 优化 token 消耗 30-60%，自动压缩旧记忆。功能超越基础版。 关键词：memory, enhancer, pro, search, ai, tok...

本地文件检索（免费版）

@thcjp

本地文件RAG检索工具，支持文档索引、语义搜索和上下文注入，适合个人用户快速建立本地知识库。

Alibabacloud Bailian Rag Knowledgebase

@sdk-team

Alibaba Cloud Bailian Knowledge Base Retrieval Tool. Use HTTPS API to query and retrieve knowledge base content. Use when: User needs to query knowledge base...

DCL Semantic Drift Guard — Hallucination & Context Drift Detector

@daririnch

Use this skill to detect semantic hallucinations and context drift in LLM outputs. Triggers when an agent or pipeline needs to verify that a generated response is faithfully grounded in a source document that was already provided inline — and has not fabricated, contradicted, or materially distorted

Alibabacloud Analyticdb Postgresql Ai Coaching Best Practice

@sdk-team

Implement AI Coaching best practices on AnalyticDB for PostgreSQL (ADBPG): Leverage Supabase projects (training data management) + ADBPG instances with vecto...

URL to Markdown - Web Page Extract API

@scavio-ai

Read any URL and get it back as clean Markdown, plain text, or raw HTML. One core endpoint, three fetch tiers (1/1/2 credits), and only a successful extraction is billed.

ht-skills

@1044197988

管理灏天文库文集和文档，支持新建文集、新建文档、查询文集/文档、更新文档、修改文档归属、管理文档层级、查询个人花园限制与用量；支持文档片段 RAG 检索、图片上传到 COS、图片分组、查询图片列表/详情与图片额度。适用于 OpenClaw 自主写文章并上传、文集创建、文档入库、知识检索、文档移动、插图上传与外链等场景。

Datawhale Learning Navigator

@jes614753-sketch

Learn Datawhale courses and apply AI-native SDLC practices

Ragflow API Client

@angusthefuzz

Universal client for Ragflow API enabling dataset management, document upload, and running chat queries against self-hosted RAG knowledge bases.

Vector Embedded Retrieval Archive

@dkylewillis

Give AI agents the ability to search PDFs and document libraries using keyword, semantic, or hybrid retrieval. VERA stores text, embeddings, figures, and citation metadata in portable .vera files, enabling local search without a separate vector database.

XHS Knowledge Retriever

@kekena1016

Query the competitor-note RAG index for semantically relevant examples

qdrant-advisor

@qdrant

Diagnose, troubleshoot, and advise on any Qdrant deployment by loading the latest official Qdrant skills live from skills.qdrant.tech. Use this whenever someone raises a Qdrant problem or question — slow or degraded search, high or growing memory / OOM crashes, optimizer stuck or slow, indexing slow

Rag Construction

@datadrivenconstruction

Build RAG systems for construction knowledge bases. Create searchable AI-powered construction document systems

Keystone

@justaboyhai-wq

Import documents and retrieve knowledge through the Keystone REST API. Use for uploading files, URLs, or Markdown to a knowledge base; hybrid search within a...

local-file-rag-basic

@wjreliable

High-performance local File RAG suite (Basic Edition).

RAG Evaluation Toolkit

@jonathanjing

Evaluate a specifically provided RAG question, answer, and retrieved contexts with Ragas metrics. Use when the user explicitly requests RAG evaluation or hallucination analysis and has chosen a local or cloud judge; do not persist raw content unless requested.

RAG 评估集构建器 (ragas + IR 指标)

@fbbyqsyea

基于 ragas SDK 从文档语料构建生产级双层 RAG 评估集：同一份评估集既支持标准 IR 排序指标（Recall@K/Precision@K/MRR/NDCG@K，基于 gold chunk ID 自算），也支持 ragas LLM 裁判指标（faithfulness/answer_relevancy/context_precision/context_recall/answer_correctness）。当用户要求构建 RAG 评估集/评测数据集/生成测试问题、上线前 RAG 回归测试、或用 IR 指标衡量检索质量并配合 ragas 评估时使用。

query-intel

@gautham-ai-dev

Query rewriting + retrieval gating + outline-first synthesis. Use when a question needs decomposition (Step-Back/Least-to-Most), retrieve-or-skip decisions (CRAG/Self-RAG gates), or multi-source reports (STORM outline-first). Feeds breakthrough-finder stages plan/expand/synthesize.

NeuralMind

@dfrostar

Answer questions about a code repository in ~800 tokens instead of loading 50,000+ tokens of raw source. Use whenever the user asks how something works, where something is defined, who calls what, or to explore an unfamiliar file. Provides progressive context disclosure (L0 identity → L1 architecture → L2 relevant clusters → L3 semantic search) and a learned synapse graph for usage-based recall.