Explore

Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or genera

in the skill textInspect a Corpus** -> Proceed to [2. Getting / Inspecting a RAG Engine Corpus]. * **Search for Contexts** -> Proceed to [3. Retrieving Contexts]. * **Answer questions using RAG

Official·Skill·Apache-2.0·★ 21k in collection·No key

Provides workflows to optimize BigQuery environments (capacity planning, editions), storage assets (partitioning, clustering, storage lifecycles, billing models), and SQL queries. Use when optimizing

in the skill textexpiration, optimizing individual SQL queries, or evaluating acceleration structures (search indexes, materialized views, BI Engine). Do not use for raw usage reporting (use bigquery

Official·Skill·Apache-2.0·★ 21k in collection·No key

Retrieve, query, and identify relevant Cloud Monitoring metric descriptors on Google Cloud for a service or resource (such as Compute Engine, Spanner, BigQuery, Cloud Run, Cloud SQL, Pub/Sub, Cloud St

in the skill textsuch as Compute Engine, Spanner, BigQuery, Cloud Run, Cloud SQL, Pub/Sub, Cloud Storage, etc.). Use when asked to find, list, search, or discover GCP

Official·Skill·Apache-2.0·★ 21k in collection·No key

Discovers requirements, and generates architectural, design, and deployment guidance for a retrieval-augmented generation (RAG)-capable enterprise search system in Google Cloud. Use when users need a

in the skill textRAG-enabled conversational search solution for private enterprise content by using an AlloyDB database, Cloud Storage, and a Google Kubernetes Engine (GKE) cluster

Official·Skill·Apache-2.0·★ 21k in collection·No key

A lightweight, lightning-fast, in-process vector database

Skill·Apache-2.0·★ 16k·No key

INVOKE THIS SKILL when building ANY retrieval-augmented generation (RAG) system. Covers document loaders, RecursiveCharacterTextSplitter, embeddings (OpenAI), and vector stores (Chroma, FAISS, Pinecon

in the skill textRetrieve**: Query → Embed → Search → Return docs 3. **Generate**: Docs + Query → LLM → Response **Key Components:** - **Document Loaders**: Ingest data from files, web, databases - **Text Splitters

Official·Skill·MIT·★ 1.3k in collection·No key

Build a local-business lead database from Google Maps in one Apify pipeline: search by target audience + geography, enrich each place with company contacts from its website, leads enrichment (names, e

in the skill textlocal-business lead database from Google Maps in one Apify pipeline: search by target audience + geography, enrich each place with company contacts from its

Official·Skill·Apache-2.0·★ 275 in collection·No key

Guides Qdrant monitoring setup including Prometheus scraping, health probes, Hybrid Cloud metrics, alerting, and log centralization. Use when someone asks 'how to set up monitoring', 'Prometheus confi

Official·Skill·Apache-2.0·★ 256 in collection·No key

Guides building on Qdrant Edge, the embedded in-process shard. Use when someone asks 'how to sync Edge with the server', 'keep a local shard in sync with Qdrant Cloud', 'BM25 or keyword search on Edge

in the skill textdevice', 'Edge snapshots', 'apply a partial snapshot', 'why is my Edge search empty after inserts', or is writing custom sync, BM25, or fusion code

Official·Skill·Apache-2.0·★ 256 in collection·No key

Diagnoses Qdrant production issues using metrics and observability tools. Use when someone reports 'optimizer stuck', 'indexing too slow', 'memory too high', 'OOM crash', 'queries are slow', 'latency

in the skill textslow', 'memory too high', 'OOM crash', 'queries are slow', 'latency spike', or 'search was fast now it's slow'. Also use when performance degrades

Official·Skill·Apache-2.0·★ 256 in collection·No key

Ontology-Augmented Generation for AI agents.

in the skill textLAN access, set both `KB_WEB_HOST` and `KB_WEB_TOKEN`. Configure `KB_SEARCH_TOKEN` before using protected search endpoints remotely. The

Skill·MIT·★ 60·No key

Automate your job search with your favorite coding agent. Skills, guides, and scripts that any agent (Devin, Claude, Cursor, opencode) consumes to search, apply, and track jobs on your behalf.

in the skill textlinkedin-invite.js # Send LinkedIn connection requests linkedin-easy-apply.js # Search + apply to Easy Apply jobs gmail-send.js # Send emails via Gmail web UI with CV attached pipeline.js # Kanban

Skill·MIT·★ 33·No key

Memseek is an open source declarative context engine for AI agents. Define agent memory in versioned YAML — like Terraform for infrastructure. Memseek learns from everything you record and gives your

in the skill textMemseek Record everything. Turn records into knowledge. **The declarative context engine for AI agents.** Define agent memory in versioned YAML — like Terraform for infrastructure. Memseek learns

Skill·Apache-2.0·★ 11·No key

DeepSeek Harness 社区记忆插件集：中文与扩展汉字全文检索、工具去重、混合召回、跨会话核心记忆、可追溯压缩与技能管理。8 个包、97 项单测；已验证 DSH 0.2.0-rc.2 完整 Web 宿主、真实持久化与冷重启。用户固定的记忆与技能受来源保护。

in the skill text跨会话核心记忆、可追溯压缩和技能管理。用户固定的记忆与技能带来源记录，模型工具与后台进化无法改写。Phase 0–3 已实现；CJK 后端已通过完整 `0.2.0-rc.2` Web 宿主的活会话与冷历史验证。 > **宿主版本要求**：DSH **`>=0.1.5-rc.3 ` 追加 Exact Sources 定位符（spill 路径 / 文件路径 / seq

Skill·MIT·★ 12·No key

Claude Skills for connecting Claude.ai to local Weaviate vector databases - manage collections, ingest data, and query with RAG

in the skill textshare and reuse across projects - **No Deployment**: Works directly in Claude.ai web or Claude Desktop - **Client-Friendly**: Just download folders and start using - **Local-First**: Run

Skill·MIT·★ 39·No key

Expert SurrealDB 3 skill for AI coding agents (Claude, Codex, Amp, Gemini CLI, Copilot, Cursor). SurrealQL, multi-model data modeling, graph queries, vector search, WASM extensions, and full ecosystem

in the skill textstrategies (unique, full-text search analyzers, HNSW vector), EXPLAIN statement for query analysis, batch operations, connection pooling, storage engine trade-offs by workload, parallel

Skill·MIT·★ 34·No key

Official AI Agent skills for building with Zvec vector database

in the skill textProxima engine. No server or external infrastructure required, ready to use out of the box. **Key Features:** - ⚡ Sub-millisecond search latency, supporting billions

Skill·Apache-2.0·★ 21·No key

Vector database BM25 + dense hybrid search reranking engine

Skill·Link only·★ 9

Local-first, PII-safe job-hunting copilot. Scrape boards, kanban-track applications, auto-fill ATS forms, tailor resumes per JD — Claude Code skill + CLI + local webapp.

in the skill textjob-hunter > A self-hosted, PII-safe job-search command center — for Claude Code, Codex, Cursor, and the terminal. ![CI ]( ![License: Apache-2.0 ](LICENSE

Skill·Apache-2.0·★ 3·Few stars·No key

Persistent AI agent architecture — memory graph in SQLite, Go maintenance pipeline, Signal integration, OAuth2

in the skill textthinking behind it. ## Architecture Architecture Overview ## What's Here ### Cortex — The Memory Engine A Go binary that manages an agent's long-term memory

Skill·MIT·★ 3·Few stars·No key