发现优质的 AI Agent 技能

<!-- 自动生成部分由 site_monitor.py 维护，手动添加的事件请在 MANUAL 区域 --> - 2026-02-26 | AI Essentials for Business — 课程 | [AI商业基础] @time:08:15-11:15 @src:canvas @id:canvas-aie-class-0226 - 2026-02-26 | 飞行训练 KGAI N586MA Piper Archer III | [飞行] @time:14:00-17:00 @src:fsp @id:fsp-20260226 - 2026-02-27 | Advanced Database Management — 课程 | [高级数据库] @time:08:15-11:15 @src:canvas @id:canvas-adb-class-0227 - 2026-02-27 | Internet Systems — 课程 | [互联网系统] @time:14:30-17:30 @src:canvas @id:canvas-is-class-0227

来自 openclaw/skills 技能

来自 openclaw/skills 技能

RAG and semantic search via OpenViking Context Database MCP server. Query documents, search knowledge base, add files/URLs to vector memory. Use for document Q&A, knowledge management, AI agent memory, file search, semantic retrieval. Triggers on "openviking", "search documents", "semantic search", "knowledge base", "vector database", "RAG", "query pdf", "document query", "add resource".

OpenViking is ByteDance's open-source **Context Database** designed for AI Agents — a next-generation RAG system that replaces flat vector storage with a filesystem paradigm for managing memories, resources, and skills.

Multi-agent workflow pipelines on OpenClaw. Each workflow is a sequence of specialized agents (planner, developer, verifier, tester, reviewer) that execute autonomously via cron jobs polling a shared SQLite database.

Production-ready Qdrant vector database operations for AI agents. Complete toolkit for semantic search, document ingestion, collection management, backups, and migrations.

An agent application is composed of one or more agents: - **Root agent (steering agent)**: Primary entry point and orchestrator. Handles main user interactions, understands overall goals, and delegates tasks. - **Sub-agent (child agent)**: Specialized agent for specific tasks/domains (e.g., searching a database). Promotes modularity.

This database provides a point-in-time reference for indicators of compromise (IOCs) tracked by the Scam Guards Shield Layer.

Manage contacts, relationships, and follow-ups with markdown files. No database needed.

The storage APIs can be used to store data in Raycast's local encrypted database.

Searchable design database with CLI for generating complete design systems from natural language queries.