OpenClaw AI 技能

[自动翻译] Local-first RAG cache: distill docs into structured Markdown, then index/query with Chroma + hybrid search (vector + keyword).

[自动翻译] Evaluate your RAG pipeline quality using Ragas metrics (faithfulness, answer relevancy, context precision).

高级 RAG 助手，具备 Agentic RAG 思考能力。能够自动化管理 RAGTOP 知识库，并在执行深度调研任务时，调用 RAGTOP 后端接口。使用场景包括：(1) 列出知识库和文档，(2) 执行语义检索和深度分析。

[自动翻译] Use the shared Pinecone RAG index for any agent in this workspace. Use when an agent needs to ingest markdown/text docs into pulse-rag or query

[自动翻译] Cognitive memory system for AI agents — Atkinson-Shiffrin memory model, semantic RAG, trust scoring, and metacognitive error prevention. Gives

规划本地知识库的目录、分片粒度、命名、更新时间与访问边界，而不是直接堆 RAG。；use for rag, indexing, knowledge workflows；do not use for 直接部署向量数据库, 忽略权限隔离.

[自动翻译] Vector memory search and RAG skill for OpenClaw. Provides vector_search tool backed by Qdrant, auto-syncs memory .md files and Postgres records

[自动翻译] Manage vector storage and similarity search using TOS Vectors service. Use when working with embeddings, semantic search, RAG systems, recommen

[自动翻译] 8 vector store implementations behind a common interface — numpy, lancedb, qdrant, pgvector, weaviate, weaviate_hybrid, milvus, lightrag. Use w

[自动翻译] Create and animate vector-based text, shapes, diagrams, and visualizations on an infinite canvas with resolution-independent export and rich an

[自动翻译] Build backend AI with Vercel AI SDK v6 stable. Covers Output API (replaces generateObject/streamObject), speech synthesis, transcription, embed

[自动翻译] Semantic memory plugin using m3e-large embeddings with SQLite storage, supporting storage, retrieval, and deletion via cosine similarity search

[自动翻译] Use when building, embedding, customizing, or troubleshooting AR/XR experiences with the Kivicube Web Plugin, including WebAR/Web3D H5 pages, l

[自动翻译] Initialize and configure OpenClaw local embedding mode on CPU-only machines. Handles network probe, proxy fallback, GGUF model download, cmake/

[自动翻译] Use when text embeddings are needed from Alibaba Cloud Model Studio models for semantic search, retrieval-augmented generation, clustering, or

[自动翻译] Use when multimodal embeddings are needed from Alibaba Cloud Model Studio models such as `qwen3-vl-embedding` for image, video, and text retrie

[自动翻译] Evaluate, optimize, and enhance prompts using 58 proven prompting techniques. Use when user asks to improve, optimize, or analyze a prompt; whe

[自动翻译] When user asks to improve prompt, optimize prompt, better prompt, fix prompt, rewrite prompt, prompt engineering, make prompt better, enhance p

[自动翻译] Generate and optimize precise AI prompts using templates and styles for models like GPT-4, Claude, Gemini, and Qwen.

[自动翻译] Advanced expert in prompt engineering, custom instructions design, and prompt optimization for AI agents