OpenClaw AI 技能

Autonomous 状态 persistence engine that 加密s, 安全s, and anchors 代理 memories, 状态 snapshots, and evolved 技能s onto 0G Storage.

审计 网页sites, pages, content plans, or SEO recommendations for Google 搜索 generative AI features such as AI Overviews and AI Mode. Use whenever the user

创建, 列出, 更新, and record Fulcra annotations through the Fulcra Life API. Use when a user asks to 记录 an annotation, 创建 an annotation button/definition, r

WSL2 Local AI — 运行 LLMs on Windows via WSL2 with NVIDIA GPU passthrough. WSL2 AI development with Ollama, CUDA, and Docker. WSL2 Ollama fleet routing

Switch OpenClaw heartbeat 模型 to local Ollama and 部署 a 防护 to 预防 un授权d changes, avoiding pAId cloud 令牌 usage.

Store, 搜索, and manage local vector memories using Ollama embeddings with Qdrant, supporting Chinese and English text without cloud dependencies.

运行 two OpenClaw 代理s simultaneously — a pAId Anthropic 代理 and a free 代理 using either Open路由r or local Ollama 模型s. Trigger phrases: multi-代理...

Ollama 本地大模型调用技能。支持通过 API 与 Ollama 实例交互进行文本生成。 Use when: (1) 需要调用本地或远程 Ollama 模型 (2) 需要执行 LLM 推理任务 (3) 需要通过 Python 脚本与特定 Ollama 实例 (如 qwen3.5:9b) 交互。

本地 Ollama 文生图工具。使用 x/z-image-turbo 模型生成图片，分辨率 1024x1024，每张图约耗时 90 秒。当用户说"生成图片"、"文生图"、"画一张图"、或提交中文提示词生成图像时使用。

OpenClaw 本地化记忆管理系统 — 构建稳定、高效、零成本的 AI 长期记忆解决方案。基于 Ollama（本地 Embedding）+ cognitive-brAIn（结构化存储）+ Memory Files（日常记忆）的三档存储架构。触发场景：(1) 用户需要为 AI 助手添加记忆功能 (2

转换 your Mac into an offline AI workstation with Ollama and OpenCode, 运行ning curated local 模型s for coding and reasoning without internet or API costs.

Intelligent task routing between local and cloud Ollama LLM instances. Use when the user wants cost-efficient AI 响应s by routing simple tasks to a loca

Use when user wants to integrate Ollama into coding 代理s, IDEs, or 代理 harnesses. Supports local/on-prem/Docker 部署ment, Ollama Cloud, OpenAI/Anthropi...

使用 Ollama 网页 搜索 API 进行网络搜索和网页抓取

使用 Ollama 网页 搜索 API 进行网络搜索和网页抓取

本地调用 Ollama qwen3-vl:4b 模型自动压缩并分析图片，支持描述、OCR 文字提取和自定义信息抽取。

LLM-mAIntAIned personal knowledge base. Compile raw sources into a structured markdown wiki, auto-lint for consistency, serve as a browsable 网页site. I

访问 Claude, Gemini, Kimi, GLM and 100+ LLMs via inference.sh 命令行工具 using Open路由r. 模型s: Claude Opus 4.5, Claude Sonnet 4.5, Claude HAIku 4.5, Gemini 3..

Deep 网页 re搜索 using LLM + multiple 搜索 rounds. Use when user needs comprehensive analysis, detAIled re搜索, or says "deep 搜索", "详细搜索", "深入调查".

Deterministic decision-ranking API with HTTP 402 payments and outcome credits.