OpenClaw AI 技能

Ken Robinson's The Element — an executable toolkit for finding your天赋 and passion at the intersection of talent and personal passion. Covers 5 use cas

James C. Hunter's The Servant — an executable toolkit for servant leadership: leading through authority, not power; through service, not self-interest

Generate and edit images from the CLI using picture-it. Use this skill whenever the user asks to create, edit, or manipulate images — blog headers, so

Create portable OpenClaw cron health checks with deterministic scripts, config, validation, and reports.

OpenClaw 网关服务本地 fork 升级 skill。覆盖 backup → upgrade → env-merge → verify 全流程。专门处理 OpenClaw systemd service 升级时丢失 user 自定义环境变量（CUDA / LD_LIBRARY_PATH / Q

Mistral AI (mistral.ai). Use this skill for ANY Mistral AI request — reading, creating, updating, and deleting data. Whenever a task involves Mistral

Baidu Qianfan (qianfan.cloud.baidu.com). Use this skill for ANY Baidu Qianfan request — reading, creating, updating, and deleting data. Whenever a tas

TextCortex (textcortex.com). Use this skill for ANY TextCortex request — reading, creating, and updating data. Whenever a task involves TextCortex, us

Deploy, operate, and integrate the VSS 3.2 GA RT-Embed Video Embedding microservice. Covers Docker Compose bring-up, GPU and storage prerequisites, th

Install cuOpt for Python, C, or server via pip, conda, or Docker; verify the install. For building cuOpt from source, see cuopt-developer.

Playbook for launching, monitoring, stopping, and debugging NeMo-RL recipes on a Kubernetes cluster via the nrl-k8s CLI. Covers ephemeral vs long-live

Select, validate, patch, and deploy existing NVIDIA Dynamo Kubernetes recipes. Use for model/backend/GPU/deployment-mode recipe bring-up; use router-s

Use when the user wants to set up, scale, validate, or harden NVIDIA physical AI infrastructure for synthetic data generation workflows across local M

Use to ask the VSS agent's video_understanding tool a fresh visual question about a recorded clip. Not for prior tool output, search hits, or metadata

Search the user's local work memory (Office Memory / OMem) — a unified, locally-indexed wiki built from the user's emails, calendar events, documents,

NVIDIA RAG Blueprint — deploy, configure, troubleshoot, and manage. Handles any RAG action: deploy, install, start, enable, disable, toggle, change, c

Official NVIDIA-authored guidance for navigating PhysicsNeMo — pick the model, datapipe, or example for a SciML/AI4Science task (surrogates, forecasti

Use to run top-level VSS fusion search on archived video, or to ingest video files / RTSP streams for search. Not for ad-hoc Q&A or live captioning.

Explains operational tasks after the quickstart: listing sandboxes, status and health checks, logs, diagnostics, port forwards, multiple sandboxes, cr

Use for VSS alert workflows — real-time monitoring, Alert-Bridge subscriptions, Slack notifications, incident queries, camera onboarding. Not for non-