OpenClaw AI 技能

Describes the NemoClaw plugin and blueprint architecture and how they orchestrate the OpenClaw sandbox. Use when looking up architecture, plugin struc

Inspects sandbox health, traces agent behavior, and diagnoses problems. Use when monitoring a running sandbox, debugging agent issues, or checking san

Adds, removes, or modifies allowed endpoints in the sandbox policy. Use when customizing network policy, changing egress rules, or configuring sandbox

Installs NemoClaw, launches a sandbox, and runs the first agent prompt. Use when onboarding, installing, or launching a NemoClaw sandbox for the first

Explains how to run NemoClaw on a remote GPU instance, including the deprecated Brev compatibility path and the preferred installer plus onboard flow.

Presents a risk framework for every configurable security control in NemoClaw. Use when evaluating security posture, reviewing sandbox security defaul

Connects NemoClaw to a local inference server. Use when setting up Ollama, vLLM, TensorRT-LLM, NIM, or any OpenAI-compatible local model server with N

Manage durable working-session memory for coding agents. Use when a user asks to preserve or recover agent context across disconnects, VS Code restart

Documentation conventions for NeMo-RL. Covers docs/index.md updates and docstring format. Do NOT use for: bug fixes, test fixes, dependency bumps, ref

Brev instance operating guidance for NeMo-RL agents working in /home/ubuntu/RL with limited workspace disk, a larger /ephemeral volume, and optional /

Autonomous NeMo-RL research agent workflow for directed hypothesis testing and open-ended discovery. Guides agents through the full experiment lifecyc

Resiliency features in Megatron Bridge including fault tolerance, straggler detection, in-process restart, preemption, and re-run state machine.

Recommend and customize Megatron Bridge recipes for a user's model, GPU count, and training goal. Indexes library recipes (pretrain/SFT/PEFT) and perf

Operational guide for enabling TP, DP, and PP communication overlap in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verificati

Validate and use packed sequences and long-context training in Megatron-Bridge, distinguishing offline packed SFT for LLMs from in-batch packing for V

Operational guide for choosing and combining parallelism strategies in Megatron Bridge, including sizing rules, hardware topology mapping, and combine

Practical guidance for training MoE VLMs in Megatron Bridge. Compares FSDP and 3D-parallel approaches, using rounded lessons from Qwen3-VL, Qwen3-Next

Systematic workflow for MoE training optimization in Megatron Bridge, based on the Megatron-Core MoE paper. Covers the Three Walls framework, parallel

Long-context MoE training guidance for Megatron Bridge. Covers CP sizing, selective recompute, dispatcher choices, and practical patterns from DSV3, Q

Representative MoE training playbooks by hardware platform and model family. Summarizes rounded throughput bands, parallelism patterns, and common tun