173 skills · sorted by relevance
Answer NemoClaw maintainer questions using policy references covering issue and pull request assessment, labels, project fields, releases, and competing contributions. It explains the relevant rules in plain language through a read-only workflow.
Reorganize NemoClaw documentation into focused pages with clearer navigation and a single home for each topic. Plan or implement structural changes while preserving useful information and existing published URLs, then validate routes, links, and builds.
Analyze the full retained history of one NemoClaw pull request to identify contributor, review, and automation delays. Generate a summary and an interactive timeline file, then compare observed timing with a default ten-minute target or a requested alternative.
Investigate failing or flaky NemoClaw end-to-end tests, which check complete workflows. Trace each assertion through its inputs and implementation, including cleanup and dependent jobs, and produce an evidence ledger to guide authorized repairs and reruns.
Review NemoClaw issues and pull requests, propose issue types, project priorities, statuses, and labels, then apply only approved changes. Supports individual items and batch triage, with explanations and a report of each update.
Prepare and create a signed NemoClaw release tag for a requested version, then monitor release workflows, documentation, and published images. It records maintainer decisions and drafts an announcement after verifying the remote tag.
Find official NemoClaw documentation for installation, configuration, operation, and troubleshooting. Get source-linked guidance tailored to the selected operating system, agent variant, and inference provider, with optional documentation MCP setup when requested.
Draft a NemoClaw release announcement from verified GitHub tags and shipped pull requests. Produce a local Markdown draft with an opening narrative, categorized changes, visible pull request links, and thanks to external contributors.
Continuously monitor automatic end-to-end tests on NemoClaw main, group failures by root cause, and coordinate fixes and peer reviews through GitHub. Track ownership and merge readiness while checking whether later runs confirm each repair.
Turn a named NemoClaw issue into an implementation plan with clear ownership, scope, completion criteria, and validation evidence. For larger changes, define independently useful steps, their dependencies, and delivery order.
Implement or review a managed runtime provider for NemoClaw. Check its required interfaces, activation requirements, saved provider identity, and lifecycle behavior, then report validation evidence and any remaining qualification requirements.
Update NemoClaw documentation after merged changes or audit it for outdated guidance. Verify current behavior against source and tests, edit the pages responsible for that guidance, and check affected links and generated variants.
Run NemoClaw live end-to-end tests, which check complete workflows, or inspect existing release evidence. Routes requests to local or trusted GitHub workflows and reports the tested commit, results, workflow link, and relevant job links.
Review a NemoClaw pull request for security risks by examining changed code, configuration, and dependencies. Assess nine categories and report findings with severity, file locations, and recommended fixes, alongside an overall assessment of whether it is safe to merge.
Close a NemoClaw maintenance day by consolidating documentation and changelog updates, reviewing merged and unfinished work, and preparing a release handoff. When requested, pass the version to the dedicated skill that verifies and creates the release tag.
Find open NemoClaw security pull requests marked Urgent or High in the project tracker. Connect them to issues, identify competing or superseding proposals, and recommend which request a maintainer should review first.
Official NVIDIA-authored guidance for PhysicsNeMo ShardTensor domain parallelism — integrate domain parallelism into training/inference scripts (new or existing) with DDP or FSDP2, write and register shard patches to enable new layers/ops, and bootstrap multi-GPU correctness tests. Use when working with ShardTensor, scatter_tensor, domain parallelism, sequence/spatial sharding, ring attention, DeviceMesh + DDP/FSDP2 hybrid parallelism, or physicsnemo.domain_parallel. Do NOT use for generic PyTorch DDP/FSDP setup without domain parallelism, picking a PhysicsNeMo model or example (use physicsnemo-discover), or non-distributed training questions.
The English summary is being prepared. Showing the original description.
Presents a risk framework for every configurable security control in NemoClaw. Use when evaluating security posture, reviewing sandbox security defaults, or assessing control trade-offs. Trigger keywords - nemoclaw security best practices, sandbox security controls risk framework, nemoclaw credential storage, credentials.json, api key security, openclaw security controls, nemoclaw security boundary, prompt injection, tool access control.
The English summary is being prepared. Showing the original description.
Add checks to LLM prompts and responses using Llama Guard 3, NeMo Guardrails, and LLM Guard. Configure content screening, conversation boundaries, and sensitive-data filtering, then measure blocking and false-positive rates with labeled test prompts.
Configure safety checks for LLM applications with NeMo Guardrails. Covers attempts to bypass safety rules, input and output validation, masking personal information, and checking factual claims through programmable rules and integrations.
Prepare training datasets for large language models with GPU-assisted cleaning. Covers duplicate removal, quality filtering, and personal information redaction, with workflows for text, images, video, and audio using NeMo Curator.
Find open issues affected by a proposed code change. Identify additional problems it may fix or requested behavior it may conflict with, then report supporting code differences, issue symptoms, and confidence levels.
Add safety checks to LLM applications with NeMo Guardrails. This skill guides input and output validation, detection of attempts to bypass safety rules, personal information masking, and checks for unsupported or inaccurate answers.
Prepare training datasets for large language models with GPU-assisted cleaning. Covers duplicate removal, quality filtering, and personal information redaction, with workflows for text, images, video, and audio using NeMo Curator.