nemoclaw-user-get-started

Installs NemoClaw, launches a sandbox, and runs the first agent prompt. Use when onboarding, installing, or launching a NemoClaw sandbox for the first time. Trigger keywords - nemoclaw quickstart, install nemoclaw openclaw sandbox, nemohermes quickstart, hermes agent nemoclaw, run hermes openshell sandbox, nemoclaw prerequisites, nemoclaw supported platforms, nemoclaw hardware software, nemoclaw windows wsl2 setup, nemoclaw install windows docker desktop.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Quality

Content

85%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with a clear sequenced workflow and well-structured one-level-deep references, but it carries some verbosity in verbatim transcript blocks and platform-specific prose that could be trimmed. Overall a strong, well-organized quickstart skill.

Suggestions

Replace the verbatim 'Review configuration' and 'NemoClaw is ready' ASCII transcript blocks with a short description of what fields to verify, since the exact box formatting is not needed to act.

Tighten the platform-specific installer behavior (Docker install, docker group changes, express install) into a compact table or bulleted env-var list instead of multi-paragraph prose.

Trim wizard prompt-by-prompt detail that is already covered in references/quickstart-details.md out of the main body to reduce overlap and save tokens.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and product-specific, but verbatim transcript blocks (the 'Review configuration' and 'NemoClaw is ready' ASCII boxes) and multi-paragraph platform prose could be tightened; not 3 because not every token earns its place, not 1 because it avoids explaining concepts Claude already knows.	2 / 3
Actionability	Provides copy-paste-ready executable commands such as 'curl -fsSL https://www.nemoclaw.sh \| bash', 'nemoclaw my-gpt-claw connect', and 'nemoclaw my-gpt-claw dashboard-url --quiet', with concrete env-var examples for non-interactive runs.	3 / 3
Workflow Clarity	The onboarding flow is clearly sequenced (install, review config, confirm, web search/messaging, network policy, ready) with an explicit confirmation checkpoint ('Apply this configuration? [Y/n]') and a reachability verification plus port-conflict rollback before the summary.	3 / 3
Progressive Disclosure	SKILL.md acts as an overview with well-signaled, one-level-deep references — a 'References' section lists each existing file (prerequisites.md, quickstart-details.md, windows-preparation.md, quickstart-hermes.md) with a 'Load ... when ...' trigger, and all referenced paths resolve to real bundle files.	3 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is concise, third-person, and clearly answers both what the skill does and when to use it, with a strong set of natural trigger keywords. It is a strong, low-conflict description.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions in third person — 'Installs NemoClaw, launches a sandbox, and runs the first agent prompt' — matching the anchor for listing several specific concrete actions.	3 / 3
Completeness	Explicitly states what it does and when to use it ('Use when onboarding, installing, or launching a NemoClaw sandbox for the first time'), satisfying both the 'what' and 'when' requirements with explicit triggers.	3 / 3
Trigger Term Quality	A dedicated 'Trigger keywords' clause gives broad natural-phrase coverage a user would actually say ('nemoclaw quickstart', 'install nemoclaw openclaw sandbox', 'nemoclaw windows wsl2 setup'), matching the good-coverage anchor.	3 / 3
Distinctiveness Conflict Risk	The NemoClaw/OpenClaw quickstart niche is narrow and the triggers are product-specific, making conflict with other skills unlikely; not the level below because the triggers are distinctive rather than merely 'somewhat specific'.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: openai/plugins
Path: plugins/nvidia/skills/nemoclaw-user-get-started/SKILL.md
Commit: 11c74d6

Reviewed: 17 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.