CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

nemoclaw-user-guide

Find official NemoClaw documentation for installation, configuration, operation, or troubleshooting. Also handles requested docs MCP setup.

65

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is nemoclaw-user-guide in NVIDIA/NemoClaw

SKILL.md
Quality
Evals
Security

Quality

Content

86%Weight 40%Scale 1-5

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

A lean, highly actionable docs-routing skill: a concrete retrieval ladder with fallbacks, a per-task routing table, and exemplary one-level-deep progressive disclosure gated by explicit read-conditions. The only tightening opportunities are merging the two overlapping secrets rules and embedding the verification requirement as a checkpoint in the retrieval workflow itself.

DimensionReasoningScore

Conciseness

The body is lean and imperative with no explanations of concepts Claude already knows, and every section earns its place. It is not a 5 because of a trimmable near-duplicate pair: 'Stop before requesting credentials, API keys, bot tokens, or private URLs' and 'Never ask the user to paste secrets into chat' state overlapping rules.

4 / 5

Actionability

Fully executable guidance throughout: a concrete index URL ('https://docs.nvidia.com/nemoclaw/llms.txt'), a named MCP tool ('searchDocs'), a mechanical URL transform rule (.html → .md), a concrete placeholder ('<PASTE_YOUR_API_KEY_HERE>'), and a per-task routing table. As an instruction-only skill, the absence of code is not penalized — the guidance is directly actionable.

5 / 5

Workflow Clarity

The six-step Retrieval Order is a clear, well-sequenced workflow with explicit fallbacks (MCP → local index → fetch, plus HTML-to-MD recovery) and a verification requirement ('Verify the requested setup or recovery outcome with the relevant documented check'). It falls short of 5 because that verification is a single generic closing line rather than checkpoints embedded at the steps where outcomes are produced.

4 / 5

Progressive Disclosure

The single bundle file (references/docs-access.md) exists at exactly the referenced path, is one level deep, and is explicitly gated: 'Read [Docs Access](references/docs-access.md) when the user requests MCP configuration or when starting an installation needs direct links... Ordinary docs questions can use the index without reading that reference.' That is a model conditional reference with a clear not-needed signal.

5 / 5

Total

18

/

20

Passed

Description

70%Weight 40%Scale 1-5

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

A concise, third-person description with a clear niche and good natural keyword coverage, but it states only the 'what' and lacks an explicit 'Use when...' trigger clause, which caps its completeness. Adding trigger guidance would lift it into the top tier.

Suggestions

Append an explicit trigger clause, e.g., 'Use when the user asks about installing, configuring, operating, or troubleshooting NemoClaw, or requests docs MCP setup.'

Include common natural synonyms users would say — e.g., 'set up', 'docs lookup', 'errors' — alongside the current keywords.

Mirror the body's task-routing vocabulary (inference, sandbox, network policy, CLI) in the description so it triggers on those sub-topics too.

DimensionReasoningScore

Specificity

The description names the domain (NemoClaw documentation) and several concrete service areas — 'installation, configuration, operation, or troubleshooting' plus 'requested docs MCP setup'. It falls short of 5 because the core action ('Find ... documentation') is a single generic verb applied to topic areas rather than multiple distinct concrete actions.

4 / 5

Completeness

The 'what' is clear ('Find official NemoClaw documentation for installation, configuration, operation, or troubleshooting'), but there is no 'Use when...' clause or equivalent explicit trigger guidance — 'Also handles requested docs MCP setup' only weakly implies a trigger, so per the judging guidelines completeness is capped at 3.

3 / 5

Trigger Term Quality

Natural phrases users would say are present — 'installation', 'configuration', 'troubleshooting', 'docs MCP setup', and the product name 'NemoClaw'. A few common variations are missing (e.g., 'set up', 'docs lookup', 'errors', 'debug'), keeping it below the comprehensive-synonym coverage of a 5.

4 / 5

Distinctiveness Conflict Risk

It occupies a clear niche — official NemoClaw documentation and its docs MCP setup — with a named product and distinct trigger terms, making conflict with other skills minimal.

5 / 5

Total

16

/

20

Passed

Validation

100%

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

NVIDIA/NemoClaw

Path

.agents/skills/nemoclaw-user-guide/SKILL.md

Reviewed

Table of Contents

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.