CtrlK
BlogDocsLog inGet started
Tessl Logo

nemoclaw-user-guide

Guides human users' AI agents to the NemoClaw docs MCP server and canonical Fern documentation in Markdown form. Use when users ask how to install, configure, operate, troubleshoot, secure, or learn NemoClaw with an AI coding assistant. Trigger keywords - nemoclaw docs, use nemoclaw with ai agent, nemoclaw mcp docs, nemoclaw install help, nemoclaw quickstart, nemoclaw markdown docs, llms.txt, agent skills.

66

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/nemoclaw-user-guide/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 well-structured, lean routing skill with concrete executable commands, a clear retrieval sequence, and good external-document navigation. It consistently sits at the strong-but-not-exemplary tier due to a mildly redundant URL list and high-level guidance for non-Claude MCP clients.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence, with no padding about what NemoClaw is, but the 14-entry 'Starting Pages' URL list partially duplicates the llms.txt index instruction it already gives, a minor instance of content that could be trimmed.

4 / 5

Actionability

Provides a copy-paste-ready command ('claude mcp add --transport http fern-docs https://...'), specific URLs, and a concrete .html→.md transformation rule, with minor gaps for Cursor and generic MCP clients whose configuration steps are left high-level.

4 / 5

Workflow Clarity

The numbered 'Retrieval Order' is a clear sequenced workflow and 'Response Requirements' directs recommending a next verification command after each step, but there is no explicit error-recovery feedback loop for failed fetches.

4 / 5

Progressive Disclosure

Well-organized into clearly headed sections that point one level deep to live external materials (llms.txt, MCP server, named .md pages) with clear navigation; minor gap is the inline full URL directory rather than deferring entirely to the llms.txt index.

4 / 5

Total

16

/

20

Passed

Description

83%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 strong, complete description that clearly answers both what the skill does and when to use it, with a rich set of natural trigger keywords. It is held back from the top tier only by generic action verbs and one generic trigger ('agent skills') that risks minor overlap.

DimensionReasoningScore

Specificity

Names the NemoClaw domain and lists several concrete action verbs — 'install, configure, operate, troubleshoot, secure, or learn' — but the actions are generic verbs rather than concrete noun-actions, leaving minor coverage gaps versus the comprehensive anchor.

4 / 5

Completeness

Clearly states both what ('Guides human users' AI agents to the NemoClaw docs MCP server and canonical Fern documentation in Markdown form') and an explicit when ('Use when users ask how to install, configure, operate...'), reinforced with concrete trigger keywords.

5 / 5

Trigger Term Quality

Good keyword coverage with natural phrases and synonyms ('nemoclaw docs', 'nemoclaw markdown docs', 'nemoclaw mcp docs', 'nemoclaw quickstart', 'llms.txt'), though a few natural variations (e.g. 'tutorial', 'setup', 'guide') are missing and 'agent skills' is generic.

4 / 5

Distinctiveness Conflict Risk

The NemoClaw niche is distinct with specific triggers, but the generic 'agent skills' keyword and the broad 'AI coding assistant' framing create minor overlap risk with other agent-oriented skills.

4 / 5

Total

17

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
NVIDIA/NemoClaw
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.