nemoclaw-skills-guide

Start here. Introduces what NemoClaw is, what agent skills are available, and which skill to use for a given task. Use when discovering NemoClaw capabilities, choosing the right skill, or orienting in the project. Trigger keywords - skills, capabilities, what can I do, help, guide, index, overview, start here.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/nemoclaw-skills-guide/SKILL.md

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 clean, well-structured index skill that earns consistent 4s: lean catalog, actionable role-based routing, a clear getting-started sequence, and appropriate progressive disclosure with one-level references. The main gap is the unspecified mechanism for actually loading a chosen skill.

Suggestions

Add a brief, concrete instruction on how to load a selected skill (e.g. the exact command or invocation) so the routing flow is fully executable end-to-end.

Break the long comma-list in the maintainer-bucket intro into a short bulleted summary to improve scannability without adding length.

Dimension	Reasoning	Score
Conciseness	The catalog is dense and well-organized with one-sentence skill summaries and no padding of concepts Claude already knows; the maintainer-bucket intro is a long run-on list but information-dense rather than verbose.	4 / 5
Actionability	Concrete, actionable guidance for an instruction-only index skill: identifies role buckets, lists specific skill names with summaries, and directs the agent to present applicable skills and recommend a starting skill, though the mechanism for 'loading' a named skill is left implicit.	4 / 5
Workflow Clarity	The getting-started flow is a clear sequence (ask role → present applicable skills → recommend starting skill) with the cumulative-skills table clarifying scope; no destructive or batch operations so no validation cap applies, but explicit checkpoints for the role-disambiguation step are minor.	4 / 5
Progressive Disclosure	Appropriately structured as an overview/index with clearly labeled sections (buckets, catalog, getting started) pointing outward to individual skills; one inline reference ([nemoclaw-maintainer-e2e](../nemoclaw-maintainer-e2e/SKILL.md)) is one level deep and well-signaled, with no bundle files to misorganize.	4 / 5
	Total	16 / 20 Passed

Description

78%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 frontmatter description that clearly states purpose and usage with explicit trigger guidance, scoring well on completeness and trigger quality. Specificity is capped by the inherently broad nature of an index skill, and a couple of generic triggers invite minor conflict risk.

Suggestions

Tighten the 'what' with one or two more concrete actions (e.g. 'lists every shipped skill by audience and maps a task to the right one') to lift specificity toward the 4-5 anchors.

Consider narrowing the generic 'help' trigger or pairing it with a NemoClaw-scoped qualifier to reduce overlap risk with general-purpose help skills.

Dimension	Reasoning	Score
Specificity	Names the domain (NemoClaw skills) and a couple concrete actions ('Introduces what NemoClaw is, what agent skills are available, and which skill to use'), but as an index skill the actions are broad rather than a comprehensive list of specific operations.	3 / 5
Completeness	Explicitly answers both 'what' ('Introduces what NemoClaw is... which skill to use for a given task') and 'when' ('Use when discovering NemoClaw capabilities, choosing the right skill, or orienting in the project') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases a user would actually say ('help', 'guide', 'index', 'overview', 'start here', 'what can I do') alongside an explicit trigger keyword list; good coverage though a few common synonyms are absent.	4 / 5
Distinctiveness Conflict Risk	It carves a clear project-scoped orientation niche ('Start here', NemoClaw index), but generic triggers like 'help' and 'what can I do' carry minor overlap risk with other skills.	4 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: NVIDIA/NemoClaw
Path: .agents/skills/nemoclaw-skills-guide/SKILL.md
Commit: e94c06f

Reviewed: 5 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.