CtrlK
BlogDocsLog inGet started
Tessl Logo

nemotron-add-model

Onboard a new model family (Nemotron or third-party) into skills/ — paper chunks, recipe summaries, context packs, and model card. Use when a contributor wants downstream skills like /nemotron-customize to be able to route to a new model.

71

Quality

86%

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

SKILL.md
Quality
Evals
Security

Quality

Content

81%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.

The body is a tight, highly structured instruction-only skill with a clear sequenced workflow and explicit validation feedback loops. Main gaps are repeated restatements of the same rules and the absence of reusable file templates.

Suggestions

Consolidate rules stated multiple times (prefer HTML over PDF, always create recipes/overview.md, do not edit step.toml) into a single source so each appears once.

Add a reusable file scaffold or template (e.g., a references/paper-chunk.template.md and frontmatter schema) so contributors can copy-paste rather than reverse-engineer nemotron-nano3.

Move the long repo-conventions list in the Orient phase into a short reference file to keep the main workflow lean.

DimensionReasoningScore

Conciseness

Largely lean, directive, and free of concepts Claude already knows, but several rules are restated across Tone, Generate, Validate, Boundaries, and When Stuck (HTML-over-PDF, recipes/overview.md, no step.toml edits), which could be trimmed.

4 / 5

Actionability

Gives exact file paths, required frontmatter fields, required sections, and validation checks, but provides no literal copy-paste templates — it relies on modeling from existing nemotron-nano3/super3 skills.

4 / 5

Workflow Clarity

Four phases (Orient → Generate → Validate → Summarize) are explicitly ordered, with a validation checklist and a fix → re-check feedback loop including a two-failure escalation rule for a batch file-generation task.

5 / 5

Progressive Disclosure

Well-organized into clear sections with one-level-deep pointers to existing repo skills and no nested references, but no bundle reference files exist and the ~190-line body inlines conventions that could be split out.

4 / 5

Total

17

/

20

Passed

Description

92%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.

The description is concrete, third-person, and explicitly pairs a 'what' with a 'when' trigger clause. Its only weak spot is trigger-term breadth, which is slightly niche rather than covering natural user phrasings.

DimensionReasoningScore

Specificity

Lists multiple concrete deliverables — 'paper chunks, recipe summaries, context packs, and model card' — plus the onboarding action, giving comprehensive coverage of what gets produced.

5 / 5

Completeness

Explicitly answers what ('Onboard a new model family ... paper chunks, recipe summaries, context packs, and model card') and when ('Use when a contributor wants downstream skills like /nemotron-customize to be able to route to a new model').

5 / 5

Trigger Term Quality

Captures natural contributor phrases like 'new model family' and 'route to a new model', but leans technical ('downstream skills', 'nemotron-customize') and lacks broader synonyms a user might say.

4 / 5

Distinctiveness Conflict Risk

Targets a narrow niche (onboarding model families into the Nemotron skill ecosystem) and names sibling skills, making overlap with other skills minimal.

5 / 5

Total

19

/

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-NeMo/Nemotron
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.