SKILLEMALL.ai
GitHub ↗ RU Sign in

BD nemotron-add-step

Add a new step under src/nemotron/steps/<category>/<step_id>/ — manifest (step.toml), runner glue, configs, and per-step README.md. Use when extending the catalog so /nemotron-customize can route to it.

The skillemall take

This skill adds a new step to the Nemotron catalog — creates a folder, step.toml manifest, configs, and README. Use it when extending the system so /nemotron-customize can route to the new step.

One file, no scripts. Quality scores lean heavily toward documentation (81) while process automation lags (42). Broken references point to missing files in the source. No critical findings, but that's less reassurance than it sounds — the skill simply hasn't been run much. Broad platform support and 100% safety score.

Install if you're already deep in Nemotron and willing to fill gaps yourself. Otherwise, skip it.

NVIDIA-NeMo/Nemotron Agent Skills author: NVIDIA-NeMo 1 file body ≈ 1 685 tokens Open the sourcegithub.com↗ analyzed 5 d ago

Add a new step under src/nemotron/steps/<category>/<stepid>/ — manifest (step.toml), runner glue, configs, and per-step README.md. Use when extending the…

As a process D 42/100 · Unfinished process — References files that are not bundled: examples/*.md

ProcedureWriting and documentstype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
B
92/100
safety, quality, tests
Safety 60%
100
Quality 40%
81
Run on models
none yet
Process rating
D
42/100
Unfinished process
References files that are not bundled: examples/*.md
Tools and files w 18
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

How to improve

  1. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 0

✓ No critical or high findings

Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: examples/*.md

Process rating: all ten parameters 42/100

Will not run. References files that are not bundled: examples/*.md
  • 0Tools and files. 1 referenced file(s) missing: examples/*.md
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 60Result and completion. Output format stated, no completion criterion
  • 85Steps. 76 steps, 2 vague phrases
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1685 tokens
  • 100Running it twice. Mutating operations check current state

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +1No license
  • +2Single-language instructions
  • +3Description length 202: enough signal without eating the budget
  • +4Structure: 11 headings
  • +3Step-by-step instructions: 76 items
  • +3Output format is stated explicitly
  • +4Has examples (2 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.