SKILLEMALL.ai

BF launch-nemo-rl

Playbook for launching, monitoring, stopping, and debugging NeMo-RL recipes on a Kubernetes cluster via the nrl-k8s CLI. Covers ephemeral vs long-lived RayCluster modes, iterating on runs, and debugging hung or failed training jobs.

ClawHub Agent Skills author: NVIDIA 1 file body ≈ 4 298 tokens Open the sourceclawhub.ai analyzed 27 h ago

Playbook for launching, monitoring, stopping, and debugging NeMo-RL recipes on a Kubernetes cluster via the nrl-k8s CLI.

As a process F 39/100 · Will not run — References files that are not bundled: examples/configs/recipes/llm/..., examples/configs/recipes/llm/…, examples/nemo_gym/…

ProcedureKubernetesInfrastructuretype and topics are labelled automatically from the skill text
JSON
Technical rating
B
81/100
safety, quality, tests
Safety 60%
95
Quality 40%
59
Run on models
none yet
Process rating
F
39/100
Will not run
References files that are not bundled: examples/configs/recipes/llm/..., examples/configs/recipes/llm/…, examples/nemo_gym/…
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Broad scope medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. 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 · 1

✓ No critical or high findings

Medium and low: 1
  • medium Broad scope meta-broad-allowed-tools SKILL.md:1
    Broad tool permissions pre-approved: Bash
    allowed-tools: Bash Read Grep Glob Edit Write

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

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning missing-ref reference to a missing file: examples/configs/recipes/llm/...
  • warning missing-ref reference to a missing file: examples/configs/recipes/llm/…
  • warning missing-ref reference to a missing file: examples/nemo_gym/…

Process rating: all ten parameters 39/100

Will not run. References files that are not bundled: examples/configs/recipes/llm/..., examples/configs/recipes/llm/…, examples/nemo_gym/…
  • 0Tools and files. 3 referenced file(s) missing: examples/configs/recipes/llm/..., examples/configs/recipes/llm/…, examples/nemo_gym/…
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 30Running it twice. 12 mutating operations with no state check
  • 70When it triggers. States when to use, but not when not to
  • 70Execution cost. Instruction body is 4298 tokens
  • 100Steps. 42 steps
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • low 14 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (8 tags): a typed call is more reliable

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)
  • +3Output format is not stated: the model decides each time
  • -2localhost URLs: will not work for another user
  • +2Single-language instructions
  • +3Description length 232: enough signal without eating the budget
  • +4Structure: 20 headings
  • +3Step-by-step instructions: 42 items
  • +4Has examples (14 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 59.