BC nemotron-3-ultra-text2sql-lora
Run the Nemotron-3 Ultra Text2SQL LoRA fine-tuning tutorial (NeMo Megatron-Bridge) end-to-end for the user on their SLURM cluster: data prep, distributed checkpoint conversion, and packed LoRA fine-tuning of the 550B hybrid Mamba-Transformer MoE, ending at a saved adapter. Use when the user wants to run this cookbook, fine-tune Nemotron-3 Ultra with LoRA, or adapt the notebook to their own cluster.
The skill promises to run the full fine-tuning cycle for Nemotron-3 Ultra on your SLURM cluster: data prep, checkpoint conversion, LoRA training of a 550B hybrid Mamba-Transformer MoE, and adapter export. Eight modules, five scripts, 1776 tokens total. No critical errors found; safety score 100, quality 80, but process score 63 hints at incomplete automation or manual steps required.
The model hasn't been tested in sandbox, so real behavior on your cluster remains unknown. The skill targets users already comfortable with SLURM and distributed training. Install if you need this specific architecture and have the hardware—otherwise you'll likely get stuck in configuration.
Run the Nemotron-3 Ultra Text2SQL LoRA fine-tuning tutorial (NeMo Megatron-Bridge) end-to-end for the user on their SLURM cluster: data prep, distributed…
As a process C 63/100 · Has gaps — weak spots: result and completion, consistency
How to improve
- 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: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 63/100
- 0Result and completion. Does not say what the result is
- 40Consistency. Frontmatter name (nemotron-3-ultra-text2sql-lora) differs from the folder (nemo-megatron-bridge)
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (node) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 33 steps
- 100Execution cost. Instruction body is 1776 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
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
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 401: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 33 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.