AC sagemaker-training-job
Submit ML training jobs to AWS SageMaker — package code, upload to S3, launch on GPU/CPU instances, poll status, download artifacts. Use when training machine learning models that need more compute than the local machine (GPU training, large datasets, parallel experiments). Supports PyTorch, TensorFlow, scikit-learn, XGBoost/LightGBM. Handles spot instances for cost savings. Triggers on "train on SageMaker", "GPU training", "submit training job", "cloud training", "SageMaker", "remote training".
As a process C 60/100 · Has gaps — weak spots: result and completion, failures and branches, progress reporting
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: 9. 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 60/100
- 0Result and completion. Does not say what the result is
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 60Tools and files. Uses tools (bash, python) 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. 19 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1146 tokens
- 100Running it twice. No mutating operations
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -31 of 5 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +3Description length 500: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 19 items
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.