AB exec-slurm-compile
Compile TensorRT-LLM on a SLURM cluster. Covers submitting a batch job with a container image, monitoring the job, and verifying the build. Use when the user wants to compile TRT-LLM remotely via SLURM rather than on a local compute node.
This skill compiles TensorRT-LLM on a SLURM cluster using a container image, then monitors and verifies the build. Three files, two scripts, no broken references or critical issues. Quality score is 88 and safety is 100, but process score dropped to 70—submission logic or monitoring has rough edges.
No sandbox run, no model testing. Saves time if you regularly compile TRT-LLM on clusters. Otherwise it's just a template. Install if you have SLURM and container infrastructure ready; otherwise it sits unused.
Compile TensorRT-LLM on a SLURM cluster.
As a process B 70/100 · Nearly there — weak spots: result and completion
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: 3. 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 70/100
- 0Result and completion. Does not say what the result is
- 60Tools and files. Uses tools (bash, 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
- 85Steps. 33 steps, 2 vague phrases
- 100Failures and branches. 5 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2441 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- low The response is described with custom markup (16 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
- +2Single-language instructions
- +3Description length 238: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 33 items
- +4Has examples (8 code blocks)
- +3All 2 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.