BA exec-local-slurm
Submit and monitor a Slurm job on a local cluster. Supports two modes: (1) Persistent allocation (default) — allocates nodes once via nohup salloc, imports the container once, installs once, and reuses across runs by setting SLURM env vars and running the sbatch script via bash. (2) One-shot sbatch — submits a fully-generated Slurm script via sbatch, polls job status, reads logs on completion, and reports results. Workflow-agnostic — handles pytest, eval, benchmark, and custom scripts identically.
The skill submits jobs to a local Slurm cluster in two modes: persistent allocation that reuses nodes and container, or one-shot sbatch with status polling. Handles pytest, benchmarks, and custom scripts the same way.
Grade B: quality 76%, process 89%, no critical findings. Single file, no lint issues, references intact. No model runs or sandbox tests—actual behavior remains unknown. Supports Claude, Cursor, Gemini, Qwen, and nine other platforms.
Install if you have a local Slurm and need job automation. Without real runs, handling of hangs and timeouts is unclear—test on a dummy task first.
Submit and monitor a Slurm job on a local cluster.
As a process A 89/100 · Runs to the end — no weak spots found
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 89/100
- 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
- 70Execution cost. Instruction body is 4546 tokens
- 85Steps. 57 steps, 1 vague phrases
- 100Result and completion. Output format and completion criterion are stated
- 100When it triggers. States when to use and when not to
- 100Inputs and preconditions. Inputs and preconditions are listed
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- high The skill tells the model to perform an irreversible action with no human approval
- low The response is described with custom markup (32 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)
- +2Single-language instructions
- +3Description length 502: enough signal without eating the budget
- +4Structure: 21 headings
- +3Step-by-step instructions: 57 items
- +3Output format is stated explicitly
- +4Has examples (26 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.