CC compute
Chooses and runs compute for research work, local shell or kernel versus a detached compute_job on this machine, a saved SSH or Slurm host, or Modal GPUs, with the target discovered from what is actually configured, the run sized and priced before dispatch, outputs declared, metrics tracked, and long work handed to the job system instead of a blocking shell. Use when a task needs a GPU, will run longer than a few minutes, must survive the session, or asks which cloud or provider to use. Provider-specific setup lives in the cloud-compute library skills; load one only after compute_job targets shows that provider.
Chooses and runs compute for research work, local shell or kernel versus a detached computejob on this machine, a saved SSH or Slurm host, or Modal GPUs, with…
As a process C 60/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Read Bash compute_job provider_compute experiments
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "summary" - note
frontmatter-keyunknown frontmatter key "role"
Process rating: all ten parameters 60/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 14 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1354 tokens
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
- 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
- +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
- +2Single-language instructions
- +3Description length 619: enough signal without eating the budget
- +4Structure: 6 headings
- +3Step-by-step instructions: 14 items
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.