CC execution-hygiene
Runs computations so they finish, reproduce and fit the machine that will re-execute them, detaching long jobs through compute_job instead of blocking or sleeping shells, checkpointing so reruns resume, fixing seeds and capping BLAS and OpenMP threads, streaming large tables with explicit dtypes, writing outputs atomically, logging every command with its exit code and rerunning the final pipeline from scratch under the target limits before finishing. Use for any analysis or pipeline that runs longer than a minute, reads files larger than memory, or will be re-executed on a machine with tighter CPU, memory, wall-clock or network limits than this one; a one-off shell command whose output is read immediately does not need it.
Runs computations so they finish, reproduce and fit the machine that will re-execute them, detaching long jobs through computejob instead of blocking or…
As a process C 58/100 · 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 python compute_job
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 58/100
- 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
- 30Running it twice. 6 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 28 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2428 tokens
- 100Progress reporting. Reports progress
- low The response is described with custom markup (3 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
- -5TODO / placeholder text left in the skill
- +2Single-language instructions
- +3Description length 732: enough signal without eating the budget
- +4Structure: 5 headings
- +3Step-by-step instructions: 28 items
- +4Has examples (2 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.