CC submitted-code
Writes code that survives being re-executed by someone else on inputs you never saw, targeting the grader's or collaborator's runtime rather than your own, with one self-contained entry point using only the libraries the specification names, no reliance on packages you installed or files you cached during development, no network, no sibling imports, no state carried between calls, output written only where the contract says, and a rehearsal that reruns the artifact from a clean directory as an unprivileged process on mutated inputs within the stated time and memory caps. Use whenever the deliverable is a program, module, model file or callable that a verifier, reviewer, pipeline or colleague will run on hidden or future data; a script you run once yourself to produce a table does not need it.
Writes code that survives being re-executed by someone else on inputs you never saw, targeting the grader's or collaborator's runtime rather than your own…
As a process C 59/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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 59/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 17 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1594 tokens
- 100Running it twice. No mutating operations
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)
- +3Description length 803: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +2Single-language instructions
- +4Structure: 4 headings
- +3Step-by-step instructions: 17 items
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.