AC test-gap-audit
Run a read-only audit for missing, weak, stale, or mis-scoped test coverage. If the user does not name a scope, audit the full repository and identify important code paths, routes, features, services, workflows, and contracts that lack proper tests. If the user names a feature, PR, branch, route, workflow, service, bug fix, API, security-sensitive path, or risky code change, focus only on that specific scope. Use when the user asks what tests are missing, whether coverage is enough, what regression tests to add, or how to prove a change is safe. This is not a general bug audit and not a security review; it evaluates whether behavior is covered by tests.
Run a read-only audit for missing, weak, stale, or mis-scoped test coverage.
As a process C 60/100 · Has gaps — weak spots: result and completion, running it twice, progress reporting
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: 2. 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 60/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, python) 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. 79 steps, 2 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3217 tokens
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 661: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 79 items
- +4Has examples (1 code blocks)
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.