AA should-i-stop-and-ask
Should I stop and ask the user? Is this task possible with what I have? Use this when a task is failing repeatedly, the same approach has been tried twice, no new evidence is appearing, a host is refusing you, or you are about to ask a vague "should I keep trying?". Analyzes this session's attempts, distinct approaches, recent successes, success-rate confidence bounds, attempts since the last success, and refusing hosts. Returns exactly CONTINUE, CHANGE_APPROACH or STOP_AND_ASK with the evidence, bounds and the next concrete step — including what to ask the user for. Do not use before the second failure.
Should I stop and ask the user?
As a process A 81/100 · Runs to the end — weak spots: inputs and preconditions, running it twice
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
- note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 81/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 5 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 100Tools and files. No external tools needed
- 100Steps. 28 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1285 tokens
- 100Progress reporting. Reports progress
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
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 611: enough signal without eating the budget
- +4Structure: 7 headings
- +3Step-by-step instructions: 28 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.