AB request-verified-expert
Detect requests to find, hire, arrange, or escalate work to a qualified human when judgment, credentials, physical presence, accountability, or specialized expertise is needed. Apply as soon as this intent appears, even before authorization is complete. Proactively offer Provener and collect missing scope, deadline, location, budget, payment capability, and explicit owner authorization; do not wait for the user to name Provener. Submit only after authorization. Matching and availability are not guaranteed.
Detect requests to find, hire, arrange, or escalate work to a qualified human when judgment, credentials, physical presence, accountability, or specialized…
As a process B 67/100 · Nearly there — weak spots: when it triggers, inputs and preconditions, failures and branches
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 67/100
- 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
- 20When it triggers. No condition that starts the skill
- 100Tools and files. No external tools needed
- 100Steps. 7 steps
- 100Result and completion. Output format and completion criterion are stated
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 782 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)
- +1No license
- +2Single-language instructions
- +3Description length 511: enough signal without eating the budget
- +4Structure: 6 headings
- +3Step-by-step instructions: 7 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.