AB menu-cost-engineer
Cost a menu item to a plate cost and food-cost percentage, then price it for a target margin. Use when asked to cost a dish, calculate food cost percentage, price a menu item, or engineer a menu for profitability. Produces a plate-cost breakdown (ingredient × yield × price), the food-cost %, a suggested price for the target margin, and menu-engineering flags (star / plow-horse / puzzle / dog) so the operator knows what to promote, reprice, or cut.
Cost a menu item to a plate cost and food-cost percentage, then price it for a target margin.
As a process B 70/100 · Nearly there — weak spots: when it triggers, failures and branches, progress reporting
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 tells the agent to hide things from you: not to show errors, not to mention actions, to report differently from what was done. You lose the ability to see what the agent really did.
Transparency beats a smooth answer. If the goal is to hide technical noise, ask the agent to "summarise briefly", not to "not mention".
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 Concealment
en-hide-from-userSKILL.md:8Instruction to hide actions from the user (quoted — discussed, not commanded)Restaurants don't fail on bad food — they fail on math they never did. A dish that "feels" priced right can quietly run a 45% food cost. This skill costs the plate honestly (accounting for yield loss
quoted
Files scanned: 1. 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 70/100
- 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
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. No external tools needed
- 100Steps. 16 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 617 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)
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 451: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 16 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.