AC food-balance
Analyse a user's meal or daily food intake and give gentle, friendly suggestions on whether their diet is balanced and within calorie/nutrient limits. Use this skill whenever a user describes what they ate — a meal, a snack, a full day of eating — and wants to know if it is healthy, balanced, or within calorie limits. Trigger on phrases like "I ate...", "I had... for lunch", "is my diet balanced?", "was that too much?", "what did I eat today?", "my meal was...", or any description of food consumption followed by a question about health, calories, balance, or nutritional adequacy. Even casual descriptions like "just had pizza and coke" should trigger this skill if the user seems to want feedback.
As a process C 62/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
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: 4. 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 62/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (food-balance) differs from the folder (foods)
- 70When it triggers. States when to use, but not when not to
- 85Steps. 24 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100Failures and branches. 2 branches, has a failure section
- 100Execution cost. Instruction body is 1177 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +3Description length 704: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 24 items
- +4Has examples (0 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.