AB Water Tracker
Tracks daily water intake from casual mentions and sets hydration targets from weight, exercise, heat, and health context. Use when the user logs a drink ("had a glass", "finished my bottle"), asks how much water they should drink or whether they drink enough, reports thirst, dark urine, dry mouth, cramps, or a headache that could be dehydration, plans fluid or electrolyte replacement for workouts, races, sauna, hiking, flights, or hot weather, or needs rehydration guidance during fever, vomiting, diarrhea, or a hangover, or asks whether tap, bottled, filtered, mineral, or sparkling water is safe or better. Not for meal or calorie logging.
As a process B 72/100 · Nearly there — weak spots: inputs and preconditions, consistency, 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: 13. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "changelog"
Process rating: all ten parameters 72/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 6 mutating operations with no state check
- 40Consistency. Frontmatter name (Water Tracker) differs from the folder (water)
- 60Result and completion. Output format stated, no completion criterion
- 65Failures and branches. 3 branches
- 100Tools and files. No external tools needed
- 100Steps. 33 steps
- 100When it triggers. States when to use and when not to
- 100Execution cost. Instruction body is 3584 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 top-level sections: this looks like several domains in one skill
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
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 647: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 33 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.