AB family-health-tracker
Use this skill when a user is actively logging or looking up health information for themselves or a family member. Specific triggers: 'log a visit with [provider],' 'add [medication] for [person],' 'what are [person]'s allergies,' 'when is [person]'s next checkup,' 'family health summary,' 'who's due for a dental cleaning,' 'pre-appointment prep for [person/visit],' 'when is [person]'s [medication] refill due,' 'add an immunization for [person],' 'update insurance for [person],' or any message that names a specific family member in a health context. Do NOT trigger on general health news, casual mentions of medications outside a logging context, unrelated calendar items, or symptom-checking requests (the skill is not a medical advisor). Covers: per-person health profiles, allergies, medications and refill reminders, doctor visits, CDC immunization schedule tracking, insurance basics, growth log for children, and a shared provider directory, all stored in a local JSON file.
As a process B 70/100 · Nearly there — 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: 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 70/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 4 mutating operations with no state check
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Failures and branches. 4 branches
- 100Steps. 122 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3428 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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)
- +3Description length 986: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +4Structure: 30 headings
- +3Step-by-step instructions: 122 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.