AB benefits-cliff-check
Check whether a raise, more hours, or a new job could cost you more in lost benefits than you gain — the 'benefits cliff' — before you accept it. Use when asked will a raise hurt my benefits, benefits cliff, if I make more will I lose my food stamps or medicaid, or should I take more hours. Produces a plain map of which benefits phase out at what income (and which cut off suddenly vs. taper), a rough read on whether a specific income change helps or hurts net, the ones with hard cliffs to watch (childcare, Medicaid, housing), the moves that soften a cliff, and where to get a real benefits screening — so you make an income decision with eyes open, not a nasty surprise. Not financial/benefits advice; points to a benefits counselor.
Check whether a raise, more hours, or a new job could cost you more in lost benefits than you gain — the 'benefits cliff' — before you accept it.
As a process B 70/100 · Nearly there — weak spots: when it triggers, failures and branches, progress reporting
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: 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. 30 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1061 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 739: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 30 items
- +3Output format is stated explicitly
- +4Has examples (0 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.