AB tax-plain-english
Use this skill whenever the user asks a tax question — even casual ones. Triggers include: questions about deductions, filing status, deadlines, refunds, W-2s, 1099s, capital gains, self-employment tax, home office, depreciation, estimated payments, tax credits, HSA/FSA, retirement accounts (401k, IRA, Roth), inheritance, gifts, rental income, crypto taxes, business expenses, payroll taxes, sales tax, or anything mentioning "the IRS", "HMRC", "write off", "tax return", "tax bracket", or "owe taxes". Also trigger for questions like "is X tax deductible?", "do I need to report X?", "how much tax will I pay on X?", or "can I claim X?". Use this skill even if the question seems simple — structured output is always more useful than a casual reply on tax topics.
As a process B 72/100 · Nearly there — weak spots: inputs and preconditions, running it twice, 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: 8. 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 72/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 65Failures and branches. 3 branches
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 41 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3505 tokens
- 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
- +4Description does not say when NOT to use the skill (false activations)
- +2Single-language instructions
- +5Description quotes 9 example trigger phrases
- +3Description length 766: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 41 items
- +3Output format is stated explicitly
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 97.