AB form-1040-review
Review U.S. individual income tax returns (Form 1040/1040-SR) for the most recent tax year, compare major return items against current-year tax rules, check consistency across historical returns when multiple years are provided, generate a standalone DOCX risk register, and estimate audit likelihood from return content. Use when tasks involve 1040 compliance review, multi-year consistency analysis, tax-law validation, or audit-risk assessment.
As a process B 68/100 · Nearly there — weak spots: when it triggers, 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: 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 68/100
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 40Consistency. Frontmatter name (form-1040-review) differs from the folder (usa-tax-return-review-1040)
- 60Result and completion. Output format stated, no completion criterion
- 60Failures and branches. 2 branches
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. No external tools needed
- 100Steps. 35 steps
- 100Execution cost. Instruction body is 851 tokens
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 447: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 35 items
- +3Output format is stated explicitly
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 94.