AC tax-filing
United States federal income tax filing assistant for US citizens, resident aliens, and nonresident aliens. Guides users through the entire IRS filing workflow: determining filer type and filing status, identifying which forms and schedules are needed, calculating amounts from source documents (W-2, 1099s, etc.), and filling IRS PDF forms using pypdf. This skill covers US federal taxes only — not state, local, or non-US tax systems. Use this skill whenever the user mentions taxes, tax returns, 1040, 1040-NR, filing status, "which forms do I need", "help me file my taxes", "tax prep", deductions, NRA tax filing, nonresident alien taxes, treaty-based returns, "check my tax forms", "review my 1040-NR", or any request related to preparing a US federal tax return — even if they don't specify their filer type. This skill handles the routing and covers both citizen/RA (Form 1040) and NRA (Form 1040-NR) workflows end to end, including PDF form filling and validation.
As a process C 56/100 · Has gaps — weak spots: result and completion, 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: 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 56/100
- 0Result and completion. Does not say what the result is
- 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
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Failures and branches. 4 branches
- 100Steps. 93 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3528 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)
- +3Description length 973: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +4Structure: 17 headings
- +3Step-by-step instructions: 93 items
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.