AC cpa-return-review
Activate when: a prepared 1040 or 1120-S is going to review; you are the second set of eyes on someone else's return; a firm wants one consistent review standard across reviewers; onboarding a preparer to the review bar; something feels off about a return and you want a systematic pass; user says 'review this return', 'before we file', 'second review', 'preparer checklist', 'did we miss anything on this return?'. Do NOT activate when: the return is not yet prepared; the question is a single technical treatment; the work is chasing missing documents rather than reviewing; the question is what an examiner would attack or whether a position invites audit rather than whether the return is right (use tax-prep-pre-file-audit-premortem instead — it applies to 1120-S as much as 1040). More: deciqai.com/c/cpa-return-review
Activate when: a prepared 1040 or 1120-S is going to review; you are the second set of eyes on someone else's return; a firm wants one consistent review…
As a process C 58/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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: 2. 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 58/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 100Tools and files. No external tools needed
- 100Steps. 65 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2883 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 825: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Structure: 15 headings
- +3Step-by-step instructions: 65 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.