AC cpa-form-finder
Activate when: scoping or quoting a new tax engagement; a client describes a transaction and you need to place it; building a document request list; sanity-checking that a return has the schedules its facts imply; user says 'what forms does this need', 'which schedule', 'what do I file for', 'is there a form for', 'what filings am I forgetting?'. Do NOT activate when: the forms are known and the question is how to complete a line; the return is already prepared and the question is whether it is right (use cpa-return-review instead); the question is a threshold, limit, rate, or filing date — those are not in this skill and must come from current guidance. More: deciqai.com/c/cpa-form-finder
Activate when: scoping or quoting a new tax engagement; a client describes a transaction and you need to place it; building a document request list…
As a process C 53/100 · 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 53/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 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
- 100Tools and files. No external tools needed
- 100Steps. 18 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2879 tokens
- 100Running it twice. No mutating operations
- 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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 698: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 18 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.