AB profit-to-cash-walk
Use when asked to reconcile operating profit to free cash flow, walk from EBIT to FCF, explain why profit and cash differ in this report, or show a company's cash conversion from its own accounts. Takes operating profit from an uploaded annual report and walks line by line to free cash flow using the report's own numbers, arithmetic shown at every step. Produces a step table (line, page, amount, running total, one-sentence reason cash and profit diverge), a drift flag on every line where the arithmetic could go wrong, a tie-out to the reported cash flow statement, and an instruction to independently check at least one subtraction. Educational, not financial advice.
Use when asked to reconcile operating profit to free cash flow, walk from EBIT to FCF, explain why profit and cash differ in this report, or show a company's…
As a process B 67/100 · Nearly there — weak spots: when it triggers, failures and branches, 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: 1. 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 67/100
- 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
- 30Running it twice. 2 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. No external tools needed
- 100Steps. 33 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1530 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 673: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 33 items
- +3Output format is stated explicitly
- +4Has examples (0 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.