AB company-compare-same-definitions
Use when asked to compare two annual reports, put two companies from the same sector side by side, or check whether two companies' adjusted numbers mean the same thing. Takes two uploaded annual reports from one sector and compares them on five ratios computed with identical definitions from audited figures, flagging every place the companies define a metric differently. Produces a page-referenced comparison table, a definitions-differ section (adjusted vs statutory, inside vs outside the audited statements), and three questions to ask before believing either company's highlights. Educational, not financial advice.
Takes two uploaded annual reports from one sector and compares them on five ratios computed with identical definitions from audited figures, flagging every…
As a process B 70/100 · Nearly there — weak spots: failures and branches, running it twice, progress reporting
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 70/100
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 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. 36 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1697 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 622: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 36 items
- +3Output format is stated explicitly
- +4Has examples (0 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.