AB recurring-charge-detector
Identifies recurring charges (subscriptions, monthly bills, biweekly paychecks) from a transaction history by clustering same-merchant transactions of similar amount on a regular cadence, requiring at least 3 confirming occurrences before promoting a candidate to active status. Detects new recurring charges, dormant subscriptions (missed expected dates), and amount drift, and computes annualized cost. Use when auditing subscriptions, building a recurring bills calendar, computing cash-flow forecast inputs, or when user mentions subscription audit, recurring detection, dormant subscription, or annualized cost.
Identifies recurring charges (subscriptions, monthly bills, biweekly paychecks) from a transaction history by clustering same-merchant transactions of similar…
As a process B 72/100 · 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 72/100
- 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. 5 mutating operations with no state check
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. No external tools needed
- 100Steps. 30 steps
- 100Result and completion. Output format and completion criterion are stated
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1857 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
- +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 616: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 30 items
- +3Output format is stated explicitly
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.