AC wise-penny
Analyze and organize personal or household finances through Wise Penny, an MCP server connected read-only (via Plaid) to the user's bank accounts. Covers balances, transactions, spending and cash flow, budgets, savings goals, subscriptions and recurring bills, plus organizing tools (categories, tags, splits, rules, transfer links). Use whenever the user asks about their money — where it goes, what they spend, upcoming bills, a subscription audit, net worth, or setting a savings goal — and has connected, or is willing to connect, Wise Penny. If the user has not set up Wise Penny yet (no account, circle, or linked bank), first direct them to sign up and link accounts at wisepenny.app. Wise Penny reads financial data and never moves money.
Analyze and organize personal or household finances through Wise Penny, an MCP server connected read-only (via Plaid) to the user's bank accounts.
As a process C 52/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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 · 1
✓ No critical or high findings
Medium and low: 1
✓ Guard found no suspicious behaviour. 1 matches are attack strings quoted in this security skill's own documentation.
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 52/100
- 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
- 30Running it twice. 8 mutating operations with no state check
- 40Consistency. Frontmatter name (wise-penny) differs from the folder (wisepenny-skill)
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 40 steps
- 100Execution cost. Instruction body is 2542 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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 746: enough signal without eating the budget
- +4Structure: 7 headings
- +3Step-by-step instructions: 40 items
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.