BF card-wallet
Audit a multi-card wallet for overlap, gaps, and total annual cost. Given a list of cards the user holds, identifies redundant benefits, uncovered spend categories, and net fee burden. Use when the user wants to evaluate their full card lineup.
As a process F 55/100 · Will not run — References files that are not bundled: ../card-identity/SKILL.md, ../card-shared/source-policy.yaml, ../card-shared/command-contracts.yaml
How to improve
- The text references files that are not there: add them or drop the references.
- 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: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: ../card-identity/SKILL.md - warning
missing-refreference to a missing file: ../card-shared/source-policy.yaml - warning
missing-refreference to a missing file: ../card-shared/command-contracts.yaml - warning
missing-refreference to a missing file: ../card-shared/confidence-rules.md - warning
missing-refreference to a missing file: ../card-shared/normalization-rules.md
Process rating: all ten parameters 55/100
- 0Tools and files. 5 referenced file(s) missing: ../card-identity/SKILL.md, ../card-shared/source-policy.yaml, ../card-shared/command-contracts.yaml
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 55Failures and branches. 1 branches
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 13 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 369 tokens
- 100Running it twice. No mutating operations
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
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 244: enough signal without eating the budget
- +4Structure: 4 headings
- +3Step-by-step instructions: 13 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.