AB axiom
Orders physical products the user asks for through Axiom, using the payment method saved in their Axiom account, checks which payment method Axiom has on file, and reviews past Axiom orders. Use when the user asks to buy, order, reorder, or purchase a specific physical product with Axiom, asks what payment method Axiom has on file, or asks about the status or receipt of an Axiom order. Before starting an order the model confirms it knows the merchant, the exact product, and required options (size, color, storage, flavor), asking the user first when anything is missing. Not for browsing, price comparison, subscriptions, digital goods, or orders the user has not clearly requested.
Orders physical products the user asks for through Axiom, using the payment method saved in their Axiom account, checks which payment method Axiom has on…
As a process B 72/100 · Nearly there — weak spots: result and completion, inputs and preconditions, 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: 6. 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
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 2 mutating operations with no state check
- 100Tools and files. No external tools needed
- 100Steps. 32 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3165 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- high The skill tells the model to perform an irreversible action with no human approval
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
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 687: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 32 items
- +4Reference files are cited in the instructions (4 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.