BB Ecommerce
Runs an online store end to end: catalog, checkout, payments, inventory, fulfillment, returns, pricing, conversion, retention, and tax. Use when building or reviewing store code — checkout totals, webhooks, stock decrements; when a payment double-charges, a webhook replays, or an order is paid but missing in the store; when stock oversells across channels or a reorder point is missing; when carts abandon, conversion drops, or AOV has to rise; when a discount or free-shipping threshold might sell below cost; when chargebacks, refund abuse, or fraud rules need setting; when choosing or migrating a platform or adding a marketplace; when VAT/OSS, sales-tax nexus, or a 14-day withdrawal window applies; and for peak season, subscriptions, and wholesale terms. Not for parcel carrier depth (skill `shipping`), payment-provider integration code (skill `payments`), CRO method (skill `conversion-rate-optimization`), SaaS pricing (skill `pricing`), or a physical shop (skill `store`).
Runs an online store end to end: catalog, checkout, payments, inventory, fulfillment, returns, pricing, conversion, retention, and tax.
As a process B 76/100 · Nearly there — weak spots: inputs and preconditions
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
body-longSKILL.md body ≈ 7672 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "changelog"
Process rating: all ten parameters 76/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 7672 tokens
- 100Tools and files. No external tools needed
- 100Steps. 46 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 top-level sections: this looks like several domains in one skill
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
- +3Description length 985: 120–800 characters recommended
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 13 headings
- +3Step-by-step instructions: 46 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.