AB multi-sku-copurchase-bundles
Mine historical orders for multi-SKU co-purchase patterns, quantify association strength between SKUs, and produce high-converting bundle and Frequently-Bought-Together (FBT) recommendations—including "if buy A then suggest B" logic chains, discount copy, and checkout hooks. Use this skill whenever the user mentions raising AOV, bundle design, FBT modules, cross-sell from order data, market-basket style rules, "what to pair with SKU X," Shopify bundle apps, or wants association coefficients from exports—even if they only say "customers who buy this also buy…" or paste a line-items CSV. Also trigger on PDP bundle blocks, cart upsell logic, and wholesale kit planning from purchase history. Do NOT use for single-SKU costing with no basket analysis, pure creative naming with no order data or methodology, or legal/compliance review of regulated product bundles.
As a process B 76/100 · Nearly there — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- 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: 7. 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 76/100
- 0Progress reporting. Says nothing while it works
- 30Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 1 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 70Failures and branches. 5 branches
- 100Tools and files. No external tools needed
- 100Steps. 9 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 948 tokens
- medium 3 test cases, all positive: not one "should refuse" or "should ask first"
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
- +3Description length 868: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 10 headings
- +3Step-by-step instructions: 9 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (2 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 94.