AB zyte-ecommerce-products-compare-skill
Extract structured product data from e-commerce URLs using the Zyte API and generate side-by-side comparison tables with intelligent purchase recommendations. Use this skill whenever the user wants to compare products from different e-commerce websites, asks "which product should I buy", wants a product comparison table, needs help deciding between product options, or provides multiple product URLs and wants them analyzed. Also trigger when the user says things like "compare these products", "which is the better deal", "help me pick between these", "product showdown", or pastes 2+ e-commerce URLs. Requires ZYTE_API_KEY in the environment.
As a process B 70/100 · Nearly there — weak spots: result and completion, progress reporting
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
-
low Secrets in code
secret-password-literalscripts/fetch_products.py:238Hard-coded password / key literal (may be an example)api_key = sys.argv[1]
Files scanned: 8. 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 70/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 28 steps
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2499 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +3Description length 646: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 28 items
- +4Has examples (11 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 2 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 97.