BC drivethru-adidas-click
Browser-driven adidas Click B2B toolkit — places purchase orders, runs live inventory / wholesale-pricing checks, and pulls shipment tracking numbers from the adidas Click portal with Playwright, since adidas exposes no public API. Ordering accepts style number, color, size, quantity, a purchase-order number, and a ship-to address, drives the cart/checkout, and (on confirm) submits the order. Checks reuse the same flow but never buy — inventory reads product pages (no cart) and reports the **re-stock date** for anything out of stock or backordered, pricing fills a throwaway "DO NOT BUY" cart, reads the priced checkout, and deletes it. Tracking searches the order book by PO number, opens every adidas order for it, and returns each delivery's carrier + tracking number (or, for an order that has not shipped, its expected ship dates). Use whenever the user needs to place/draft a PO on adidas Click, check live stock levels, restock/back-in-stock dates, or wholesale pricing, or find tracking numbers / ship dates for adidas POs.
Browser-driven adidas Click B2B toolkit — places purchase orders, runs live inventory / wholesale-pricing checks, and pulls shipment tracking numbers from the…
As a process C 58/100 · Has gaps — weak spots: result and completion, inputs and preconditions, progress reporting
How to improve
- Shorten the description to 1024 characters.
- 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: 0. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1037 chars, limit 1024 - warning
body-longSKILL.md body ≈ 6800 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "emoji" - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 58/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 6800 tokens
- 85Steps. 34 steps, 1 vague phrases
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 11 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1037: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -35 of 6 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Structure: 14 headings
- +3Step-by-step instructions: 34 items
- +4Has examples (6 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 45.