BD xborder-ecom-check
Cross-Border E-Commerce Compliance Check — Cross-border e-commerce rules: customs, product safety, consumer protection, tax (VAT/GST), advertising, and data privacy of destination markets. Free to install; scoring runs on the CQDev cloud compliance engine. No Key? The skill auto-runs an anonymous trial (5 real cloud-scored runs, 7-day window) before asking you to register. Covers 12 core items. Use when: the user explicitly asks to run the xborder-ecom-check skill (e.g. "run xborder-ecom-check", "use the xborder-ecom-check skill"). Do NOT activate on generic mentions of "跨境电商" or "cross-border ecommerce" in ordinary conversation — this skill transmits answers to a third-party cloud and must be opted into explicitly by name. Trigger (explicit opt-in only): xborder-ecom-check, run xborder-ecom-check, use xborder-ecom-check skill, run the xborder-ecom-check skill Pricing: Free skill; cloud scoring is free (anonymous trial 5 runs, then register for a free API Key with 100 calls) ⚠️ Cloud scoring sends your answers to compliancehub.cn. The free preview (--non-interactive / --non-interactive-json) runs FULLY OFFLINE using the bundled 12-item set and never contacts the cloud (no network, no IP/UA leakage). Scored runs fetch the latest check items from the cloud rule library and transmit your answers (scored online). Without a Key the skill runs an anonymous trial (up to 5 scored runs) using a local random anon_id; registering gives a free Key with 100 calls. 🔑 API Key is user-supplied (not auto-provisioned): get a free Key on the account page, then set COMPLIANCEHUB_API_KEY or save it to ~/.config/compliancehub/xborder-ecom-check.key (mode 0600). No email/password is ever collected by this skill. 🌐 Language: bilingual (中文/English). Guidance and recommendations default to Chinese for Chinese-speaking compliance teams; legal/regulatory terms keep English originals. Users may request English output at any time. 💡 Free preview: --non-interactive lists the 12 items without
Cross-Border E-Commerce Compliance Check — Cross-border e-commerce rules: customs, product safety, consumer protection, tax (VAT/GST), advertising, and data…
As a process D 43/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Shorten the description to 1024 characters.
- 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
- error
description-longdescription is 2007 chars, limit 1024 - note
description-budgetdescription takes 2007 of the ~15000-char shared budget for all skills - note
frontmatter-keyunknown frontmatter key "permissions"
Process rating: all ten parameters 43/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 100Steps. 14 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1162 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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)
- +3Description length 2006: 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
- +4Structure: 13 headings
- +3Step-by-step instructions: 14 items
- +4Has examples (3 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 60.