CF retail-digital-ai-expert-international
【Global Top-Tier Retail Digital & AI Transformation Expert — International Edition】 — Full-stack intelligence for retail digitalization & AI deployment worldwide. 12 retail formats ■ 8 business chains ■ 60 digital scenarios ■ 15 AI applications ■ 80+ technology vendors ■ R-DMM maturity model ■ RICE+ AI scoring ■ 7-dimension vendor selection matrix ■ 5-layer franchise governance ■ AIPL omnichannel model ■ ADKAR change management. Covers: convenience store, neighborhood supermarket, specialty apparel/beauty chain, fast fashion/lifestyle, hypermarket/supercenter, department store/shopping mall, consumer electronics/home improvement, discount retail, DTC brand, e-commerce/omnichannel, franchise chain, global enterprise retail. Vendors: Shopify POS, Square, Lightspeed, Toast, Oracle Retail, SAP, Microsoft Dynamics 365, Salesforce, Adobe Commerce (Magento), Stripe, Adyen, PayPal, Workday, UKG, Blue Yonder, Manhattan Associates. Global benchmarks: Walmart, Amazon, Costco, 7-Eleven, Carrefour, Tesco, Aldi, Lidl, Zara (Inditex), H&M, Uniqlo, IKEA, Nike, Sephora, Best Buy, Home Depot, Target, Kroger. Regulations: GDPR, PCI DSS, SOC 2, ISO 27001, CCPA/CPRA. Platforms: TikTok Shop, Instagram Shopping, WhatsApp Business, Google Shopping, Facebook Shops, Amazon Marketplace, eBay, Etsy. Trigger words: retail digital transformation, POS selection, omnichannel, OMS, WMS, ERP, CRM, CDP, AI demand forecasting, dynamic pricing, retail AI, franchise management, retail maturity assessment, vendor selection, retail ROI, retail technology, unified commerce, headless commerce, MACH architecture, RFID retail, ESL electronic shelf labels, self-checkout, cashierless store, smart retail, retail data platform, retail analytics.
【Global Top-Tier Retail Digital & AI Transformation Expert — International Edition】 — Full-stack intelligence for retail digitalization & AI deployment…
As a process F 54/100 · Will not run — References files that are not bundled: templates/digital-maturity-assessment-report.md, templates/digital-transformation-roadmap.md, templates/technology-selection-vendor-evaluation.md
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.
- The text references files that are not there: add them or drop the references.
- 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: 56. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1727 chars, limit 1024 - warning
body-longSKILL.md body ≈ 61552 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: templates/digital-maturity-assessment-report.md - warning
missing-refreference to a missing file: templates/digital-transformation-roadmap.md - warning
missing-refreference to a missing file: templates/technology-selection-vendor-evaluation.md - warning
missing-refreference to a missing file: templates/ai-scenario-priority-scorecard.md - warning
missing-refreference to a missing file: templates/roi-business-case-report.md - warning
missing-refreference to a missing file: templates/project-implementation-plan.md - warning
missing-refreference to a missing file: templates/change-management-plan.md - warning
missing-refreference to a missing file: templates/project-acceptance-report.md - warning
missing-refreference to a missing file: templates/omnichannel-operations-plan.md - warning
missing-refreference to a missing file: templates/franchise-digital-governance.md - note
description-budgetdescription takes 1727 of the ~15000-char shared budget for all skills - note
frontmatter-keyunknown frontmatter key "language" - note
frontmatter-keyunknown frontmatter key "contact"
Process rating: all ten parameters 54/100
- 0Tools and files. 10 referenced file(s) missing: templates/digital-maturity-assessment-report.md, templates/digital-transformation-roadmap.md, templates/technology-selection-vendor-evaluation.md
- 10Execution cost. Instruction body is 61552 tokens: crowds the task out of the window
- 30Running it twice. 42 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Steps. 84 steps, 6 vague phrases
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Result and completion. Output format and completion criterion are stated
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 48 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 1727: 120–800 characters recommended
- -46 reference files, but SKILL.md never points to them: the model will not open them
- +2Single-language instructions
- +4Structure: 257 headings
- +3Step-by-step instructions: 84 items
- +3Output format is stated explicitly
- +4Has examples (34 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 29.