AI for Retail

Move a buying team from quarterly batch assortment reviews to a continuous, agent-orchestrated replan loop. Output is a weekly (or daily, in fast fashion / grocery) assortment-decision packet: which SKUs to add, hold, mark down, exit, or reallocate across stores and channels — with the productivity-per-square-foot, overlap, whitespace, and margin-at-risk evidence each call rests on. The skill does not replace the buyer; it produces the structured packet a buyer can approve, edit, or reject in one sitting and pushes the approved deltas into the assortment system through the merchant's existing PIM / merchandising stack.

Produce a targeted fraud-signal review and chargeback-defense plan for retailers whose storefront is being hit by autonomous AI shopping agents, friendly-fraud disputes, or AI-generated return scams. Translate raw transaction, device, and dispute data into tuned risk rules, evidence packets, and policy adjustments that preserve conversion while cutting loss — and write back into the PSP / fraud-platform with a config-traceable per-card-scheme representment template shelf.

Produce a decision-ready competitive price comparison across 3–7 competitors for a target SKU set — built on a formal SKU-match taxonomy, a seven-component landed-price formula, a six-tier positioning ladder, a MAP / UPP violation escalation path, and a time-bounded promo-urgency score — so pricing, buying, and merchandising teams can commit to an action inside one business day instead of waiting for the monthly report. Output is an accurate, dated, traceable deliverable the merchant can hand directly to the pricing-council or the promo-desk.

Produce a structured, accuracy-scored demand forecast for a product category or SKU set by decomposing history into level / trend / seasonality / external, picking the right method per SKU pattern, attaching confidence intervals, and tying the forecast to open-to-buy, safety-stock, and promotional decisions. Output names its own accuracy (MAPE, bias) and refresh cadence so buyers know when to trust it and when to rerun it.

Move a multi-node retail network from a static "ship from nearest DC" routing rule to an agent-orchestrated, per-order allocation decision: for every digital order line, pick the node — DC, store, dark store, vendor drop-ship, marketplace partner, or split-shipment combination — that minimizes total landed cost, respects the customer's promised delivery window, protects store labor capacity, and reflects the merchant's carbon and brand-experience targets. Output is an approval-ready allocation policy and a per-order decision packet that writes back to the order management system (OMS) without an irreversible commit until the human policy gate is cleared.

Produce a per-SKU pricing move — new price, expected volume, expected margin, psychological price point, and risk flags — grounded in price-elasticity math, a markdown-cadence rubric tied to weeks-of-supply, competitor-response game theory, and MAP / UPP guardrails. Output is PO-ready by a pricing manager, not an essay about pricing theory.

Design and operate an in-store digital media network with AI-driven content targeting, computer vision audience analytics, programmatic ad-serving, and closed-loop sensor-attributed measurement — giving a retail operator a blueprint to turn physical store screens into a measurable, demand-partner-ready media channel that integrates with its broader retail media network. Output covers the full stack: screen-location zone taxonomy and scoring, AI-driven content scheduling and dayparting, computer vision audience-analytics configuration (with biometric-privacy compliance), demand-partner deal-type hierarchy, clean-room attribution pipeline design, regulatory compliance spec per jurisdiction, yield-management rules, brand-safety and creative-compliance gate, IAB Tech Lab measurement alignment, cross-surface integration with digital and conversational retail media, audit log schema, and a KPI scorecard with red-line rollback triggers. Distinct from `visual-merchandising-planogram-brief` (which governs physical product placement, fixture layout, and brand-block rules for shelving) and from `agentic-retail-media-mediation` (which governs ad mediation on conversational and AI-agent surfaces such as chatbots, AI Mode, and sponsored prompts): this skill is the *physical-world screen network* — the screens, sensors, measurement, and programmatic infrastructure the retailer operates inside the store itself.

Analyze current inventory levels against sales velocity, lead times, supplier terms, landed cost (including 2026-era tariffs and duties), and seasonal patterns to produce a prioritized, PO-ready reorder recommendation with specific quantities, timing, supplier actions, an MOQ-vs-EOQ reconciliation, a landed-cost-per-unit breakdown, a payment-terms sensitivity (net 30 vs. net 60 vs. early-pay discount), and a working-capital impact line — preventing both stockouts and overstock while respecting the merchant's cash-flow position.

Move a multi-store retailer from a published-once-and-pinned shift schedule to a continuous, agent-orchestrated labor-plan loop. Output is an approval-ready labor packet for each store and week: shift skeleton with named associates, role-coverage check against the live demand forecast, intra-week reflow rules, fairness audit, predictive-scheduling compliance check, and a write-back plan into the workforce-management (WFM) system. The skill produces a manager-reviewable plan, not an autopublish — the human store leader still owns the final post.

Build a defensive program against AI-generated and recycled damage photos in online returns, combining metadata rules, image-authenticity signals, behavioral scoring, and computer-vision comparison against the catalog. Output is a per-claim decisioning rubric, an evidence checklist for chargeback representment, a reviewer SOP, and a KPI scorecard — tuned for a retailer who is seeing photo-based not-as-described or damaged-on-arrival claims climb faster than their return volume can explain.

Turn a fleet of in-store headsets, tablets, or earpieces into a hands-free AI assistant program for sales-floor associates. Translate store format, staffing model, SOP library, and operational data sources into a concrete rollout plan — grounded utterance set, answer-library build, escalation matrix, privacy rules, KPI scorecard, and a 60-day pilot. Output is a deployable program brief, not a vendor comparison.

Turn an existing in-store camera fleet, self-checkout (SCO) footage, and exception-based reporting (EBR) journal into a prioritized, privacy-aware loss-prevention program. Translate shrink numbers, incident logs, camera coverage, and POS / EBR exceptions into a deployment plan, alert playbook, investigator workflow, and KPI scorecard for a computer-vision-based loss prevention (CV-LP) rollout — covering sweethearting at staffed lanes, scan-avoidance and barcode-occlusion at SCO, ticket-switching, organized retail crime (ORC) cluster cross-reference, and return-counter fraud — with an explicit honest-shopper friction-floor rule that protects throughput and complaint volume from over-alerting and an explicit named bridge to `return-fraud-image-shield` and `agentic-checkout-fraud-shield` so a returns-side or checkout-side abuse case lands in the same evidence trail.

Produce a store- and shelf-level planogram brief that converts sales velocity, margin, adjacency logic, vendor contracts, brand block rules, and 2026-era in-store digital surfaces (electronic shelf-edge labels, retail-media screens, AI image-recognition compliance) into a concrete placement plan a merchandiser, a generative-planogram engine, or a robotic shelf-scanner can execute. Output includes the math (space-to-sales, GMROF, facings formula), an explicit constraint-reconciliation trail (vendor-mandated facings vs. own-data preferred facings vs. fixture capacity vs. brand block rules), a compliance-check rubric for AI shelf-scan vendors, and a rollback / re-set trigger so a bad reset can be reverted before it costs a season.

Audit and prioritize the changes a retailer's catalog, structured data, storefront, and checkout need to be discoverable, comparable, and purchasable by 2026-era autonomous shopping agents (OpenAI Operator / ChatGPT shopping, Anthropic Computer Use, Google Shopping AI + Agent Protocol, Shopify Agent Commerce, Perplexity Shop, and long-tail browser agents). Output is a scored readiness report, a prioritized fix-it backlog with effort × impact, a named 2026-protocol compliance checklist, and a configuration of rate-limit / parity rules — tuned for a merchant whose agent-originated traffic and abandoned-basket rate are both climbing.

Author the mediation, disclosure, brand-safety, bid-floor, creative-compliance, prompt-injection-defense, measurement, and audit packet a retailer or marketplace needs before it monetizes a conversational or agent surface — Topsort Sponsored Prompts on chatbot product discovery, Target's ChatGPT contextual-ad pilot, Google AI Mode and AI Overviews sponsored placements, Microsoft Copilot retail-media surfaces, Amazon Sponsored on the Rufus / Buy-for-Me agent, Walmart Connect on Sparky, Roundel inside Target conversational inventory, Albertsons Media Collective on the Albertsons agentic shopping assistant, Kroger Precision Marketing inside the Kroger / Boost AI Search Bar, and the merchant's own brand-agent / Custom GPT / Claude Project / Gemini Gem when it surfaces sponsored adjacencies. Output is a turn-on-ready packet a retailer can hand to the retail-media team, the platform team, the legal team, and the brand-safety team and use as the *configuration source-of-truth* for the auction, the disclosure layer, the eligibility rules, the creative-compliance rules, and the closed-loop measurement contract on the conversational surface — not a pitch deck, not a prompt template, not a generic "AI ads" explainer.

Author the persona, knowledge plan, conversational guardrails, jurisdiction matrix, and audit / drift-detection scorecard for a brand-owned AI agent that speaks on the merchant's behalf across Microsoft Brand Agents on Shopify, Cognizant Agentic Retail CX on Gemini Enterprise, Argano Retail Clienteling Agent on Dynamics 365, Amicis Store Commerce Agent (voice-first), Salesforce Loyalty / Service / Commerce Agentforce skills, and the merchant's own Copilot Studio / Custom GPT / Claude Project / Gemini Gem deployments. Output is a turn-on-ready packet a retailer can hand to the platform team and the legal team and use as the system-prompt-and-grounding-set for the agent itself: persona spec, FAQ training-data plan, refusal posture, regulated-category guardrails, escalation rules, attribution rules across surfaces, audit-log schema, and a drift-detection scorecard with a rollback trigger. The skill replaces the off-the-shelf "brand voice doc + a few FAQs" pattern with a content-and-governance discipline tuned for an agent that will *speak unsupervised at machine speed* in front of the brand.

Design a retailer's AI-augmented clienteling program — the operational discipline by which named store associates (or a dedicated clienteling team) reach out to identified customers one-to-one across SMS, email, in-app, voice, and in-store appointment surfaces, supported by AI for next-best-action triggering, draft-composition, send-time optimization, and post-conversation summarization. Output is a deployable program brief covering platform selection, associate role and data-access model, AI-outreach configuration, segmentation and trigger taxonomy, channel-and-send-time policy, privacy and consent guardrails, escalation and handoff rules, attribution and incrementality measurement, and a phased rollout — not a vendor slide deck. The skill replaces the off-the-shelf "give associates a CRM and hope" pattern with a content-and-governance discipline tuned for a clienteling motion that has to scale across luxury, specialty, and mass formats without inviting consent, fairness, or attribution-double-counting incidents.

Produce a retailer-specific personalization roadmap that turns first-party behavioral, transactional, and contextual data into measurable revenue lift across the homepage, product-detail page, cart, checkout, email, SMS, retail-media, and post-purchase touchpoints — and explicitly into the off-site AI-assistant surface so the merchant's first-party signal is not stranded on its own domain. The output is a prioritized backlog of personalization plays, a data-readiness gap list, an anticipatory-vs-reactive decision rule per surface, named handoffs to `product-description-writer` (catalog content readiness) and `agentic-commerce-readiness` (off-site personalization parity), and a measurement plan — not a vendor slide deck.

Write SEO-optimized, conversion-focused product descriptions — title, bullet features, long-form copy, meta description, image alt text, structured-data attributes, and a conversational-readiness block — tailored to the target ecommerce platform (Shopify, Amazon, Walmart Marketplace, Target+, Etsy, TikTok Shop, DTC site) so the product ranks in search, is parseable by AI shopping agents (Operator, Anthropic Computer Use, Google Agent Protocol, Shopify Agent Commerce), and converts browsers and bots to buyers without tripping platform or legal guardrails.

Build a full, ready-to-schedule promotional campaign — mechanics, email suite, SMS, RCS, organic social, paid ad copy, on-site banners, push, and an A/B test plan with margin guardrails — for seasonal sales, clearance events, product launches, and loyalty pushes. Produce copy that fits platform character limits, complies with TCPA / CAN-SPAM / 10DLC / FTC, and ships with a margin-protection floor and a roll-back trigger so the merchant can launch the same day without lighting promotional margin on fire.

Translate a merchant's apparel, footwear, eyewear, jewelry, or beauty catalog and current size / fit data into a deployable virtual try-on (VTO) and fit-confidence program. Output is a prioritized rollout plan: which SKUs and categories qualify for VTO, which fit / size-recommendation pattern to use, which cite-able fit signals to expose to AI shopping assistants, the measurement plan that proves return-rate reduction, and the legal / accessibility / model-diversity guardrails. This skill assumes the merchant is responding to AI-search and AI-shopping channels — including assistants that surface VTO inline (Google Search after the April 30, 2026 Doppl-to-Search migration) — and treats VTO as a return-rate and conversion lever, not a marketing demo.

Draft first-contact-resolution-grade replies to any customer inquiry (not returns — see Return Policy Explainer) across email, chat, social, marketplace messages, and phone notes. Produce a channel-tuned, brand-voiced reply with a structured internal note and a pre-dispute chargeback deflection paragraph when applicable — so the team resolves in one touch, keeps decisions inside policy lanes, and does not re-set expectations the next agent has to walk back.

Generate clear, customer-facing explanations for return, exchange, refund, and warranty scenarios — with a full RMA + reverse-logistics-path + refund-method decision, dual-path (strict / goodwill) draft, RFID / serialized-item authentication step, and a fraud / dispute guardrail with a named bridge to `return-fraud-image-shield` — so frontline agents resolve the case in one touch, set correct expectations, route image-claim cases through the four-signal score before goodwill is granted, and protect the business from policy abuse and chargeback escalation.

Turn rough notes into a professional email matching your company's voice and tone.

Summarize meeting notes into action items, decisions, and follow-ups.

Craft professional responses to online reviews — both positive and negative.