本文へ移動
cccskills
無料GitHub で公開

consumer-goods-cloud-setup

Consumer Goods Cloud setup: visit execution, retail execution, route planning, in-store task management, compliance checks, off-shelf detection, image recognition. NOT for territory planning and route optimization for sales reps - use integration/salesforce-maps-setup. NOT for B2B Commerce storefronts - use admin/b2b-commerce-store-setup.

インストール方法を見る

含まれるファイル(7)

  • SKILL.md8.7 KB
  • references/examples.md7.0 KB
  • references/gotchas.md6.5 KB
  • references/llm-anti-patterns.md3.2 KB
  • references/well-architected.md5.7 KB
  • scripts/check_consumer_goods_cloud_setup.py3.3 KB
  • templates/consumer-goods-cloud-setup-template.md639 B

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Consumer Goods Cloud Setup

Activate when configuring Salesforce Consumer Goods (CG) Cloud for a consumer-packaged-goods company: retail execution, visit planning, in-store task capture, order-taking on the field, promotion compliance, and image-recognition-driven off-shelf detection. CG Cloud is distinct from Field Service — it is merchandising-first, not dispatch-first.

Before Starting

  • Confirm the CG Cloud license and mobile offline package. The CG mobile app is its own download; reps cannot use the standard Salesforce mobile app for visit execution.
  • Map the retail hierarchy. Retailer → Banner → Store → Shelf is the typical hierarchy. Modeling this as Account hierarchies drives visit targeting, route planning, and reporting.
  • Know the visit cadence. Weekly, biweekly, monthly, or exception-triggered visits each imply a different Route Plan and Visit auto-generation strategy.

Core Concepts

Retail Store + Visit + Task model

RetailStore is its own standard object — "Create records for physical retail stores associated to business accounts" — not an Account record type. Visit (API 47.0 and later) tracks "information related to a field rep's visit to a retail store where they perform retail activities." The work inside a visit is AssessmentTask: "Perform activities such as planogram check, inventory check, promotion check, in-store survey, or custom task in stores." Visitor represents "the sales reps performing visits" and VisitedParty "the contact person at the account that's being visited."

Two models in one product

CG Cloud is half standard objects and half a cgcloud__ managed package, and the split is not intuitive. Retail Execution ships standard: RetailStore, Visit, AssessmentTask, RetailStoreKpi, RetailVisitKpi, InStoreLocation, Assortment, Promotion, RetailLocationGroup. Route planning, order taking, and inventory are managed-package custom objects — cgcloud__Trip_List__c ("Use Trip List to plan visits based on a predefined sequence of customers"), cgcloud__Visit_Template__c ("Template that describes the basic call behavior"), cgcloud__Order__c, cgcloud__Inventory__c, cgcloud__POS__c, cgcloud__Org_Unit__c. There is no object named RoutePlan.

Visit templates and KPI targets

cgcloud__Visit_Template__c is the "Template that describes the basic call behavior" — the task list a rep executes. Targets and results are separate standard objects: AssessmentIndicatorDefinition "Define parameters that act as markers of compliance for retail tasks to compare target and actual values," RetailStoreKpi maps "store groups to assessment indicator definition, products, and in-store location categories and define targets," and RetailVisitKpi captures "the actual information during a visit against the defined assessment indicator definition and target values." Store segmentation for targeting comes from RetailLocationGroup plus RetailStoreGroupAssignment.

Image Recognition / Computer Vision

CG Cloud integrates with Salesforce Image Recognition for on-shelf photo analysis. It scores SKU facing counts, out-of-stock flags, and planogram compliance. Requires IR license and the shipped ML models.

Common Patterns

Pattern: Weekly route with in-store survey

A cgcloud__Trip_List__c sequences a Tier-1 territory weekly; each Visit carries AssessmentTask records from a cgcloud__Visit_Template__c — a merchandising check, an AssessmentTaskOrder step ("Define an order activity that the sales rep can perform during a visit to stores"), and a compliance photo step. RetailVisitKpi records the captured values against the store's RetailStoreKpi targets.

Pattern: Off-shelf alert routing

Image Recognition flags a SKU out-of-stock against the InStoreLocation ("locations within a retail store's layout such as aisles, shelves, or backrooms") and the expected StoreProduct. A Case routes to the retailer's category manager, with resolution SLA tracked via Entitlement.

Pattern: Promotion compliance audit

A Promotion runs Aug 1–14, scoped by PromotionChannel ("Associate a promotion with a store, store group, or an account") and PromotionProduct. The visit template for that window includes a compliance AssessmentTask: "Is the endcap display up?" Photos attach through AssessmentTaskContentDocument; IR scores planogram match; RetailVisitKpi rows aggregate to a promotion compliance dashboard.

Decision Guidance

SituationRecommended ApproachReason
Scheduled weekly rep visitscgcloud__Trip_List__c + cgcloud__Visit_Template__cShipped flow; offline-capable
Exception-driven visitEvent-triggered Visit via FlowNo trip-list disruption
Planogram complianceImage Recognition + IR modelsDeterministic, auditable scoring
Field order captureAssessmentTaskOrder / cgcloud__Order__cNative to CG Cloud
Dispatch-based field workUse Field Service, not CGDifferent shipped features

Recommended Workflow

  1. Confirm CG Cloud license, IR license (if using), and mobile offline package are provisioned.
  2. Enable CG Cloud features in Setup and create the RetailStore account record type.
  3. Import the retail hierarchy (Account → RetailStore → InStoreLocation) and RetailLocationGroup segmentation before any visit or trip-list data.
  4. Define cgcloud__Visit_Template__c records per store tier; attach AssessmentTask definitions and RetailStoreKpi targets.
  5. Build cgcloud__Trip_List__c sequences per territory; assign Visitor records; smoke-test Visit generation.
  6. Configure Image Recognition models (shipped or custom-trained) and attach to photo task steps.
  7. Run a full round-trip in a sandbox: sync offline → execute a Visit → upload → verify KPIs populate.

Review Checklist

  • CG mobile offline app installed on a rep test device
  • RetailStore and RetailLocationGroup loaded before any Visit or trip-list records
  • Visit Templates assigned to every active store segment
  • Trip-list visit generation validated for next week's window
  • IR models trained / validated on agency SKU set
  • Offline conflict resolution policy documented
  • KPI dashboards render expected rollups per rep/territory

Salesforce-Specific Gotchas

  1. CG Cloud uses shipped platform events for visit sync. Disabling the events breaks offline reconciliation silently; always check the Platform Events usage monitor after enabling.
  2. Image Recognition requires pre-trained models per product line. Out-of-the-box models do not know your SKUs; budget model-training time before go-live.
  3. Trip-list regeneration is expensive. Rebuilding sequences on large territories can take hours — schedule off-hours.

Output Artifacts

ArtifactDescription
CG activation runbookLicense checks, feature toggles, data load order
Visit template catalogTemplates by store tier and program
Trip-list matrixTerritory × rep × cadence view
IR model inventoryModels in use, accuracy metrics, retrain cadence

Related Skills

  • architect/sales-cloud-architecture — account and data-model foundation
  • integration/platform-events-integration — CG visit-sync backbone

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

Use this skill when writing test-first, behavior-driven acceptance criteria in Given/When/Then format for a Salesforce user story. Covers happy path, edge cases, negative paths, permission boundaries, and data-state preconditions so the AC block can drive UAT scripts and Apex test design downstream. Trigger keywords: given when then, gherkin, behavior driven AC, test first acceptance criteria, scenario outline, BDD acceptance criteria. NOT for the user-story format itself (use admin/user-story-writing-for-salesforce). NOT for UAT script writing (use admin/uat-test-case-design). NOT for Apex test method generation (use agents/test-class-generator). NOT for high-level UAT planning (use admin/uat-and-acceptance-criteria). More triggers: acceptance criteria record, ac_id, req_id on a criterion, artefact under test, negative case for a rule-type requirement, no-match fall-through criterion, oracle for a Then clause, test type apex flow manual, criteria linter, check_ac_format.py, --manifest-dir.

日本語の概要は準備中です。原文の説明を表示しています。

PranavNagrecha/AwesomeSalesforceSkills192026年10月4日 更新

Task and Event objects: polymorphic WhatId/WhoId, Activity object model, ActivityHistory vs OpenActivity, activity timeline customization, bulk task creation, Einstein Activity Capture boundaries. NOT for turning on EAC or calendar sync — use admin/einstein-activity-capture-setup. NOT for Email-to-Case — use admin/case-management-setup. Covers ActivitiesSettings metadata, enableActivities, shared Task/Event custom fields and FLS, TaskStatus value sets, Shared Activities and TaskRelation/EventRelation, recurring and child activities, and partial-success bulk DML on Task.

日本語の概要は準備中です。原文の説明を表示しています。

PranavNagrecha/AwesomeSalesforceSkills192026年10月4日 更新

Design Invocable Apex actions that return deterministic, agent-friendly errors instead of surfacing raw exceptions to the LLM. NOT for authoring the action itself — @InvocableMethod schema, labels, security context — use agentforce/custom-agent-actions-apex. NOT for the Apex tests that force each error branch — use agentforce/agent-action-unit-tests.

日本語の概要は準備中です。原文の説明を表示しています。

PranavNagrecha/AwesomeSalesforceSkills192026年10月4日 更新

Use when designing how an Agentforce agent extracts structured input parameters (slots) from a user's natural-language utterance to invoke an action. Triggers: 'agent extract date from user', 'agent action argument extraction', 'agentforce slot filling', 'agent invocable input mapping', 'agent fails to fill required parameter'. NOT for action authoring (use agentforce/agent-actions) or for prompt-template variable binding (use agentforce/prompt-builder-templates).

日本語の概要は準備中です。原文の説明を表示しています。

PranavNagrecha/AwesomeSalesforceSkills192026年10月4日 更新

Apex test patterns for @InvocableMethod agent actions: per-reason-code branch coverage, bulk safety, callout mocking, deterministic assertions. NOT for testing whether the agent routes to the right topic or answers well — use agentforce/agent-testing-and-evaluation. NOT for designing the error envelope the tests assert on — use agentforce/agent-action-error-handling.

日本語の概要は準備中です。原文の説明を表示しています。

PranavNagrecha/AwesomeSalesforceSkills192026年10月4日 更新

Designing or reviewing Agentforce actions: Flow actions, Apex invocable actions, prompt-template actions, action naming, input and output contracts, confirmation requirements, and safe error behavior. Triggers: 'agent actions', 'build an agent that can look up an order', 'make the agent able to check order status', 'give the agent a capability', 'agent that can retrieve a record', 'flow action for agent', 'agent invocable action', 'action schema design'. NOT for writing the Apex class itself — use agentforce/custom-agent-actions-apex. NOT for the reason_code error envelope that stops an agent retry loop — use agentforce/agent-action-error-handling.

日本語の概要は準備中です。原文の説明を表示しています。

PranavNagrecha/AwesomeSalesforceSkills192026年10月4日 更新

PranavNagrecha のスキルをすべて見る

このスキルの問題を報告する