Skip to main content
skill CX Codex

data-cloud-2025 — Claude Code skill: what it does, how to install

data-cloud-2025 is a Claude Code skill with Salesforce Data Cloud architecture patterns for designing data streams, identity resolution rules, and CRM activation pipelines.

MIT 155 installs ★ 66 updated 2026-06-18

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add JosiahSiegel/claude-plugin-marketplace --skill data-cloud-2025 -a claude-code
Open on GitHub

What data-cloud-2025 does

This skill provides 2025 architecture patterns for Salesforce Data Cloud. It guides coding assistants through mapping source DSO records into common Data Model Objects (DMO), configuring identity resolution rules, and writing calculated insights like churn risk or customer lifetime value. It covers Zero Copy setups for Snowflake, BigQuery, and Databricks, alongside context grounding for Agentforce.

Guidance is organized across modular documents in references/. The assistant references only relevant files during tasks involving CDC streaming, vector search, or Reverse ETL pipelines. A dedicated instruction enforces Windows path handling: the agent must supply backslashes \ in file_path parameters to prevent edit failures on Windows systems.

The included operational guidelines explicitly recommend Zero Copy architecture over traditional batch imports whenever data volume exceeds 10M records.

What it helps with

  • Map inbound data lake streams into Data Model Objects (DMO)
  • Set match and reconciliation rules for customer identity resolution
  • Configure Zero Copy sharing with Databricks or Snowflake
  • Ground Agentforce actions using unified profile data and calculated insights

Example prompts for the agent

  • Map incoming transaction fields from S3 into standard DMO structures
  • Draft identity resolution match rules using phone and email criteria
  • Configure a Zero Copy data stream connection to Snowflake for 15M records

How to install data-cloud-2025

1Skills CLI (Vercel)

npx skills add JosiahSiegel/claude-plugin-marketplace --skill data-cloud-2025 -a claude-code

2Manually: put the files in place

~/.claude/skills/data-cloud-2025/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/data-cloud-2025/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about data-cloud-2025

How to install data-cloud-2025 in Claude Code?

Run npx skills add JosiahSiegel/claude-plugin-marketplace --skill data-cloud-2025 -a claude-code in your terminal. The configuration is stored at ~/.claude/skills/data-cloud-2025/SKILL.md.

What does data-cloud-2025 do?

It gives AI assistants architecture patterns and workflows for Salesforce Data Cloud, covering ingestion, identity resolution, Zero Copy lakes, and Agentforce grounding.

When does the skill advise using Zero Copy?

Its performance guidelines prescribe Zero Copy data sharing instead of standard batch imports for datasets exceeding 10M records.

Source text

SKILL.md · MIT
---
name: data-cloud-2025
description: |
  Salesforce Data Cloud integration patterns and architecture (2025).
  PROACTIVELY activate for: (1) Data Cloud setup and ingestion, (2) Data Streams (cloud, mobile, web SDK, ingestion API), (3) data model objects (DMO) and source objects (DSO), (4) identity resolution and unified profiles, (5) calculated insights and segmentation, (6) activations to Marketing Cloud, advertising platforms, Salesforce CRM, (7) Bring Your Own Lake (BYOL) with Snowflake, BigQuery, Databricks, (8) zero-copy data sharing, (9) Data Cloud + Agentforce grounding, (10) consent management and compliance.
  Provides: data-stream selection matrix, identity resolution rules, segmentation patterns, BYOL configuration, and activation playbook.
---

## CRITICAL GUIDELINES

### Windows File Path Requirements

**MANDATORY: Always Use Backslashes on Windows for File Paths**

When using Edit or Write tools on Windows, you MUST use backslashes (`\`) in file paths, NOT forward slashes (`/`).

Examples:
- WRONG: `D:/repos/project/file.tsx`
- CORRECT: `D:\repos\project\file.tsx`

This applies to:
- Edit tool file_path parameter
- Write tool file_path parameter
- All file operations on Windows systems

### Documentation Guidelines

NEVER create new documentation files unless explicitly requested by the user.

- **Priority**: Update existing README.md files rather than creating new documentation
- **Repository cleanliness**: Keep repository root clean - only README.md unless user requests otherwise
- **Style**: Documentation should be concise, direct, and professional - avoid AI-generated tone
- **User preference**: Only create additional .md files when user specifically asks for documentation

---

# Salesforce Data Cloud Integration Patterns (2025)

## What is Salesforce Data Cloud?

Salesforce Data Cloud is a real-time customer data platform (CDP) that unifies data from any source to create a complete, actionable view of every customer. It powers AI, automation, and analytics across the entire Customer 360 platform.

**Key Capabilities:**
- **Data Ingestion** — Connect 200+ sources (Salesforce, external systems, data lakes)
- **Data Harmonization** — Map disparate data to unified data model
- **Identity Resolution** — Match and merge customer records across sources
- **Real-Time Activation** — Trigger actions based on streaming data
- **Zero Copy Architecture** — Query data in place without moving it
- **AI/ML Ready** — Powers Einstein, Agentforce, and predictive models
- **Vector Database** (GA March 2025) — Store and query unstructured data with semantic search
- **Hybrid Search** (Pilot 2025) — Combine semantic and keyword search for accuracy

## Reference Map

Detailed material lives in `references/`. Load only what the current task needs.

| Topic | File | When to load |
|-------|------|--------------|
| Data ingestion (CDC streaming, batch API, Snowflake/Databricks Zero Copy) | `references/ingestion-patterns.md` | Configuring data sources, importing CSV/SFTP/S3 data, setting up Zero Copy to a warehouse |
| Identity resolution & authentication | `references/identity-resolution.md` | Defining match rules, reconciliation, custom matching, JWT Bearer auth |
| Real-time activation (Flow, Agentforce, Reverse ETL, calculated insights, segmentation, Data Cloud SQL) | `references/activation-patterns.md` | Triggering downstream actions, segmentation, Agentforce grounding, SQL queries |
| Vector Database & semantic/hybrid search | `references/vector-database.md` | Unstructured data indexing, semantic search, Einstein Copilot Search, multi-language search |

## Data Cloud Architecture

```text
┌──────────────────────────────────────────────────────────┐
│                    Data Sources                          │
│  Salesforce CRM │ External Apps │ Data Warehouses │ APIs │
└────────┬─────────────────┬──────────────┬───────────┬────┘
         │                 │              │           │
    ┌────▼─────────────────▼──────────────▼───────────▼────┐
    │         Data Cloud Connectors & Ingestion            │
    │  ├─ Real-time Streaming (Change Data Capture)        │
    │  ├─ Batch Import (scheduled/on-demand)               │
    │  └─ Zero Copy (Snowflake, Databricks, BigQuery)      │
    └────────────────────────┬─────────────────────────────┘
                             │
    ┌────────────────────────▼─────────────────────────────┐
    │            Data Model & Harmonization                │
    │  ├─ Map to Common Data Model (DMO objects)           │
    │  ├─ Identity Resolution (match & merge)              │
    │  └─ Data Transformation (calculated insights)        │
    └────────────────────────┬─────────────────────────────┘
                             │
    ┌────────────────────────▼─────────────────────────────┐
    │         Unified Customer Profile (360° View)         │
    │  ├─ Demographics, Transactions, Behavior, Events     │
    │  └─ Real-time Profile API for instant access         │
    └────────────────────────┬─────────────────────────────┘
                             │
    ┌────────────────────────▼─────────────────────────────┐
    │              Activation & Actions                    │
    │  ├─ Salesforce Flow (real-time automation)           │
    │  ├─ Marketing Cloud (segmentation/journeys)          │
    │  ├─ Agentforce (AI agents)                           │
    │  ├─ Einstein AI (predictions/recommendations)        │
    │  └─ External Systems (reverse ETL)                   │
    └──────────────────────────────────────────────────────┘
```

## Core Workflow

1. **Identify use case** — Ingestion, identity, segmentation, activation, or unstructured/AI search? Pick the matching reference.
2. **Map data sources** — CRM CDC (real-time), external batch (S3/SFTP), or warehouse Zero Copy.
3. **Define DMOs and matching** — Map source fields to Data Model Objects; configure identity resolution match + reconciliation rules.
4. **Build insights / segments** — Calculated insights for KPIs (LTV, churn risk); segments for activation targets.
5. **Activate** — Flow / Platform Events / Agentforce actions / Reverse ETL data actions.
6. **Validate** — Use Data Cloud SQL workbench, check sync logs, monitor identity resolution metrics.

## Best Practices

### Performance
- **Use Zero Copy** for large datasets (>10M records)
- **Batch imports** outside business hours
- **Index frequently queried fields** in Data Cloud
- **Limit real-time triggers** to critical events
- **Cache unified profiles** when possible

### Security
- **Field-level security** applies to Data Cloud queries from Salesforce
- **Data masking** for PII in non-production environments
- **Encryption at rest** and in transit (TLS 1.2+)
- **Audit logging** for all data access
- **Role-based access control** (RBAC) for Data Cloud users

### Data Quality
- **Data validation** before ingestion
- **Deduplication rules** at source and in Data Cloud
- **Data lineage tracking** (know source of each field)
- **Quality scores** for unified profiles
- **Regular data audits** and cleansing

## Resources

- **Data Cloud Documentation:** https://developer.salesforce.com/docs/data/data-cloud-int/guide
- **Zero Copy Partner Network:** https://www.salesforce.com/data/zero-copy/
- **Data Cloud Pricing:** Part of Customer 360 platform, usage-based pricing
- **Trailhead:** "Data Cloud Basics" and "Data Cloud for Developers"

© JosiahSiegel · MIT · JosiahSiegel/claude-plugin-marketplace

Similar skills

All skills for Data and databases →

From the same set96

The whole set →
deployment-stacks-2025 The deployment-stacks-2025 skill covers Azure Deployment Stacks, including resource protection, cleanup rules, Bicep templates, and az stack commands. CX Codex +1 157installs advanced-patterns advanced-patterns provides advanced T-SQL query patterns for SQL Server and Azure SQL, covering recursive CTEs, APPLY operators, MERGE, and temporal tables. CX Codex +1 157installs microsoft-guide microsoft-guide is a Claude Code skill for finding Microsoft guidance on .NET microservice architecture. It activates for questions about DDD, CQRS, integration events, or deployment. CX Codex +1 157installs terraform-tasks terraform-tasks — a skill for autonomous Terraform work: generates infrastructure code, builds CI/CD pipelines, migrates resources to state, fixes version issues. CX Codex +1 155installs advanced-array-patterns advanced-array-patterns is a Claude Code skill with Bash array recipes for indexed and associative arrays, mapfile, slicing, and safe iteration under set -u. CX Codex +1 155installs ffmpeg-noise-reduction ffmpeg-noise-reduction is a Claude Code skill that references FFmpeg filters for noisy video and audio, helping choose a filter and arguments for the noise. CX Codex +1 150installs cloudflare-knowledge cloudflare-knowledge is a Claude Code skill that opens Cloudflare references for Workers, Pages, R2, D1, Workers AI and Zero Trust during setup. CX Codex +1 139installs unity-shaders-rendering unity-shaders-rendering guides AI assistants through Unity shaders, lighting setups, and render pipelines across URP, HDRP, and Built-in RP. CX Codex +1 133installs

More in the catalog

Project sponsors

Companies that keep this analytics open