sf-datacloud-retrieve

Executes SQL queries, vector search, and metadata introspection against Salesforce Data Cloud.

1|Updated May 7, 2026
One-click install
npx skills add https://github.com/amanpraaj/sf-skill-hub --skill sf-datacloud-retrieve-amanpraaj
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: sf-datacloud-retrieve
Source: https://github.com/amanpraaj/sf-skill-hub/tree/main/skills/salesforce/sf-datacloud-retrieve
Command: npx skills add https://github.com/amanpraaj/sf-skill-hub --skill sf-datacloud-retrieve-amanpraaj

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Working with Salesforce Data Cloud requires knowing which query surface to use—sync SQL, paginated sqlv2, async queries, vector search, or hybrid search—and getting it wrong leads to failed queries, wrong syntax (Data Cloud SQL is not SOQL), or searches against unhealthy indexes. This Skill provides a structured retrieve-phase workflow that picks the correct query shape and validates readiness first. ## Core Features & Use Cases - Query Execution: Run quick SQL counts, paginated sqlv2 queries, and async query lifecycles via the sf data360 CLI plugin. - Schema Introspection: Describe Data Cloud tables before writing SQL so you never guess column names. - Vector & Hybrid Search: Execute semantic and hybrid searches with optional prefilters, plus create and inspect search indexes using curated JSON examples. - Use Case: You need to troubleshoot why a vector search on your Knowledge index returns no results. The Skill first runs the readiness classifier, lists search indexes to confirm lifecycle health, then runs the vector query with the correct index and parameters. ## Quick Start Ask the agent to run a Data Cloud SQL query against unified profiles in your org, for example counting rows in the ssot__Individual__dlm table.

Frequently Asked Questions about sf-datacloud-retrieve

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run a SQL query against Salesforce Data Cloud?▼

Use sf data360 query sql with your org alias and a SQL statement, quoting table names in double quotes. For larger result sets, use sqlv2 for pagination or async-create for big exports instead of ad hoc OFFSET paging.

How do I perform vector or hybrid search in Data Cloud?▼

Run sf data360 query vector or query hybrid with an index name, query text, and limit. Hybrid search supports a --prefilter flag, but only on fields configured as prefilter-capable when the search index was created.

Is Data Cloud SQL the same as SOQL?▼

No, Data Cloud SQL is its own query language and is not SOQL. Standard CRM SOQL tasks should use a dedicated SOQL skill, while Data Cloud tables must be double-quoted and queried through the data360 query commands.

What do I need before using the sf data360 CLI plugin?▼

You need the external community sf data360 CLI plugin installed and a Data Cloud-enabled Salesforce org. The Skill also runs a shared diagnose-org readiness classifier with the retrieve phase before relying on query or search surfaces.

Why does my Data Cloud vector search return no results?▼

Vector and hybrid queries depend on the search index lifecycle being healthy. List indexes with sf data360 search-index list to confirm the index exists and is active before running searches.

When should I not use this Data Cloud retrieve workflow?▼

Avoid it for standard CRM SOQL queries, segment or calculated insight design, and STDM/session tracing or parquet telemetry analysis. Those tasks belong to dedicated SOQL, segment, or observability skills instead.