Retrieving Datacloud

Name: Retrieving Datacloud
Author: forcedotcom

forcedotcom/afv-library

523 installs
787 repo stars
Updated August 5, 2026
forcedotcom/afv-library

This is a copy of retrieving-datacloud by forcedotcom - installs and ranking accrue to the original listing.

retrieving-datacloud is a Salesforce AFV skill that queries and introspects Data Cloud via SQL, vector search, async queries, and the sf data360 CLI for developers retrieving Data Cloud objects and search indexes.

About

retrieving-datacloud is a forcedotcom/afv-library skill for the Salesforce Data Cloud Retrieve phase. It guides agents through Data Cloud SQL, describe operations, async queries, vector search, search-index workflows, and metadata introspection using the community sf data360 CLI plugin in a Data Cloud-enabled org. The skill triggers when developers run Data Cloud queries or inspect Data Cloud object metadata, and it explicitly defers standard CRM SOQL to querying-soql, segment creation to segmenting-datacloud, and STDM or parquet tracing to observing-agentforce. Developers reach for retrieving-datacloud when building retrieval pipelines, debugging Data Cloud SQL, or exploring search-index configuration during Agentforce or analytics integrations. The CLI-first workflow keeps agents on supported Data Cloud interfaces instead of guessing REST endpoints or mixing CRM and Data Cloud query languages.

Handles sync SQL, paginated SQL, async query workflows, and result interpretation
Supports vector search, hybrid search, and search-index operations
Performs table describe, profile, and insight metadata introspection
Requires external community sf data360 CLI plugin and Data Cloud-enabled org
Explicit routing: delegates standard CRM SOQL to querying-soql and segment design to segmenting-datacloud

Retrieving Datacloud by the numbers

523 all-time installs (skills.sh)
Data as of Aug 5, 2026 (Skillselion catalog sync)

npx skills add https://github.com/forcedotcom/afv-library --skill retrieving-datacloud

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

[![Listed on Skillselion](https://skillselion.com/badge/skills/forcedotcom/afv-library/retrieving-datacloud.svg)](https://skillselion.com/skills/forcedotcom/afv-library/retrieving-datacloud)

Installs	523
repo stars	★ 787
Last updated	August 5, 2026
Repository	forcedotcom/afv-library ↗

How do you query Salesforce Data Cloud with SQL?

Query, search, and introspect Salesforce Data Cloud using SQL, vector search, async queries, and metadata operations via the sf data360 CLI.

Who is it for?

Salesforce developers with a Data Cloud-enabled org who need CLI-guided SQL, vector search, and metadata introspection during retrieval workflows.

Skip if: Developers running standard CRM SOQL or designing calculated insights should use querying-soql or segmenting-datacloud instead of retrieving-datacloud.

When should I use this skill?

A task runs Data Cloud SQL, async queries, vector search, search-index workflows, or metadata introspection for Data Cloud objects.

What you get

Data Cloud SQL result sets, async query handles, vector search responses, and described Data Cloud object metadata.

Data Cloud query results
Vector search responses
Described Data Cloud metadata

By the numbers

Requires the external community sf data360 CLI plugin for Data Cloud operations

Files

SKILL.mdMarkdownGitHub ↗

retrieving-datacloud: Data Cloud Retrieve Phase

Use this skill when the user needs query, search, and metadata introspection for Data Cloud: sync SQL, paginated SQL, async query workflows, table describe, vector search, hybrid search, or search index operations.

When This Skill Owns the Task

Use retrieving-datacloud when the work involves:

sf data360 query *
sf data360 search-index *
sf data360 metadata *
sf data360 profile * or sf data360 insight * inspection
understanding Data Cloud SQL results or query shape

Delegate elsewhere when the user is:

writing standard CRM SOQL only → querying-soql
designing segment or calculated insight assets → segmenting-datacloud
analyzing STDM/session tracing/parquet telemetry → observing-agentforce

---

Required Context to Gather First

Ask for or infer:

target org alias
whether the user needs quick count, medium result set, large export, schema inspection, or semantic search
table/index name if known
whether the task is read-only SQL or search-index lifecycle management

---

Core Operating Rules

Treat Data Cloud SQL as its own query language, not SOQL.
Run the shared readiness classifier before relying on query/search surfaces: node ../orchestrating-datacloud/scripts/diagnose-org.mjs -o <org> --phase retrieve --json.
Use describe before guessing columns.
Prefer sqlv2 or async query flows for larger result sets.
Use vector search or hybrid search only when the search index lifecycle is healthy.
Keep STDM/parquet/session-tracing workflows out of this skill family.

---

Recommended Workflow

1. Classify readiness for retrieve work

node ../orchestrating-datacloud/scripts/diagnose-org.mjs -o <org> --phase retrieve --json
# optional query-plane probe, only with a real table name
node ../orchestrating-datacloud/scripts/diagnose-org.mjs -o <org> --phase retrieve --describe-table MyDMO__dlm --json

2. Choose the smallest correct query shape

sf data360 query sql -o <org> --sql 'SELECT COUNT(*) FROM "ssot__Individual__dlm"' 2>/dev/null
sf data360 query sqlv2 -o <org> --sql 'SELECT * FROM "ssot__Individual__dlm"' 2>/dev/null
sf data360 query async-create -o <org> --sql 'SELECT * FROM "ssot__Individual__dlm"' 2>/dev/null

3. Use describe before guessing fields

sf data360 query describe -o <org> --table ssot__Individual__dlm 2>/dev/null

4. Use vector or hybrid search only when an index exists

sf data360 search-index list -o <org> 2>/dev/null
sf data360 query vector -o <org> --index Knowledge_Index --query "reset password" --limit 5 2>/dev/null
sf data360 query hybrid -o <org> --index Knowledge_Index --query "reset password" --limit 5 2>/dev/null
sf data360 query hybrid -o <org> --index Insurance_Index --query "weather damage coverage" --prefilter "Type_of_Insurance__c='Home'" --limit 10 2>/dev/null

5. Reuse curated search-index examples when creating indexes

Use the phase-owned examples instead of inventing JSON from scratch:

examples/search-indexes/vector-knowledge.json
examples/search-indexes/hybrid-structured.json

---

High-Signal Gotchas

Data Cloud SQL is not SOQL.
Table names should be double-quoted in SQL.
sqlv2 is better than ad hoc OFFSET paging for medium result sets.
async query is preferable for large results.
search-index operations and vector/hybrid queries depend on the index lifecycle being healthy.
Hybrid search can use --prefilter, but only on fields configured as prefilter-capable when the search index was created.
HNSW index parameters are typically read-only on create; leave userValues: [] unless the platform explicitly documents otherwise.
query describe is not a universal tenant probe; only run it with a known DMO or DLO table after broader readiness has been confirmed.

---

Output Format

Retrieve task: <sql / sqlv2 / async / describe / vector / search-index>
Target org: <alias>
Target object: <table or index>
Commands: <key commands run>
Verification: <query rows / schema / status>
Next step: <segment / harmonize / follow-up>

---

References

README.md
examples/search-indexes/vector-knowledge.json
examples/search-indexes/hybrid-structured.json
../orchestrating-datacloud/assets/definitions/search-index.template.json
../orchestrating-datacloud/references/plugin-setup.md
../orchestrating-datacloud/references/feature-readiness.md

{
  "label": "<INDEX_NAME>",
  "developerName": "<INDEX_NAME>",
  "description": "Hybrid search index on a structured Data Cloud DMO",
  "sourceDmoDeveloperName": "<SOURCE_DMO>__dlm",
  "chunkDmoName": "<INDEX_NAME> chunk",
  "chunkDmoDeveloperName": "<INDEX_NAME>_chunk",
  "vectorDmoName": "<INDEX_NAME> index",
  "vectorDmoDeveloperName": "<INDEX_NAME>_index",
  "searchType": "HYBRID",
  "vectorEmbedding": {
    "vectorEmbeddingRelatedFields": []
  },
  "rankingConfigurations": [],
  "chunkingConfiguration": {
    "fieldLevelConfigurations": [
      {
        "sourceDmoDeveloperName": "<SOURCE_DMO>__dlm",
        "sourceDmoFieldDeveloperName": "<TEXT_FIELD>__c",
        "config": {
          "id": "passage_extraction",
          "userValues": [
            { "id": "max_tokens", "value": "512" },
            { "id": "strip_html", "value": "true" }
          ]
        }
      }
    ]
  },
  "vectorEmbeddingConfiguration": {
    "embeddingModel": {
      "id": "e5_large_v2",
      "userValues": [
        { "id": "dimension", "value": "1024" },
        { "id": "max_token_limit", "value": "512" }
      ]
    },
    "index": {
      "id": "HNSW",
      "userValues": []
    },
    "similarityMetric": "COSINE"
  }
}

{
  "label": "My_kav",
  "developerName": "My_kav",
  "sourceDmoDeveloperName": "ssot__KnowledgeArticleVersion__dlm",
  "chunkDmoName": "My_kav chunk",
  "chunkDmoDeveloperName": "My_kav_chunk",
  "vectorDmoName": "My_kav index",
  "vectorDmoDeveloperName": "My_kav_index",
  "searchType": "VECTOR",
  "vectorEmbedding": {
    "vectorEmbeddingRelatedFields": []
  },
  "chunkingConfiguration": {
    "fieldLevelConfigurations": [
      {
        "sourceDmoDeveloperName": "ssot__KnowledgeArticleVersion__dlm",
        "sourceDmoFieldDeveloperName": "ssot__Name__c",
        "config": {
          "id": "passage_extraction",
          "userValues": [
            { "id": "strip_html", "value": "true" },
            { "id": "max_tokens", "value": "512" }
          ]
        }
      }
    ]
  },
  "vectorEmbeddingConfiguration": {
    "embeddingModel": {
      "id": "e5_large_v2",
      "userValues": [
        { "id": "dimension", "value": "1024" },
        { "id": "max_token_limit", "value": "512" }
      ]
    },
    "index": {
      "id": "HNSW",
      "userValues": []
    },
    "similarityMetric": "COSINE"
  },
  "rankingConfigurations": []
}

retrieving-datacloud

Query and search workflows for Salesforce Data Cloud.

Use this skill for

quick SQL counts
paginated SQL (sqlv2)
async query lifecycles
table describe
vector search
hybrid search with optional prefilter
search index inspection and lifecycle work

Example requests

"Run a Data Cloud SQL query against unified profiles"
"Describe this Data Cloud table before I write SQL"
"Help me troubleshoot vector search in Data Cloud"
"Run a hybrid search with a prefilter in Data Cloud"
"Create and inspect a search index"

Common commands

sf data360 query sql -o myorg --sql 'SELECT COUNT(*) FROM "ssot__Individual__dlm"' 2>/dev/null
sf data360 query describe -o myorg --table ssot__Individual__dlm 2>/dev/null
sf data360 search-index list -o myorg 2>/dev/null
sf data360 query vector -o myorg --index Knowledge_Index --query "reset password" --limit 5 2>/dev/null
sf data360 query hybrid -o myorg --index Knowledge_Index --query "reset password" --limit 5 2>/dev/null

Example payloads

examples/search-indexes/vector-knowledge.json
examples/search-indexes/hybrid-structured.json

References

SKILL.md
../orchestrating-datacloud/assets/definitions/search-index.template.json
CREDITS.md

Related skills

Lark Openapi ExplorerInstantly explore, test, and generate calls against the full Lark (Feishu) OpenAPI surface without leaving their agent workflow.493k

Lark EventConsume real-time events from Lark/Feishu as structured NDJSON streams inside AI agent workflows.387k16k

Lark Openapi ExplorerWhen an existing Lark/Feishu skill or CLI command cannot fulfill a specific requirement and they need to discover and invoke the exact native OpenAPI endpoint.386k16k

Just ScrapeQuickly search, crawl, extract structured JSON, or monitor web pages without writing custom scraping code.245k41

Lark AppsQuery the current visibility and permission scope of a Lark (Feishu) app without writing HTTP client code.235k16k

Design An InterfaceGenerate multiple radically different interface or API designs in parallel before committing to one.188k198k

How it compares

Use retrieving-datacloud for Data Cloud SQL and vector search; use querying-soql for standard Salesforce CRM queries.

FAQ

What CLI does retrieving-datacloud require?

retrieving-datacloud requires the external community sf data360 CLI plugin and a Data Cloud-enabled Salesforce org. Agents use it for SQL, async queries, vector search, and metadata describe operations instead of standard SOQL tooling.

When should retrieving-datacloud not be used?

retrieving-datacloud is only for Data Cloud retrieval. Use querying-soql for standard CRM SOQL, segmenting-datacloud for segment or calculated insight design, and observing-agentforce for STDM, session tracing, or parquet analysis.

Backend & APIsagentsautomation

About

Retrieving Datacloud by the numbers

Add your badge

How do you query Salesforce Data Cloud with SQL?

Who is it for?

When should I use this skill?

What you get

By the numbers

Files

retrieving-datacloud: Data Cloud Retrieve Phase

When This Skill Owns the Task

Required Context to Gather First

Core Operating Rules

Recommended Workflow

1. Classify readiness for retrieve work

2. Choose the smallest correct query shape

3. Use describe before guessing fields

4. Use vector or hybrid search only when an index exists

5. Reuse curated search-index examples when creating indexes

High-Signal Gotchas

Output Format

References

Credits & Acknowledgments

retrieving-datacloud

Use this skill for

Example requests

Common commands

Example payloads

References

Related skills

How it compares

FAQ

What CLI does retrieving-datacloud require?

When should retrieving-datacloud not be used?

This week in AI coding