Agent Skills
› forcedotcom/sf-skills
› data360-query
data360-query
GitHub用于 Salesforce Data Cloud 的数据检索技能，支持同步/异步 SQL、向量搜索、混合搜索及元数据探查。需先运行诊断脚本检查就绪状态，严格区分于标准 SOQL 查询和 Segment 设计任务。
Trigger Scenarios
用户执行 Data Cloud SQL 查询
用户进行向量或混合搜索
用户探查 Data Cloud 表结构或元数据
Install
npx skills add forcedotcom/sf-skills --skill data360-query -g -y
SKILL.md
Frontmatter
{
"name": "data360-query",
"metadata": {
"version": "1.0",
"cliTools": [
{
"tool": [
"node"
],
"semver": ">=18.0.0"
},
{
"tool": [
"sf"
],
"semver": ">=2.0.0"
}
],
"relatedSkills": [
"agentforce-observe",
"data360-orchestrate",
"data360-segment",
"platform-soql-query"
]
},
"description": "Salesforce Data Cloud Retrieve phase. Use this skill when the user runs Data Cloud SQL, async queries, vector search, search-index workflows, or metadata introspection for Data Cloud objects. TRIGGER when: user runs Data Cloud SQL, describe, async queries, vector search, search-index workflows, or metadata introspection for Data Cloud objects. DO NOT TRIGGER when: the task is standard CRM SOQL (use platform-soql-query), segment creation or calculated insight design (use data360-segment), or STDM\/session tracing\/parquet analysis (use agentforce-observe).",
"compatibility": "Requires an external community sf data360 CLI plugin and a Data Cloud-enabled org"
}
data360-query: 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 data360-query when the work involves:
sf data360 query *sf data360 search-index *sf data360 metadata *sf data360 profile *orsf data360 insight *inspection- understanding Data Cloud SQL results or query shape
Delegate elsewhere when the user is:
- writing standard CRM SOQL only → platform-soql-query
- designing segment or calculated insight assets → data360-segment
- analyzing STDM/session tracing/parquet telemetry → agentforce-observe
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 ../data360-orchestrate/scripts/diagnose-org.mjs -o <org> --phase retrieve --json. - Use describe before guessing columns.
- Prefer
sqlv2or 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 ../data360-orchestrate/scripts/diagnose-org.mjs -o <org> --phase retrieve --json
# optional query-plane probe, only with a real table name
node ../data360-orchestrate/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.jsonexamples/search-indexes/hybrid-structured.json
High-Signal Gotchas
- Data Cloud SQL is not SOQL.
- Table names should be double-quoted in SQL.
sqlv2is 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 describeis 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
Version History
- 1.37.0 Current 2026-08-13 14:52
- 1.31.0 2026-07-19 23:12
- 1.29.0 2026-07-05 18:48
