data360-query

Name: data360-query
Author: forcedotcom

744stars272forks

How to install data360-query?

forcedotcom/sf-skills/data360-query

$npx -y skills add forcedotcom/sf-skills --skill data360-query

Installs into the current project.

Summary

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-i

Files · 1

View on GitHub

SKILL.md

1	# data360-query: Data Cloud Retrieve Phase
2
3	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.
4
5	## When This Skill Owns the Task
6
7	Use `data360-query` when the work involves:
8	- `sf data360 query *`
9	- `sf data360 search-index *`
10	- `sf data360 metadata *`
11	- `sf data360 profile ` or `sf data360 insight ` inspection
12	- understanding Data Cloud SQL results or query shape
13
14	Delegate elsewhere when the user is:
15	- writing standard CRM SOQL only → [platform-soql-query](../platform-soql-query/SKILL.md)
16	- designing segment or calculated insight assets → [data360-segment](../data360-segment/SKILL.md)
17	- analyzing STDM/session tracing/parquet telemetry → [agentforce-observe](../agentforce-observe/SKILL.md)
18
19	---
20
21	## Required Context to Gather First
22
23	Ask for or infer:
24	- target org alias
25	- whether the user needs quick count, medium result set, large export, schema inspection, or semantic search
26	- table/index name if known
27	- whether the task is read-only SQL or search-index lifecycle management
28
29	---
30
31	## Core Operating Rules
32
33	- Treat Data Cloud SQL as its own query language, not SOQL.
34	- Run the shared readiness classifier before relying on query/search surfaces: `node ../data360-orchestrate/scripts/diagnose-org.mjs -o <org> --phase retrieve --json`.
35	- Use describe before guessing columns.
36	- Prefer `sqlv2` or async query flows for larger result sets.
37	- Use vector search or hybrid search only when the search index lifecycle is healthy.
38	- Keep STDM/parquet/session-tracing workflows out of this skill family.
39
40	---
41
42	## Recommended Workflow
43
44	### 1. Classify readiness for retrieve work
45	```bash
46	node ../data360-orchestrate/scripts/diagnose-org.mjs -o <org> --phase retrieve --json
47	# optional query-plane probe, only with a real table name
48	node ../data360-orchestrate/scripts/diagnose-org.mjs -o <org> --phase retrieve --describe-table MyDMO__dlm --json
49	```
50
51	### 2. Choose the smallest correct query shape
52	```bash
53	sf data360 query sql -o <org> --sql 'SELECT COUNT(*) FROM "ssot__Individual__dlm"' 2>/dev/null
54	sf data360 query sqlv2 -o <org> --sql 'SELECT * FROM "ssot__Individual__dlm"' 2>/dev/null
55	sf data360 query async-create -o <org> --sql 'SELECT * FROM "ssot__Individual__dlm"' 2>/dev/null
56	```
57
58	### 3. Use describe before guessing fields
59	```bash
60	sf data360 query describe -o <org> --table ssot__Individual__dlm 2>/dev/null
61	```
62
63	### 4. Use vector or hybrid search only when an index exists
64	```bash
65	sf data360 search-index list -o <org> 2>/dev/null
66	sf data360 query vector -o <org> --index Knowledge_Index --query "reset password" --limit 5 2>/dev/null
67	sf data360 query hybrid -o <org> --index Knowledge_Index --query "reset password" --limit 5 2>/dev/null
68	sf data360 query hybrid -o <org> --index Insurance_Index --query "weather damage coverage" --prefilter "Type_of_Insurance__c='Home'" --limit 10 2>/dev/null
69	```
70
71	### 5. Reuse curated search-index examples when creating indexes
72	Use the phase-owned examples instead of inventing JSON from scratch:
73	- `examples/search-indexes/vector-knowledge.json`
74	- `examples/search-indexes/hybrid-structured.json`
75
76	---
77
78	## High-Signal Gotchas
79
80	- Data Cloud SQL is not SOQL.
81	- Table names should be double-quoted in SQL.
82	- `sqlv2` is better than ad hoc OFFSET paging for medium result sets.
83	- async query is preferable for large results.
84	- search-index operations and vector/hybrid queries depend on the index lifecycle being healthy.
85	- Hybrid search can use `--prefilter`, but only on fields configured as prefilter-capable when the search index was created.
86	- HNSW index parameters are typically read-only on create; leave `userValues: []` unless the platform explicitly documents otherwise.
87	- `query describe` is not a universal tenant probe; only run it with a known DMO or DLO table after broader readiness has been confirmed.
88
89	---
90
91	## Output Format
92
93	```text
94	Retrieve task: <sql / sqlv2 / async / describe / vector / search-index>
95	Target org: <alias>
96	Target object: <table or index>
97	Commands: <key commands run>
98	Verification: <query rows / schema / status>
99	Next step: <segment / harmonize / follow-up>
100	```
101
102	---
103
104	## References
105
106	- [examples/search-indexes/vect

People who liked this also viewed

6 picks

Type

data360-query

744stars272forks

View on GitHub

How to install data360-query?

forcedotcom/sf-skills/data360-query

$npx -y skills add forcedotcom/sf-skills --skill data360-query

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# data360-query: Data Cloud Retrieve Phase
2
3	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.
4
5	## When This Skill Owns the Task
6
7	Use `data360-query` when the work involves:
8	- `sf data360 query *`
9	- `sf data360 search-index *`
10	- `sf data360 metadata *`
11	- `sf data360 profile ` or `sf data360 insight ` inspection
12	- understanding Data Cloud SQL results or query shape
13
14	Delegate elsewhere when the user is:
15	- writing standard CRM SOQL only → [platform-soql-query](../platform-soql-query/SKILL.md)
16	- designing segment or calculated insight assets → [data360-segment](../data360-segment/SKILL.md)
17	- analyzing STDM/session tracing/parquet telemetry → [agentforce-observe](../agentforce-observe/SKILL.md)
18
19	---
20
21	## Required Context to Gather First
22
23	Ask for or infer:
24	- target org alias
25	- whether the user needs quick count, medium result set, large export, schema inspection, or semantic search
26	- table/index name if known
27	- whether the task is read-only SQL or search-index lifecycle management
28
29	---
30
31	## Core Operating Rules
32
33	- Treat Data Cloud SQL as its own query language, not SOQL.
34	- Run the shared readiness classifier before relying on query/search surfaces: `node ../data360-orchestrate/scripts/diagnose-org.mjs -o <org> --phase retrieve --json`.
35	- Use describe before guessing columns.
36	- Prefer `sqlv2` or async query flows for larger result sets.
37	- Use vector search or hybrid search only when the search index lifecycle is healthy.
38	- Keep STDM/parquet/session-tracing workflows out of this skill family.
39
40	---
41
42	## Recommended Workflow
43
44	### 1. Classify readiness for retrieve work
45	```bash
46	node ../data360-orchestrate/scripts/diagnose-org.mjs -o <org> --phase retrieve --json
47	# optional query-plane probe, only with a real table name
48	node ../data360-orchestrate/scripts/diagnose-org.mjs -o <org> --phase retrieve --describe-table MyDMO__dlm --json
49	```
50
51	### 2. Choose the smallest correct query shape
52	```bash
53	sf data360 query sql -o <org> --sql 'SELECT COUNT(*) FROM "ssot__Individual__dlm"' 2>/dev/null
54	sf data360 query sqlv2 -o <org> --sql 'SELECT * FROM "ssot__Individual__dlm"' 2>/dev/null
55	sf data360 query async-create -o <org> --sql 'SELECT * FROM "ssot__Individual__dlm"' 2>/dev/null
56	```
57
58	### 3. Use describe before guessing fields
59	```bash
60	sf data360 query describe -o <org> --table ssot__Individual__dlm 2>/dev/null
61	```
62
63	### 4. Use vector or hybrid search only when an index exists
64	```bash
65	sf data360 search-index list -o <org> 2>/dev/null
66	sf data360 query vector -o <org> --index Knowledge_Index --query "reset password" --limit 5 2>/dev/null
67	sf data360 query hybrid -o <org> --index Knowledge_Index --query "reset password" --limit 5 2>/dev/null
68	sf data360 query hybrid -o <org> --index Insurance_Index --query "weather damage coverage" --prefilter "Type_of_Insurance__c='Home'" --limit 10 2>/dev/null
69	```
70
71	### 5. Reuse curated search-index examples when creating indexes
72	Use the phase-owned examples instead of inventing JSON from scratch:
73	- `examples/search-indexes/vector-knowledge.json`
74	- `examples/search-indexes/hybrid-structured.json`
75
76	---
77
78	## High-Signal Gotchas
79
80	- Data Cloud SQL is not SOQL.
81	- Table names should be double-quoted in SQL.
82	- `sqlv2` is better than ad hoc OFFSET paging for medium result sets.
83	- async query is preferable for large results.
84	- search-index operations and vector/hybrid queries depend on the index lifecycle being healthy.
85	- Hybrid search can use `--prefilter`, but only on fields configured as prefilter-capable when the search index was created.
86	- HNSW index parameters are typically read-only on create; leave `userValues: []` unless the platform explicitly documents otherwise.
87	- `query describe` is not a universal tenant probe; only run it with a known DMO or DLO table after broader readiness has been confirmed.
88
89	---
90
91	## Output Format
92
93	```text
94	Retrieve task: <sql / sqlv2 / async / describe / vector / search-index>
95	Target org: <alias>
96	Target object: <table or index>
97	Commands: <key commands run>
98	Verification: <query rows / schema / status>
99	Next step: <segment / harmonize / follow-up>
100	```
101
102	---
103
104	## References
105
106	- [examples/search-indexes/vect

People who liked this also viewed

6 picks

Type