$npx -y skills add forcedotcom/sf-skills --skill data360-orchestrateSalesforce Data Cloud product orchestrator for connect→prepare→harmonize→segment→act workflows. Use this skill when the user needs a multi-step Data Cloud pipeline, cross-phase troubleshooting, or data space and data kit management. TRIGGER when: user needs a multi-step Data Clou
| 1 | # data360-orchestrate: Salesforce Data Cloud Orchestrator |
| 2 | |
| 3 | Use this skill when the user needs **product-level Data Cloud workflow guidance** rather than a single isolated command family: pipeline setup, cross-phase troubleshooting, data spaces, data kits, or deciding whether a task belongs in Connect, Prepare, Harmonize, Segment, Act, or Retrieve. |
| 4 | |
| 5 | This skill intentionally follows sf-skills house style while using the external `sf data360` command surface as the runtime. The plugin is **not vendored into this repo**. |
| 6 | |
| 7 | --- |
| 8 | |
| 9 | ## When This Skill Owns the Task |
| 10 | |
| 11 | Use `data360-orchestrate` when the work involves: |
| 12 | - multi-phase Data Cloud setup or remediation |
| 13 | - data spaces (`sf data360 data-space *`) |
| 14 | - data kits (`sf data360 data-kit *`) |
| 15 | - health checks (`sf data360 doctor`) |
| 16 | - CRM-to-unified-profile pipeline design |
| 17 | - deciding how to move from ingestion → harmonization → segmentation → activation |
| 18 | - cross-phase troubleshooting where the root cause is not yet clear |
| 19 | |
| 20 | Delegate to a phase-specific skill when the user is focused on one area: |
| 21 | |
| 22 | | Phase | Use this skill | Typical scope | |
| 23 | |---|---|---| |
| 24 | | Connect | [data360-connect](../data360-connect/SKILL.md) | connections, connectors, source discovery | |
| 25 | | Prepare | [data360-prepare](../data360-prepare/SKILL.md) | data streams, DLOs, transforms, DocAI | |
| 26 | | Harmonize | [data360-harmonize](../data360-harmonize/SKILL.md) | DMOs, mappings, identity resolution, data graphs | |
| 27 | | Segment | [data360-segment](../data360-segment/SKILL.md) | segments, calculated insights | |
| 28 | | Act | [data360-activate](../data360-activate/SKILL.md) | activations, activation targets, data actions | |
| 29 | | Retrieve | [data360-query](../data360-query/SKILL.md) | SQL, search indexes, vector search, async query | |
| 30 | |
| 31 | Delegate outside the family when the user is: |
| 32 | - extracting Session Tracing / STDM telemetry → [agentforce-observe](../agentforce-observe/SKILL.md) |
| 33 | - writing CRM SOQL only → [platform-soql-query](../platform-soql-query/SKILL.md) |
| 34 | - loading CRM source data → [platform-data-manage](../platform-data-manage/SKILL.md) |
| 35 | - creating missing CRM schema → [platform-custom-object-generate](../platform-custom-object-generate/SKILL.md) or [platform-custom-field-generate](../platform-custom-field-generate/SKILL.md) |
| 36 | - implementing downstream Apex or Flow logic → [platform-apex-generate](../platform-apex-generate/SKILL.md), [automation-flow-generate](../automation-flow-generate/SKILL.md) |
| 37 | |
| 38 | --- |
| 39 | |
| 40 | ## Required Context to Gather First |
| 41 | |
| 42 | Ask for or infer: |
| 43 | - target org alias |
| 44 | - whether the plugin is already installed and linked |
| 45 | - whether the user wants design guidance, read-only inspection, or live mutation |
| 46 | - data sources involved: CRM objects, external databases, file ingestion, knowledge, etc. |
| 47 | - desired outcome: unified profiles, segments, activations, vector search, analytics, or troubleshooting |
| 48 | - whether the user is working in the default data space or a custom one |
| 49 | - whether the org has already been classified with `scripts/diagnose-org.mjs` |
| 50 | - which command family is failing today, if any |
| 51 | |
| 52 | If plugin availability or org readiness is uncertain, start with: |
| 53 | - [references/plugin-setup.md](references/plugin-setup.md) |
| 54 | - [references/feature-readiness.md](references/feature-readiness.md) |
| 55 | - `scripts/verify-plugin.sh` |
| 56 | - `scripts/diagnose-org.mjs` |
| 57 | - `scripts/bootstrap-plugin.sh` |
| 58 | |
| 59 | --- |
| 60 | |
| 61 | ## Core Operating Rules |
| 62 | |
| 63 | - Use the external `sf data360` plugin runtime; do **not** reimplement or vendor the command layer. |
| 64 | - Prefer the smallest phase-specific skill once the task is localized. |
| 65 | - Run readiness classification before mutation-heavy work. Prefer `scripts/diagnose-org.mjs` over guessing from one failing command. |
| 66 | - For `sf data360` commands, suppress linked-plugin warning noise with `2>/dev/null` unless the stderr output is needed for debugging. |
| 67 | - Distinguish **Data Cloud SQL** from CRM SOQL. |
| 68 | - Do **not** treat `sf data360 doctor` as a full-product readiness check; the current upstream command only checks the search-index surface. |
| 69 | - Do **not** treat `query describe` as a universal tenant probe; only use it with a known DMO/DLO table after broader readiness is confirmed. |
| 70 | - Preserve Data Cloud |