@salesforce/afv-skills 1.21.0 → 1.22.0

package/skills/data360-orchestrate/SKILL.md

@@ -0,0 +1,235 @@
+---
+name: data360-orchestrate
+description: "Salesforce 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 Cloud pipeline, asks to set up or troubleshoot Data Cloud across phases, manages data spaces or data kits, or wants a cross-phase sf data360 workflow. DO NOT TRIGGER when: work is isolated to a single phase (use the matching phase-specific skill), the task is STDM/session tracing/parquet telemetry (use agentforce-observe), standard CRM SOQL (use platform-soql-query), or Apex implementation (use platform-apex-generate)."
+compatibility: "Requires an external community sf data360 CLI plugin and a Data Cloud-enabled org"
+metadata:
+  version: "1.0"
+---
+
+# data360-orchestrate: Salesforce Data Cloud Orchestrator
+
+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.
+
+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**.
+
+---
+
+## When This Skill Owns the Task
+
+Use `data360-orchestrate` when the work involves:
+- multi-phase Data Cloud setup or remediation
+- data spaces (`sf data360 data-space *`)
+- data kits (`sf data360 data-kit *`)
+- health checks (`sf data360 doctor`)
+- CRM-to-unified-profile pipeline design
+- deciding how to move from ingestion → harmonization → segmentation → activation
+- cross-phase troubleshooting where the root cause is not yet clear
+
+Delegate to a phase-specific skill when the user is focused on one area:
+
+| Phase | Use this skill | Typical scope |
+|---|---|---|
+| Connect | [data360-connect](../data360-connect/SKILL.md) | connections, connectors, source discovery |
+| Prepare | [data360-prepare](../data360-prepare/SKILL.md) | data streams, DLOs, transforms, DocAI |
+| Harmonize | [data360-harmonize](../data360-harmonize/SKILL.md) | DMOs, mappings, identity resolution, data graphs |
+| Segment | [data360-segment](../data360-segment/SKILL.md) | segments, calculated insights |
+| Act | [data360-activate](../data360-activate/SKILL.md) | activations, activation targets, data actions |
+| Retrieve | [data360-query](../data360-query/SKILL.md) | SQL, search indexes, vector search, async query |
+
+Delegate outside the family when the user is:
+- extracting Session Tracing / STDM telemetry → [agentforce-observe](../agentforce-observe/SKILL.md)
+- writing CRM SOQL only → [platform-soql-query](../platform-soql-query/SKILL.md)
+- loading CRM source data → [platform-data-manage](../platform-data-manage/SKILL.md)
+- 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)
+- implementing downstream Apex or Flow logic → [platform-apex-generate](../platform-apex-generate/SKILL.md), [automation-flow-generate](../automation-flow-generate/SKILL.md)
+
+---
+
+## Required Context to Gather First
+
+Ask for or infer:
+- target org alias
+- whether the plugin is already installed and linked
+- whether the user wants design guidance, read-only inspection, or live mutation
+- data sources involved: CRM objects, external databases, file ingestion, knowledge, etc.
+- desired outcome: unified profiles, segments, activations, vector search, analytics, or troubleshooting
+- whether the user is working in the default data space or a custom one
+- whether the org has already been classified with `scripts/diagnose-org.mjs`
+- which command family is failing today, if any
+
+If plugin availability or org readiness is uncertain, start with:
+- [references/plugin-setup.md](references/plugin-setup.md)
+- [references/feature-readiness.md](references/feature-readiness.md)
+- `scripts/verify-plugin.sh`
+- `scripts/diagnose-org.mjs`
+- `scripts/bootstrap-plugin.sh`
+
+---
+
+## Core Operating Rules
+
+- Use the external `sf data360` plugin runtime; do **not** reimplement or vendor the command layer.
+- Prefer the smallest phase-specific skill once the task is localized.
+- Run readiness classification before mutation-heavy work. Prefer `scripts/diagnose-org.mjs` over guessing from one failing command.
+- For `sf data360` commands, suppress linked-plugin warning noise with `2>/dev/null` unless the stderr output is needed for debugging.
+- Distinguish **Data Cloud SQL** from CRM SOQL.
+- Do **not** treat `sf data360 doctor` as a full-product readiness check; the current upstream command only checks the search-index surface.
+- Do **not** treat `query describe` as a universal tenant probe; only use it with a known DMO/DLO table after broader readiness is confirmed.
+- Preserve Data Cloud-specific API-version workarounds when they matter.
+- Prefer generic, reusable JSON definition files over org-specific workshop payloads.
+
+---
+
+## Recommended Workflow
+
+### 1. Verify the runtime and auth
+Confirm:
+- `sf` is installed
+- the community Data Cloud plugin is linked
+- the target org is authenticated
+
+Recommended checks:
+```bash
+sf data360 man
+sf org display -o <alias>
+bash ./scripts/verify-plugin.sh <alias>
+```
+
+Treat `sf data360 doctor` as a broad health signal, not the sole gate. On partially provisioned orgs it can fail even when read-only command families like connectors, DMOs, or segments still work.
+
+### 2. Classify readiness before changing anything
+Run the shared classifier first:
+```bash
+node ./scripts/diagnose-org.mjs -o <org> --json
+```
+
+Only use a query-plane probe after you know the table name is real:
+```bash
+node ./scripts/diagnose-org.mjs -o <org> --phase retrieve --describe-table MyDMO__dlm --json
+```
+
+Use the classifier to distinguish:
+- empty-but-enabled modules
+- feature-gated modules
+- query-plane issues
+- runtime/auth failures
+
+### 3. Discover existing state with read-only commands
+Use targeted inspection after classification:
+```bash
+sf data360 doctor -o <org> 2>/dev/null
+sf data360 data-space list -o <org> 2>/dev/null
+sf data360 data-stream list -o <org> 2>/dev/null
+sf data360 dmo list -o <org> 2>/dev/null
+sf data360 identity-resolution list -o <org> 2>/dev/null
+sf data360 segment list -o <org> 2>/dev/null
+sf data360 activation platforms -o <org> 2>/dev/null
+```
+
+### 4. Localize the phase
+Route the task:
+- source/connector issue → Connect
+- ingestion/DLO/stream issue → Prepare
+- mapping/IR/unified profile issue → Harmonize
+- audience or insight issue → Segment
+- downstream push issue → Act
+- SQL/search/index issue → Retrieve
+
+### 5. Choose deterministic artifacts when possible
+Prefer JSON definition files and repeatable scripts over one-off manual steps. Generic templates live in:
+- `assets/definitions/data-stream.template.json`
+- `assets/definitions/dmo.template.json`
+- `assets/definitions/mapping.template.json`
+- `assets/definitions/relationship.template.json`
+- `assets/definitions/identity-resolution.template.json`
+- `assets/definitions/data-graph.template.json`
+- `assets/definitions/calculated-insight.template.json`
+- `assets/definitions/segment.template.json`
+- `assets/definitions/activation-target.template.json`
+- `assets/definitions/activation.template.json`
+- `assets/definitions/data-action-target.template.json`
+- `assets/definitions/data-action.template.json`
+- `assets/definitions/search-index.template.json`
+
+### 6. Verify after each phase
+Typical verification:
+- stream/DLO exists
+- DMO/mapping exists
+- identity resolution run completed
+- unified records or segment counts look correct
+- activation/search index status is healthy
+
+---
+
+## High-Signal Gotchas
+
+- `connection list` requires `--connector-type`.
+- `dmo list --all` is useful when you need the full catalog, but first-page `dmo list` is often enough for readiness checks and much faster.
+- Segment creation may need `--api-version 64.0`.
+- `segment members` returns opaque IDs; use SQL joins for human-readable details.
+- `sf data360 doctor` can fail on partially provisioned orgs even when some read-only commands still work; fall back to targeted smoke checks.
+- `query describe` errors such as `Couldn't find CDP tenant ID` or `DataModelEntity ... not found` are query-plane clues, not automatic proof that the whole product is disabled.
+- Many long-running jobs are asynchronous in practice even when the command returns quickly.
+- Some Data Cloud operations still require UI setup outside the CLI runtime.
+
+---
+
+## Output Format
+
+When finishing, report in this order:
+1. **Task classification**
+2. **Runtime status**
+3. **Readiness classification**
+4. **Phase(s) involved**
+5. **Commands or artifacts used**
+6. **Verification result**
+7. **Next recommended step**
+
+Suggested shape:
+
+```text
+Data Cloud task: <setup / inspect / troubleshoot / migrate>
+Runtime: <plugin ready / missing / partially verified>
+Readiness: <ready / ready_empty / partial / feature_gated / blocked>
+Phases: <connect / prepare / harmonize / segment / act / retrieve>
+Artifacts: <json files, commands, scripts>
+Verification: <passed / partial / blocked>
+Next step: <next phase, setup guidance, or cross-skill handoff>
+```
+
+---
+
+## Cross-Skill Integration
+
+| Need | Delegate to | Reason |
+|---|---|---|
+| load or clean CRM source data | [platform-data-manage](../platform-data-manage/SKILL.md) | seed or fix source records before ingestion |
+| create missing CRM schema | [platform-custom-object-generate](../platform-custom-object-generate/SKILL.md), [platform-custom-field-generate](../platform-custom-field-generate/SKILL.md) | Data Cloud expects existing objects/fields |
+| deploy permissions or bundles | [platform-metadata-deploy](../platform-metadata-deploy/SKILL.md) | environment preparation |
+| write Apex against Data Cloud outputs | [platform-apex-generate](../platform-apex-generate/SKILL.md) | code implementation |
+| Flow automation after segmentation/activation | [automation-flow-generate](../automation-flow-generate/SKILL.md) | declarative orchestration |
+| session tracing / STDM / parquet analysis | [agentforce-observe](../agentforce-observe/SKILL.md) | different Data Cloud use case |
+
+---
+
+## Reference Map
+
+### Start here
+- [README.md](README.md)
+- [references/plugin-setup.md](references/plugin-setup.md)
+- [references/feature-readiness.md](references/feature-readiness.md)
+- [UPSTREAM.md](UPSTREAM.md)
+
+### Phase skills
+- [data360-connect](../data360-connect/SKILL.md)
+- [data360-prepare](../data360-prepare/SKILL.md)
+- [data360-harmonize](../data360-harmonize/SKILL.md)
+- [data360-segment](../data360-segment/SKILL.md)
+- [data360-activate](../data360-activate/SKILL.md)
+- [data360-query](../data360-query/SKILL.md)
+
+### Deterministic helpers
+- [scripts/bootstrap-plugin.sh](scripts/bootstrap-plugin.sh)
+- [scripts/verify-plugin.sh](scripts/verify-plugin.sh)
+- [scripts/diagnose-org.mjs](scripts/diagnose-org.mjs)
+- [assets/definitions/](assets/definitions/)

package/skills/data360-orchestrate/UPSTREAM.md

@@ -0,0 +1,45 @@
+# Upstream Distillation Map for data360-orchestrate
+
+This file exists to make downstream maintenance easy without sacrificing sf-skills consistency.
+
+## Maintenance contract
+
+When upstream changes, do **not** copy blindly.
+
+Instead:
+1. review new upstream commits
+2. identify changed command behaviors, install patterns, or gotchas
+3. update sf-skills prompts and templates in a distilled form
+4. keep naming, attribution, and cross-skill boundaries consistent with sf-skills
+5. update this file with the new reviewed commit SHAs
+
+## High-priority upstream areas to re-check
+
+- installation / linking workflow for the community plugin
+- command counts and topic coverage
+- API-version guidance
+- known issues and bug-fix notes
+- live-tested command set
+- any new commands affecting Connect / Prepare / Harmonize / Segment / Act / Retrieve boundaries
+- connector-specific payload examples worth distilling into generic repo-safe examples
+- search-index / hybrid-search guidance and any command-surface changes around hybrid scoring or prefilter behavior
+- Ingestion API schema-upload flow, send-data examples, and problem-record guidance
+- unstructured-source setup differences between connection-level reruns, stream refreshes, and initial UI seeding
+- UI-only gaps where upstream introduces browser automation; validate before importing
+
+## Cross-skill boundary reminders
+
+Keep Data Cloud product work in `*-datacloud`, but do not blur into:
+- `agentforce-observe` for STDM/session tracing/parquet workflows
+- `platform-soql-query` for CRM SOQL-only tasks
+- `platform-data-manage` for CRM record seeding/cleanup
+- `platform-*-generate` skills for CRM schema creation (custom objects, fields, validation rules, etc.)
+
+## Local helper files in this family
+
+- `references/plugin-setup.md`
+- `scripts/bootstrap-plugin.sh`
+- `scripts/verify-plugin.sh`
+- `assets/definitions/`
+
+These are sf-skills-owned conveniences and should evolve independently from upstream when that improves user experience.

package/skills/data360-orchestrate/assets/definitions/activation-target.template.json

@@ -0,0 +1,5 @@
+{
+  "developerName": "CRM_Target",
+  "displayName": "CRM Target",
+  "description": "Example activation target definition for a downstream destination"
+}

package/skills/data360-orchestrate/assets/definitions/activation.template.json

@@ -0,0 +1,7 @@
+{
+  "developerName": "High_Value_Customers_Activation",
+  "displayName": "High Value Customers Activation",
+  "description": "Example activation linking a published segment to a destination target",
+  "segmentName": "High_Value_Customers",
+  "activationTargetName": "CRM_Target"
+}

package/skills/data360-orchestrate/assets/definitions/calculated-insight.template.json

@@ -0,0 +1,7 @@
+{
+  "developerName": "Lifetime_Value",
+  "displayName": "Lifetime Value",
+  "description": "Example calculated insight over an order-style DMO",
+  "definitionType": "CALCULATED_METRIC",
+  "expression": "SELECT ssot__IndividualId__c, SUM(ssot__TotalAmount__c) AS total_spend FROM ssot__SalesOrder__dlm GROUP BY ssot__IndividualId__c"
+}

package/skills/data360-orchestrate/assets/definitions/data-action-target.template.json

@@ -0,0 +1,5 @@
+{
+  "developerName": "Webhook_Target",
+  "displayName": "Webhook Target",
+  "description": "Example data action target for downstream delivery"
+}

package/skills/data360-orchestrate/assets/definitions/data-action.template.json

@@ -0,0 +1,5 @@
+{
+  "developerName": "Notify_High_Value_Customer_System",
+  "displayName": "Notify High Value Customer System",
+  "description": "Example data action definition that uses a downstream data action target"
+}

package/skills/data360-orchestrate/assets/definitions/data-graph.template.json

@@ -0,0 +1,21 @@
+{
+  "developerName": "Customer_360_Graph",
+  "displayName": "Customer 360 Graph",
+  "description": "Example Data Graph rooted on a unified customer entity",
+  "sourceObject": {
+    "name": "UnifiedssotIndividualMain__dlm",
+    "type": "derived",
+    "fields": [
+      {
+        "name": "ssot__Id__c"
+      },
+      {
+        "name": "ssot__FirstName__c"
+      },
+      {
+        "name": "ssot__LastName__c"
+      }
+    ],
+    "relatedObjects": []
+  }
+}

package/skills/data360-orchestrate/assets/definitions/data-stream.template.json

@@ -0,0 +1,55 @@
+{
+  "name": "Customer_Stream",
+  "label": "Customer Stream",
+  "datasource": "SalesforceDotCom_Home",
+  "datastreamType": "CONNECTORSFRAMEWORK",
+  "connectorInfo": {
+    "connectorType": "SalesforceDotCom",
+    "connectorDetails": {
+      "name": "SalesforceDotCom_Home",
+      "sourceObject": "Custom_Object__c"
+    }
+  },
+  "dataLakeObjectInfo": {
+    "label": "Customer",
+    "name": "Customer__dll",
+    "category": "Profile",
+    "dataspaceInfo": [
+      {
+        "name": "Default"
+      }
+    ],
+    "dataLakeFieldInputRepresentations": [
+      {
+        "name": "Id",
+        "label": "Record ID",
+        "dataType": "Text",
+        "isPrimaryKey": true
+      },
+      {
+        "name": "External_Id_c",
+        "label": "External ID",
+        "dataType": "Text",
+        "isPrimaryKey": false
+      }
+    ]
+  },
+  "sourceFields": [
+    {
+      "name": "Id",
+      "dataType": "Text"
+    },
+    {
+      "name": "External_Id__c",
+      "dataType": "Text"
+    }
+  ],
+  "mappings": [],
+  "refreshConfig": {
+    "isAccelerationEnabled": true,
+    "refreshMode": "UPSERT",
+    "frequency": {
+      "frequencyType": "HOURLY"
+    }
+  }
+}

package/skills/data360-orchestrate/assets/definitions/dmo.template.json

@@ -0,0 +1,17 @@
+{
+  "developerName": "Customer_Profile__dlm",
+  "label": "Customer Profile",
+  "category": "Profile",
+  "fields": [
+    {
+      "name": "External_Id_c__c",
+      "label": "External ID",
+      "type": "Text"
+    },
+    {
+      "name": "Preferred_Tier_c__c",
+      "label": "Preferred Tier",
+      "type": "Text"
+    }
+  ]
+}

package/skills/data360-orchestrate/assets/definitions/identity-resolution.template.json

@@ -0,0 +1,30 @@
+{
+  "label": "Main",
+  "description": "Generic identity resolution ruleset using customer identifiers and contact points",
+  "configurationType": "individual",
+  "rulesetId": "main",
+  "doesRunAutomatically": false,
+  "matchRules": [
+    {
+      "label": "Exact Email",
+      "criteria": [
+        {
+          "entityName": "ssot__ContactPointEmail__dlm",
+          "fieldName": "ssot__EmailAddress__c",
+          "matchMethodType": "exactnormalized",
+          "caseSensitiveMatch": false,
+          "shouldMatchOnBlank": false
+        }
+      ]
+    }
+  ],
+  "reconciliationRules": [
+    {
+      "entityName": "ssot__Individual__dlm",
+      "ruleType": "lastupdated",
+      "shouldIgnoreEmptyValue": true,
+      "sources": [],
+      "fields": []
+    }
+  ]
+}

package/skills/data360-orchestrate/assets/definitions/mapping.template.json

@@ -0,0 +1,14 @@
+{
+  "sourceObjectName": "Customer__dll",
+  "targetObjectName": "Customer_Profile__dlm",
+  "fieldMappings": [
+    {
+      "sourceFieldName": "External_Id_c",
+      "targetFieldName": "External_Id_c__c"
+    },
+    {
+      "sourceFieldName": "Preferred_Tier_c",
+      "targetFieldName": "Preferred_Tier_c__c"
+    }
+  ]
+}

package/skills/data360-orchestrate/assets/definitions/relationship.template.json

@@ -0,0 +1,12 @@
+{
+  "relationships": [
+    {
+      "sourceObjectName": "Order_Header__dlm",
+      "targetObjectName": "ssot__Individual__dlm",
+      "cardinality": "ManyToOne",
+      "sourceFieldName": "Customer_ID_c__c",
+      "targetFieldName": "ssot__PartyId__c",
+      "relationshipOwner": "DataCloud"
+    }
+  ]
+}

package/skills/data360-orchestrate/assets/definitions/search-index.template.json

@@ -0,0 +1,9 @@
+{
+  "developerName": "Knowledge_Index",
+  "displayName": "Knowledge Index",
+  "description": "Example semantic search index for a structured or unstructured Data Cloud source",
+  "sourceObject": "KnowledgeArticleVersion__dlm",
+  "embeddingModel": "e5_large_v2",
+  "chunkingStrategy": "passage_extraction",
+  "similarityMetric": "COSINE"
+}

package/skills/data360-orchestrate/assets/definitions/segment.template.json

@@ -0,0 +1,16 @@
+{
+  "displayName": "High Value Customers",
+  "developerName": "High_Value_Customers",
+  "description": "Example segment built from a unified DMO",
+  "segmentType": "Dbt",
+  "includeDbt": {
+    "models": {
+      "models": [
+        {
+          "name": "UnifiedCustomers",
+          "sql": "SELECT ui.ssot__Id__c FROM UnifiedssotIndividualMain__dlm ui JOIN ssot__SalesOrder__dlm so ON ui.ssot__Id__c = so.ssot__IndividualId__c GROUP BY ui.ssot__Id__c HAVING SUM(so.ssot__TotalAmount__c) > 1000"
+        }
+      ]
+    }
+  }
+}

package/skills/data360-orchestrate/references/feature-readiness.md

@@ -0,0 +1,157 @@
+# Data Cloud Feature Readiness
+
+Use this guide when a Data Cloud command fails and you need to decide whether the issue is:
+- runtime / plugin setup
+- org authentication
+- product provisioning
+- feature gating
+- empty-but-enabled configuration
+- a bad table name or wrong probe
+
+The goal is to **detect first, classify second, and guide third** instead of blindly executing a command and surfacing a raw error.
+
+## Core principle
+
+Do **not** treat one failing command as proof that all of Data Cloud is unavailable.
+
+Different command families hit different backend surfaces. A failure in one area can coexist with successful read-only access in another.
+
+Examples:
+- `sf data360 doctor` checks the **search-index** endpoint only.
+- `sf data360 query describe` checks the **query** plane and requires a real DMO/DLO table name.
+- `sf data360 dmo list` checks a **catalog/listing** endpoint.
+- `sf data360 activation platforms` checks the **activation destination** surface.
+
+## Recommended first step
+
+Run the shared readiness classifier before mutation-heavy work:
+
+```bash
+node ../scripts/diagnose-org.mjs -o myorg --json
+```
+
+For retrieve/query work, only add a table probe when you already know the table name is real:
+
+```bash
+node ../scripts/diagnose-org.mjs -o myorg --phase retrieve --describe-table MyDMO__dlm --json
+```
+
+## Signal matrix
+
+| Signal | What it usually means | What to do next | What **not** to assume |
+|---|---|---|---|
+| `sf data360 man` fails | Runtime/plugin missing | Install or relink the community runtime | Do not debug org features yet |
+| `sf org display -o <org>` fails | Org auth missing | Re-authenticate the org | Do not blame Data Cloud |
+| `No results.` | Feature is reachable but currently empty | Continue with create/setup flow | Do not say the feature is disabled |
+| `This feature is not currently enabled for this user type or org: [CdpXxx]` | Specific module is gated for the current org/user | Guide the user to setup/provisioning/permission review for that module | Do not say the entire product is disabled |
+| `Couldn't find CDP tenant ID. Please enable CDP first.` | The **query** plane could not resolve a CDP tenant for that request | Re-check broader readiness with `data-space list`, `dmo list`, and `doctor`; then retry with a known table if appropriate | Do not treat this as universal proof that all Data Cloud endpoints are off |
+| `NOT_FOUND: DataModelEntity ... is not found` | The table name is not queryable in that org | Pick a real DMO/DLO from `dmo list`, `dlo list`, or `dmo get` | Do not say the whole query feature is unavailable |
+| `Request failed` | Generic endpoint failure or inconclusive response | Fall back to neighboring read-only probes | Do not stop after one generic failure |
+
+## High-signal feature gates
+
+### `CdpDataStreams`
+Typical impact:
+- `sf data360 data-stream list`
+- prepare / ingestion workflows
+
+Suggested guidance:
+- review Data Cloud Setup provisioning
+- review source connector readiness
+- confirm the user has the right Data Cloud permissions
+- for Salesforce CRM ingestion, confirm the connector/integration user has object + field read access in the source org
+
+### `CdpIdentityResolution`
+Typical impact:
+- `sf data360 identity-resolution list`
+- harmonize / unified profile workflows
+
+Suggested guidance:
+- review harmonization and identity-resolution entitlements
+- verify Data Cloud permission sets for the acting user
+- confirm upstream DLO/DMO work is already healthy before retrying IR
+
+### `CdpActivationTarget`
+Typical impact:
+- `sf data360 activation-target list`
+- downstream audience delivery setup
+
+Suggested guidance:
+- review Data Cloud activation permissions
+- review target/destination setup in Data Cloud Setup
+- confirm the org/edition actually exposes activation-target management for that user
+
+### `CdpActivationExternalPlatform`
+Typical impact:
+- `sf data360 activation platforms`
+- platform catalog for destinations such as ads or storage targets
+
+Suggested guidance:
+- review Activation Targets setup
+- review destination-specific authentication/configuration
+- check whether the org exposes additional toggles in **Data Cloud Setup → Feature Manager**
+
+### `CdpDataSpace`
+Typical impact:
+- `sf data360 data-space list`
+- core multi-space administration
+
+Suggested guidance:
+- review core Data Cloud provisioning and user access
+- confirm the user is intended to administer/view data spaces
+
+## What is usually **not** fully programmatic
+
+Do not promise a pure CLI flow for:
+- initial Data Cloud tenant provisioning
+- license assignment
+- every org-wide Data Cloud enablement step
+
+These commonly require Setup UI, provisioning, licensing, or account-level activation.
+
+## What is often programmatic **after** provisioning
+
+Once the org is properly provisioned, many workflows are programmatic through `sf data360`, including:
+- data-space listing / get / create / update
+- DMO catalog inspection and some DMO mutations
+- segment and calculated insight lifecycle operations
+- activation target and data action target operations
+- search-index lifecycle operations
+- hybrid search and related retrieve-plane workflows on newer runtime versions
+
+Exact coverage still depends on org entitlements and the user's permissions.
+
+## Known partial-automation gap
+
+Some external database connectors can be created via API while the corresponding data-stream creation flow still requires UI steps or org-specific browser automation.
+
+Practical guidance:
+- treat connection creation and stream creation as separate capability checks
+- do not assume a successful external connection create call means `data-stream create` will work for that connector
+- if the org relies on that path, guide the user toward manual UI creation or a locally validated Playwright/browser automation helper rather than promising a generic CLI-only workflow
+
+## User-facing guidance model
+
+When blocked, respond in this order:
+1. **Classify the failing surface** — runtime, auth, provisioning, feature gate, empty state, or bad table
+2. **Show the evidence** — the specific command + high-signal error text
+3. **Give the next setup step** — Data Cloud Setup, permissions, Feature Manager, source-object permissions, destination auth, etc.
+4. **Avoid false claims** — don't say "Data Cloud is off" unless multiple core probes support that conclusion
+
+## Setup guidance to point users toward
+
+Depending on the failing feature, guide users to review:
+- **Setup → Data Cloud Setup** for core provisioning / Get Started flow
+- **Standard Data Cloud permission sets** appropriate to the task (for example Architect/Admin vs activation-focused roles)
+- **Data Cloud Setup → Feature Manager** for org-specific toggles or beta features that are actually exposed there
+- **Source org permissions** for CRM ingestion users when streams/connectors depend on object/field access
+- **Activation target and destination authentication** when activation features are partially enabled but not usable yet
+
+## Skill author checklist
+
+Before telling the user a feature is unavailable:
+- [ ] Did I run a targeted probe for this phase?
+- [ ] Did I check at least one neighboring read-only probe?
+- [ ] Did I avoid treating `doctor` as a full product readiness check?
+- [ ] Did I avoid treating `query describe` as a universal tenant probe?
+- [ ] Did I tell the user exactly what setup area to review next?