[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CB8SNJMAR6XX82CESGA02A":3,"skill-same:01M7CB8SNJMAR6XX82CESGA02A":58},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":30,"commitSha":31,"skillDirectory":32,"forksCount":33,"repositoryHtmlUrl":34,"repositoryHomepageUrl":6,"ownerHtmlUrl":35,"ownerBlogUrl":6,"ownerDescription":36,"updatedAt":37,"install":38,"resources":51},"01M7CB8SNJMAR6XX82CESGA02A","sf-datacloud",null,"Salesforce Data Cloud product orchestrator for connect→prepare→harmonize→segment→act workflows. 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 sf-datacloud-* skill), the task is STDM\u002Fsession tracing\u002Fparquet telemetry (use sf-ai-agentforce-observability), standard CRM SOQL (use sf-soql), or Apex implementation (use sf-apex).","om-scogo\u002Fskillsh-scraper","om-scogo","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160466840?v=4","01M79AWB6DFVCQ7RK70CS34B96","Om Achrekar","01M79AWB6ZM9SKR8KDH1WSSM22",0,"MIT","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fjaganpro-sf-skills\u002Fsf-datacloud\u002FSkill.md",[],[],"2026-11-15 14:19:17",false,"---\nname: sf-datacloud\ndescription: >\n  Salesforce Data Cloud product orchestrator for connect→prepare→harmonize→segment→act workflows.\n  TRIGGER when: user needs a multi-step Data Cloud pipeline, asks to set up or troubleshoot\n  Data Cloud across phases, manages data spaces or data kits, or wants a cross-phase `sf data360`\n  workflow.\n  DO NOT TRIGGER when: work is isolated to a single phase (use the matching sf-datacloud-* skill),\n  the task is STDM\u002Fsession tracing\u002Fparquet telemetry (use sf-ai-agentforce-observability),\n  standard CRM SOQL (use sf-soql), or Apex implementation (use sf-apex).\nlicense: MIT\ncompatibility: \"Requires an external community sf data360 CLI plugin and a Data Cloud-enabled org\"\nmetadata:\n  version: \"1.0.0\"\n  author: \"Gnanasekaran Thoppae\"\n  runtime: \"External sf data360 community CLI plugin\"\n---\n\n# sf-datacloud: Salesforce Data Cloud Orchestrator\n\nUse 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.\n\nThis 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**.\n\n---\n\n## When This Skill Owns the Task\n\nUse `sf-datacloud` when the work involves:\n- multi-phase Data Cloud setup or remediation\n- data spaces (`sf data360 data-space *`)\n- data kits (`sf data360 data-kit *`)\n- health checks (`sf data360 doctor`)\n- CRM-to-unified-profile pipeline design\n- deciding how to move from ingestion → harmonization → segmentation → activation\n- cross-phase troubleshooting where the root cause is not yet clear\n\nDelegate to a phase-specific skill when the user is focused on one area:\n\n| Phase | Use this skill | Typical scope |\n|---|---|---|\n| Connect | [sf-datacloud-connect](..\u002Fsf-datacloud-connect\u002FSKILL.md) | connections, connectors, source discovery |\n| Prepare | [sf-datacloud-prepare](..\u002Fsf-datacloud-prepare\u002FSKILL.md) | data streams, DLOs, transforms, DocAI |\n| Harmonize | [sf-datacloud-harmonize](..\u002Fsf-datacloud-harmonize\u002FSKILL.md) | DMOs, mappings, identity resolution, data graphs |\n| Segment | [sf-datacloud-segment](..\u002Fsf-datacloud-segment\u002FSKILL.md) | segments, calculated insights |\n| Act | [sf-datacloud-act](..\u002Fsf-datacloud-act\u002FSKILL.md) | activations, activation targets, data actions |\n| Retrieve | [sf-datacloud-retrieve](..\u002Fsf-datacloud-retrieve\u002FSKILL.md) | SQL, search indexes, vector search, async query |\n\nDelegate outside the family when the user is:\n- extracting Session Tracing \u002F STDM telemetry → [sf-ai-agentforce-observability](..\u002Fsf-ai-agentforce-observability\u002FSKILL.md)\n- writing CRM SOQL only → [sf-soql](..\u002Fsf-soql\u002FSKILL.md)\n- loading CRM source data → [sf-data](..\u002Fsf-data\u002FSKILL.md)\n- creating missing CRM schema → [sf-metadata](..\u002Fsf-metadata\u002FSKILL.md)\n- implementing downstream Apex or Flow logic → [sf-apex](..\u002Fsf-apex\u002FSKILL.md), [sf-flow](..\u002Fsf-flow\u002FSKILL.md)\n\n---\n\n## Required Context to Gather First\n\nAsk for or infer:\n- target org alias\n- whether the plugin is already installed and linked\n- whether the user wants design guidance, read-only inspection, or live mutation\n- data sources involved: CRM objects, external databases, file ingestion, knowledge, etc.\n- desired outcome: unified profiles, segments, activations, vector search, analytics, or troubleshooting\n- whether the user is working in the default data space or a custom one\n- whether the org has already been classified with `scripts\u002Fdiagnose-org.mjs`\n- which command family is failing today, if any\n\nIf plugin availability or org readiness is uncertain, start with:\n- [references\u002Fplugin-setup.md](references\u002Fplugin-setup.md)\n- [references\u002Ffeature-readiness.md](references\u002Ffeature-readiness.md)\n- `scripts\u002Fverify-plugin.sh`\n- `scripts\u002Fdiagnose-org.mjs`\n- `scripts\u002Fbootstrap-plugin.sh`\n\n---\n\n## Core Operating Rules\n\n- Use the external `sf data360` plugin runtime; do **not** reimplement or vendor the command layer.\n- Prefer the smallest phase-specific skill once the task is localized.\n- Run readiness classification before mutation-heavy work. Prefer `scripts\u002Fdiagnose-org.mjs` over guessing from one failing command.\n- For `sf data360` commands, suppress linked-plugin warning noise with `2>\u002Fdev\u002Fnull` unless the stderr output is needed for debugging.\n- Distinguish **Data Cloud SQL** from CRM SOQL.\n- Do **not** treat `sf data360 doctor` as a full-product readiness check; the current upstream command only checks the search-index surface.\n- Do **not** treat `query describe` as a universal tenant probe; only use it with a known DMO\u002FDLO table after broader readiness is confirmed.\n- Preserve Data Cloud-specific API-version workarounds when they matter.\n- Prefer generic, reusable JSON definition files over org-specific workshop payloads.\n\n---\n\n## Recommended Workflow\n\n### 1. Verify the runtime and auth\nConfirm:\n- `sf` is installed\n- the community Data Cloud plugin is linked\n- the target org is authenticated\n\nRecommended checks:\n```bash\nsf data360 man\nsf org display -o \u003Calias>\nbash ~\u002F.claude\u002Fskills\u002Fsf-datacloud\u002Fscripts\u002Fverify-plugin.sh \u003Calias>\n```\n\nTreat `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.\n\n### 2. Classify readiness before changing anything\nRun the shared classifier first:\n```bash\nnode ~\u002F.claude\u002Fskills\u002Fsf-datacloud\u002Fscripts\u002Fdiagnose-org.mjs -o \u003Corg> --json\n```\n\nOnly use a query-plane probe after you know the table name is real:\n```bash\nnode ~\u002F.claude\u002Fskills\u002Fsf-datacloud\u002Fscripts\u002Fdiagnose-org.mjs -o \u003Corg> --phase retrieve --describe-table MyDMO__dlm --json\n```\n\nUse the classifier to distinguish:\n- empty-but-enabled modules\n- feature-gated modules\n- query-plane issues\n- runtime\u002Fauth failures\n\n### 3. Discover existing state with read-only commands\nUse targeted inspection after classification:\n```bash\nsf data360 doctor -o \u003Corg> 2>\u002Fdev\u002Fnull\nsf data360 data-space list -o \u003Corg> 2>\u002Fdev\u002Fnull\nsf data360 data-stream list -o \u003Corg> 2>\u002Fdev\u002Fnull\nsf data360 dmo list -o \u003Corg> 2>\u002Fdev\u002Fnull\nsf data360 identity-resolution list -o \u003Corg> 2>\u002Fdev\u002Fnull\nsf data360 segment list -o \u003Corg> 2>\u002Fdev\u002Fnull\nsf data360 activation platforms -o \u003Corg> 2>\u002Fdev\u002Fnull\n```\n\n### 4. Localize the phase\nRoute the task:\n- source\u002Fconnector issue → Connect\n- ingestion\u002FDLO\u002Fstream issue → Prepare\n- mapping\u002FIR\u002Funified profile issue → Harmonize\n- audience or insight issue → Segment\n- downstream push issue → Act\n- SQL\u002Fsearch\u002Findex issue → Retrieve\n\n### 5. Choose deterministic artifacts when possible\nPrefer JSON definition files and repeatable scripts over one-off manual steps. Generic templates live in:\n- `assets\u002Fdefinitions\u002Fdata-stream.template.json`\n- `assets\u002Fdefinitions\u002Fdmo.template.json`\n- `assets\u002Fdefinitions\u002Fmapping.template.json`\n- `assets\u002Fdefinitions\u002Frelationship.template.json`\n- `assets\u002Fdefinitions\u002Fidentity-resolution.template.json`\n- `assets\u002Fdefinitions\u002Fdata-graph.template.json`\n- `assets\u002Fdefinitions\u002Fcalculated-insight.template.json`\n- `assets\u002Fdefinitions\u002Fsegment.template.json`\n- `assets\u002Fdefinitions\u002Factivation-target.template.json`\n- `assets\u002Fdefinitions\u002Factivation.template.json`\n- `assets\u002Fdefinitions\u002Fdata-action-target.template.json`\n- `assets\u002Fdefinitions\u002Fdata-action.template.json`\n- `assets\u002Fdefinitions\u002Fsearch-index.template.json`\n\n### 6. Verify after each phase\nTypical verification:\n- stream\u002FDLO exists\n- DMO\u002Fmapping exists\n- identity resolution run completed\n- unified records or segment counts look correct\n- activation\u002Fsearch index status is healthy\n\n---\n\n## High-Signal Gotchas\n\n- `connection list` requires `--connector-type`.\n- `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.\n- Segment creation may need `--api-version 64.0`.\n- `segment members` returns opaque IDs; use SQL joins for human-readable details.\n- `sf data360 doctor` can fail on partially provisioned orgs even when some read-only commands still work; fall back to targeted smoke checks.\n- `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.\n- Many long-running jobs are asynchronous in practice even when the command returns quickly.\n- Some Data Cloud operations still require UI setup outside the CLI runtime.\n\n---\n\n## Output Format\n\nWhen finishing, report in this order:\n1. **Task classification**\n2. **Runtime status**\n3. **Readiness classification**\n4. **Phase(s) involved**\n5. **Commands or artifacts used**\n6. **Verification result**\n7. **Next recommended step**\n\nSuggested shape:\n\n```text\nData Cloud task: \u003Csetup \u002F inspect \u002F troubleshoot \u002F migrate>\nRuntime: \u003Cplugin ready \u002F missing \u002F partially verified>\nReadiness: \u003Cready \u002F ready_empty \u002F partial \u002F feature_gated \u002F blocked>\nPhases: \u003Cconnect \u002F prepare \u002F harmonize \u002F segment \u002F act \u002F retrieve>\nArtifacts: \u003Cjson files, commands, scripts>\nVerification: \u003Cpassed \u002F partial \u002F blocked>\nNext step: \u003Cnext phase, setup guidance, or cross-skill handoff>\n```\n\n---\n\n## Cross-Skill Integration\n\n| Need | Delegate to | Reason |\n|---|---|---|\n| load or clean CRM source data | [sf-data](..\u002Fsf-data\u002FSKILL.md) | seed or fix source records before ingestion |\n| create missing CRM schema | [sf-metadata](..\u002Fsf-metadata\u002FSKILL.md) | Data Cloud expects existing objects\u002Ffields |\n| deploy permissions or bundles | [sf-deploy](..\u002Fsf-deploy\u002FSKILL.md) | environment preparation |\n| write Apex against Data Cloud outputs | [sf-apex](..\u002Fsf-apex\u002FSKILL.md) | code implementation |\n| Flow automation after segmentation\u002Factivation | [sf-flow](..\u002Fsf-flow\u002FSKILL.md) | declarative orchestration |\n| session tracing \u002F STDM \u002F parquet analysis | [sf-ai-agentforce-observability](..\u002Fsf-ai-agentforce-observability\u002FSKILL.md) | different Data Cloud use case |\n\n---\n\n## Reference Map\n\n### Start here\n- [README.md](README.md)\n- [references\u002Fplugin-setup.md](references\u002Fplugin-setup.md)\n- [references\u002Ffeature-readiness.md](references\u002Ffeature-readiness.md)\n- [UPSTREAM.md](UPSTREAM.md)\n\n### Phase skills\n- [sf-datacloud-connect](..\u002Fsf-datacloud-connect\u002FSKILL.md)\n- [sf-datacloud-prepare](..\u002Fsf-datacloud-prepare\u002FSKILL.md)\n- [sf-datacloud-harmonize](..\u002Fsf-datacloud-harmonize\u002FSKILL.md)\n- [sf-datacloud-segment](..\u002Fsf-datacloud-segment\u002FSKILL.md)\n- [sf-datacloud-act](..\u002Fsf-datacloud-act\u002FSKILL.md)\n- [sf-datacloud-retrieve](..\u002Fsf-datacloud-retrieve\u002FSKILL.md)\n\n### Deterministic helpers\n- [scripts\u002Fbootstrap-plugin.sh](scripts\u002Fbootstrap-plugin.sh)\n- [scripts\u002Fverify-plugin.sh](scripts\u002Fverify-plugin.sh)\n- [scripts\u002Fdiagnose-org.mjs](scripts\u002Fdiagnose-org.mjs)\n- [assets\u002Fdefinitions\u002F](assets\u002Fdefinitions\u002F)\n","# sf-datacloud: Salesforce Data Cloud Orchestrator\n\nUse 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.\n\nThis 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**.\n\n---\n\n## When This Skill Owns the Task\n\nUse `sf-datacloud` when the work involves:\n- multi-phase Data Cloud setup or remediation\n- data spaces (`sf data360 data-space *`)\n- data kits (`sf data360 data-kit *`)\n- health checks (`sf data360 doctor`)\n- CRM-to-unified-profile pipeline design\n- deciding how to move from ingestion → harmonization → segmentation → activation\n- cross-phase troubleshooting where the root cause is not yet clear\n\nDelegate to a phase-specific skill when the user is focused on one area:\n\n| Phase | Use this skill | Typical scope |\n|---|---|---|\n| Connect | [sf-datacloud-connect](..\u002Fsf-datacloud-connect\u002FSKILL.md) | connections, connectors, source discovery |\n| Prepare | [sf-datacloud-prepare](..\u002Fsf-datacloud-prepare\u002FSKILL.md) | data streams, DLOs, transforms, DocAI |\n| Harmonize | [sf-datacloud-harmonize](..\u002Fsf-datacloud-harmonize\u002FSKILL.md) | DMOs, mappings, identity resolution, data graphs |\n| Segment | [sf-datacloud-segment](..\u002Fsf-datacloud-segment\u002FSKILL.md) | segments, calculated insights |\n| Act | [sf-datacloud-act](..\u002Fsf-datacloud-act\u002FSKILL.md) | activations, activation targets, data actions |\n| Retrieve | [sf-datacloud-retrieve](..\u002Fsf-datacloud-retrieve\u002FSKILL.md) | SQL, search indexes, vector search, async query |\n\nDelegate outside the family when the user is:\n- extracting Session Tracing \u002F STDM telemetry → [sf-ai-agentforce-observability](..\u002Fsf-ai-agentforce-observability\u002FSKILL.md)\n- writing CRM SOQL only → [sf-soql](..\u002Fsf-soql\u002FSKILL.md)\n- loading CRM source data → [sf-data](..\u002Fsf-data\u002FSKILL.md)\n- creating missing CRM schema → [sf-metadata](..\u002Fsf-metadata\u002FSKILL.md)\n- implementing downstream Apex or Flow logic → [sf-apex](..\u002Fsf-apex\u002FSKILL.md), [sf-flow](..\u002Fsf-flow\u002FSKILL.md)\n\n---\n\n## Required Context to Gather First\n\nAsk for or infer:\n- target org alias\n- whether the plugin is already installed and linked\n- whether the user wants design guidance, read-only inspection, or live mutation\n- data sources involved: CRM objects, external databases, file ingestion, knowledge, etc.\n- desired outcome: unified profiles, segments, activations, vector search, analytics, or troubleshooting\n- whether the user is working in the default data space or a custom one\n- whether the org has already been classified with `scripts\u002Fdiagnose-org.mjs`\n- which command family is failing today, if any\n\nIf plugin availability or org readiness is uncertain, start with:\n- [references\u002Fplugin-setup.md](references\u002Fplugin-setup.md)\n- [references\u002Ffeature-readiness.md](references\u002Ffeature-readiness.md)\n- `scripts\u002Fverify-plugin.sh`\n- `scripts\u002Fdiagnose-org.mjs`\n- `scripts\u002Fbootstrap-plugin.sh`\n\n---\n\n## Core Operating Rules\n\n- Use the external `sf data360` plugin runtime; do **not** reimplement or vendor the command layer.\n- Prefer the smallest phase-specific skill once the task is localized.\n- Run readiness classification before mutation-heavy work. Prefer `scripts\u002Fdiagnose-org.mjs` over guessing from one failing command.\n- For `sf data360` commands, suppress linked-plugin warning noise with `2>\u002Fdev\u002Fnull` unless the stderr output is needed for debugging.\n- Distinguish **Data Cloud SQL** from CRM SOQL.\n- Do **not** treat `sf data360 doctor` as a full-product readiness check; the current upstream command only checks the search-index surface.\n- Do **not** treat `query describe` as a universal tenant probe; only use it with a known DMO\u002FDLO table after broader readiness is confirmed.\n- Preserve Data Cloud-specific API-version workarounds when they matter.\n- Prefer generic, reusable JSON definition files over org-specific workshop payloads.\n\n---\n\n## Recommended Workflow\n\n### 1. Verify the runtime and auth\nConfirm:\n- `sf` is installed\n- the community Data Cloud plugin is linked\n- the target org is authenticated\n\nRecommended checks:\n```bash\nsf data360 man\nsf org display -o \u003Calias>\nbash ~\u002F.claude\u002Fskills\u002Fsf-datacloud\u002Fscripts\u002Fverify-plugin.sh \u003Calias>\n```\n\nTreat `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.\n\n### 2. Classify readiness before changing anything\nRun the shared classifier first:\n```bash\nnode ~\u002F.claude\u002Fskills\u002Fsf-datacloud\u002Fscripts\u002Fdiagnose-org.mjs -o \u003Corg> --json\n```\n\nOnly use a query-plane probe after you know the table name is real:\n```bash\nnode ~\u002F.claude\u002Fskills\u002Fsf-datacloud\u002Fscripts\u002Fdiagnose-org.mjs -o \u003Corg> --phase retrieve --describe-table MyDMO__dlm --json\n```\n\nUse the classifier to distinguish:\n- empty-but-enabled modules\n- feature-gated modules\n- query-plane issues\n- runtime\u002Fauth failures\n\n### 3. Discover existing state with read-only commands\nUse targeted inspection after classification:\n```bash\nsf data360 doctor -o \u003Corg> 2>\u002Fdev\u002Fnull\nsf data360 data-space list -o \u003Corg> 2>\u002Fdev\u002Fnull\nsf data360 data-stream list -o \u003Corg> 2>\u002Fdev\u002Fnull\nsf data360 dmo list -o \u003Corg> 2>\u002Fdev\u002Fnull\nsf data360 identity-resolution list -o \u003Corg> 2>\u002Fdev\u002Fnull\nsf data360 segment list -o \u003Corg> 2>\u002Fdev\u002Fnull\nsf data360 activation platforms -o \u003Corg> 2>\u002Fdev\u002Fnull\n```\n\n### 4. Localize the phase\nRoute the task:\n- source\u002Fconnector issue → Connect\n- ingestion\u002FDLO\u002Fstream issue → Prepare\n- mapping\u002FIR\u002Funified profile issue → Harmonize\n- audience or insight issue → Segment\n- downstream push issue → Act\n- SQL\u002Fsearch\u002Findex issue → Retrieve\n\n### 5. Choose deterministic artifacts when possible\nPrefer JSON definition files and repeatable scripts over one-off manual steps. Generic templates live in:\n- `assets\u002Fdefinitions\u002Fdata-stream.template.json`\n- `assets\u002Fdefinitions\u002Fdmo.template.json`\n- `assets\u002Fdefinitions\u002Fmapping.template.json`\n- `assets\u002Fdefinitions\u002Frelationship.template.json`\n- `assets\u002Fdefinitions\u002Fidentity-resolution.template.json`\n- `assets\u002Fdefinitions\u002Fdata-graph.template.json`\n- `assets\u002Fdefinitions\u002Fcalculated-insight.template.json`\n- `assets\u002Fdefinitions\u002Fsegment.template.json`\n- `assets\u002Fdefinitions\u002Factivation-target.template.json`\n- `assets\u002Fdefinitions\u002Factivation.template.json`\n- `assets\u002Fdefinitions\u002Fdata-action-target.template.json`\n- `assets\u002Fdefinitions\u002Fdata-action.template.json`\n- `assets\u002Fdefinitions\u002Fsearch-index.template.json`\n\n### 6. Verify after each phase\nTypical verification:\n- stream\u002FDLO exists\n- DMO\u002Fmapping exists\n- identity resolution run completed\n- unified records or segment counts look correct\n- activation\u002Fsearch index status is healthy\n\n---\n\n## High-Signal Gotchas\n\n- `connection list` requires `--connector-type`.\n- `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.\n- Segment creation may need `--api-version 64.0`.\n- `segment members` returns opaque IDs; use SQL joins for human-readable details.\n- `sf data360 doctor` can fail on partially provisioned orgs even when some read-only commands still work; fall back to targeted smoke checks.\n- `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.\n- Many long-running jobs are asynchronous in practice even when the command returns quickly.\n- Some Data Cloud operations still require UI setup outside the CLI runtime.\n\n---\n\n## Output Format\n\nWhen finishing, report in this order:\n1. **Task classification**\n2. **Runtime status**\n3. **Readiness classification**\n4. **Phase(s) involved**\n5. **Commands or artifacts used**\n6. **Verification result**\n7. **Next recommended step**\n\nSuggested shape:\n\n```text\nData Cloud task: \u003Csetup \u002F inspect \u002F troubleshoot \u002F migrate>\nRuntime: \u003Cplugin ready \u002F missing \u002F partially verified>\nReadiness: \u003Cready \u002F ready_empty \u002F partial \u002F feature_gated \u002F blocked>\nPhases: \u003Cconnect \u002F prepare \u002F harmonize \u002F segment \u002F act \u002F retrieve>\nArtifacts: \u003Cjson files, commands, scripts>\nVerification: \u003Cpassed \u002F partial \u002F blocked>\nNext step: \u003Cnext phase, setup guidance, or cross-skill handoff>\n```\n\n---\n\n## Cross-Skill Integration\n\n| Need | Delegate to | Reason |\n|---|---|---|\n| load or clean CRM source data | [sf-data](..\u002Fsf-data\u002FSKILL.md) | seed or fix source records before ingestion |\n| create missing CRM schema | [sf-metadata](..\u002Fsf-metadata\u002FSKILL.md) | Data Cloud expects existing objects\u002Ffields |\n| deploy permissions or bundles | [sf-deploy](..\u002Fsf-deploy\u002FSKILL.md) | environment preparation |\n| write Apex against Data Cloud outputs | [sf-apex](..\u002Fsf-apex\u002FSKILL.md) | code implementation |\n| Flow automation after segmentation\u002Factivation | [sf-flow](..\u002Fsf-flow\u002FSKILL.md) | declarative orchestration |\n| session tracing \u002F STDM \u002F parquet analysis | [sf-ai-agentforce-observability](..\u002Fsf-ai-agentforce-observability\u002FSKILL.md) | different Data Cloud use case |\n\n---\n\n## Reference Map\n\n### Start here\n- [README.md](README.md)\n- [references\u002Fplugin-setup.md](references\u002Fplugin-setup.md)\n- [references\u002Ffeature-readiness.md](references\u002Ffeature-readiness.md)\n- [UPSTREAM.md](UPSTREAM.md)\n\n### Phase skills\n- [sf-datacloud-connect](..\u002Fsf-datacloud-connect\u002FSKILL.md)\n- [sf-datacloud-prepare](..\u002Fsf-datacloud-prepare\u002FSKILL.md)\n- [sf-datacloud-harmonize](..\u002Fsf-datacloud-harmonize\u002FSKILL.md)\n- [sf-datacloud-segment](..\u002Fsf-datacloud-segment\u002FSKILL.md)\n- [sf-datacloud-act](..\u002Fsf-datacloud-act\u002FSKILL.md)\n- [sf-datacloud-retrieve](..\u002Fsf-datacloud-retrieve\u002FSKILL.md)\n\n### Deterministic helpers\n- [scripts\u002Fbootstrap-plugin.sh](scripts\u002Fbootstrap-plugin.sh)\n- [scripts\u002Fverify-plugin.sh](scripts\u002Fverify-plugin.sh)\n- [scripts\u002Fdiagnose-org.mjs](scripts\u002Fdiagnose-org.mjs)\n- [assets\u002Fdefinitions\u002F](assets\u002Fdefinitions\u002F)\n",{"name":5,"license":15,"metadata":24,"description":28,"compatibility":29},{"author":25,"runtime":26,"version":27},"Gnanasekaran Thoppae","External sf data360 community CLI plugin","1.0.0","Salesforce Data Cloud product orchestrator for connect→prepare→harmonize→segment→act workflows. 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 sf-datacloud-* skill), the task is STDM\u002Fsession tracing\u002Fparquet telemetry (use sf-ai-agentforce-observability), standard CRM SOQL (use sf-soql), or Apex implementation (use sf-apex).\n","Requires an external community sf data360 CLI plugin and a Data Cloud-enabled org","main","8859218955d9504cd18b59e7892100718039d3b4","data\u002Fskills\u002Fjaganpro-sf-skills\u002Fsf-datacloud",1,"https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper","https:\u002F\u002Fgithub.com\u002Fom-scogo","SDE-1 @ Scogo ","2026-07-18 12:22:46",{"source":8,"skillName":5,"commands":39,"prompt":49,"zipAvailable":50},[40,43,46],{"tool":41,"command":42},"npx","npx skills add om-scogo\u002Fskillsh-scraper --skill sf-datacloud",{"tool":44,"command":45},"bunx","bunx skills add om-scogo\u002Fskillsh-scraper --skill sf-datacloud",{"tool":47,"command":48},"pnpm","pnpm dlx skills add om-scogo\u002Fskillsh-scraper --skill sf-datacloud","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fjaganpro-sf-skills\u002Fsf-datacloud\u002FSkill.md",true,[52],{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},"metadata.json","REFERENCE","参考文档",422,"https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fjaganpro-sf-skills\u002Fsf-datacloud\u002Fmetadata.json",[59,66,71,78,83,90],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M7D6MC9FAAEV4CMNYX8W7JTG","arxiv-search","Search arXiv physics, math, and computer science preprints using natural language queries. Powered by Valyu semantic search.","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fyorkeccak-scientific-skills\u002Farxiv-search\u002Fskills\u002Farxiv-search\u002FSKILL.md",[],[],{"skillNo":67,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":19},"01M7D6M85CKKN87TA98VCQV4H7","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fyorkeccak-scientific-skills\u002Farxiv-search\u002FSkill.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M7D4ZTCS4DR3CE4JY06X84T2","working-with-legacy-code","Safely change and test untested codebases using Feathers' \"Working Effectively with Legacy Code\". Use when the user mentions \"legacy code\", \"no tests\", \"untested codebase\", \"how do I test this\", \"seams\", \"characterization tests\", \"golden master\", \"sprout method\", \"afraid to change this code\", \"monster method\", \"dependency breaking\", or \"inherited a messy codebase\". Also trigger when changing code without tests safely, getting a class under test when constructors, statics, or singletons block it, adding features to tangled modules, or planning incremental test coverage for an old codebase. Covers the legacy-code change algorithm, seams, characterization tests, sprout\u002Fwrap, and dependency-breaking techniques. For refactoring code that already has tests, see refactoring-patterns. For day-to-day code quality, see clean-code.","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fwondelai-skills\u002Fworking-with-legacy-code\u002Fworking-with-legacy-code\u002FSKILL.md",[],[],{"skillNo":79,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7D4ZHZKJD2RSNGAF63V14P4","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fwondelai-skills\u002Fworking-with-legacy-code\u002FSkill.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M7D4ZB4CJBFW5JE67CPH2QRV","web-typography","Select, pair, and implement typefaces for web projects. Use when the user mentions \"font pairing\", \"which typeface\", \"line height\", \"responsive typography\", \"web font loading\", \"type hierarchy\", \"variable fonts\", \"FOUT\u002FFOIT\", \"typographic scale\", or \"the text is hard to read\". Also trigger when choosing between system fonts and web fonts, optimizing font-loading performance, or designing readable long-form content. Covers readability evaluation, CSS implementation, and performance optimization. For overall UI design systems, see refactoring-ui. For dramatic typographic experiences, see top-design.","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fwondelai-skills\u002Fweb-typography\u002Fweb-typography\u002FSKILL.md",[],[],{"skillNo":91,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M7D4Z4MVYVY3NMJ18BNV6WNA","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fwondelai-skills\u002Fweb-typography\u002FSkill.md",[],[]]