Skip to main content
skill CX Codex

service-omni-command-center-analyze — Claude Code skill

service-omni-command-center-analyze analyzes whether to adopt Command Center V2 or classic Omni Supervisor and recommends the next action — read-only, safe to run on production. Returns explicit state plus the suggested follow-up skill.

Apache-2.0 132 installs ★ 1,183 updated 2026-10-23

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add forcedotcom/sf-skills --skill service-omni-command-center-analyze -a claude-code
Open on GitHub

What service-omni-command-center-analyze does

Entry point for the Command Center automation flow. The skill probes three independent gates: release capability, the CommandCenterForServiceV2 org preference, and per-supervisor CommandCenterForServiceUser permission. Returns one of six states — v2_ready, v2_permission_missing, v2_seed_incomplete, v2_available_not_enabled, legacy_selected, or ambiguous (blocking, when state cannot be proven via public APIs).

Input: org alias and optional supervisor username or ID. The skill runs only SOQL and Tooling queries; no changes are made. Requires sf CLI ≥ 2.139.6, Service Cloud license, and authenticated access to the target org. Output is JSON with the recommended next skill (e.g., service-omni-supervisor-config-deploy for the classic path) and detailed signals for each gate dimension.

What it helps with

  • Decide between Command Center V2 and classic Omni Supervisor before configuration
  • Verify org and supervisor readiness for V2 without risking config breakage
  • Diagnose incomplete V2 provisioning — FlexiPage and tab mismatch
  • Check supervisor permission for Command Center V2 access

Example prompts for the agent

  • Which supervisor experience should we choose — Command Center V2 or classic Omni?
  • Analyze whether org is ready for Command Center V2 for supervisor [email protected]
  • Diagnose Command Center availability and recommend next steps

How to install service-omni-command-center-analyze

1Skills CLI (Vercel)

npx skills add forcedotcom/sf-skills --skill service-omni-command-center-analyze -a claude-code

2Manually: put the files in place

~/.claude/skills/service-omni-command-center-analyze/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/service-omni-command-center-analyze/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about service-omni-command-center-analyze

How do I install service-omni-command-center-analyze in Claude Code?

Run npx skills add forcedotcom/sf-skills --skill service-omni-command-center-analyze -a claude-code, then open ~/.claude/skills/service-omni-command-center-analyze/SKILL.md.

What does service-omni-command-center-analyze do?

It probes your org's readiness for Command Center V2 against three independent dimensions, maps observable signals to one of six states, and recommends the next skill in the flow — all read-only, no changes.

What are the prerequisites?

Service Cloud license, authenticated sf CLI ≥ 2.139.6, and jq ≥ 1.6 and python3 ≥ 3.8 available. Target org requires API version 66.0 or later.

Source text

SKILL.md · Apache-2.0
---
name: service-omni-command-center-analyze
description: "Use to analyze whether an org should use Command Center for Service V2 or classic Omni Supervisor and recommend the next action without making changes. Triggers: detect Command Center V2 versus classic, check supervisor readiness, choose a supervisor experience, diagnose Command Center availability, assess Omni Supervisor setup. Do not use to enable V2, assign permissions, or deploy configuration."
allowed-tools: Bash Read Grep Glob
metadata:
  version: "1.0"
  domains: ["Service"]
  minApiVersion: "66.0"
  relatedSkills:
    - "service-omni-channel-setup-coordinate"
    - "service-omni-supervisor-config-deploy"
  accessCheck: "OrgPermissions.LightningService"
  cliTools:
    - tool: ["jq"]
      semver: ">=1.6"
    - tool: ["python3"]
      semver: ">=3.8"
    - tool: ["sf"]
      semver: ">=2.139.6"
---

# service-omni-command-center-analyze

Decide, **without changing anything**, which supervisor experience an org should use and what to do next. Command Center for Service V2 is gated on three independent dimensions — org **capability** (release gater), the **`CommandCenterForServiceV2` org preference** (whose ON-flip seeds the `CommandCenterForServiceV2_L` FlexiPage and registers the V2 tab), and the per-supervisor **`CommandCenterForServiceUser`** permission. A single boolean cannot express that, so this skill returns an explicit **state** plus the recommended follow-up skill (e.g. `service-omni-supervisor-config-deploy` for the classic path). It is the entry point of the Command Center flow — `service-omni-channel-setup-coordinate` runs it first — and is safe to run on any org, including production, because it only reads.

## Inputs

```bash
bash scripts/analyze.sh <org-alias> [supervisor_username_or_id]
```

- `org-alias` (required).
- `supervisor_username_or_id` (optional). A Username (`…@…`) or 15/18-char User Id (`005…`). When given, the per-user `CommandCenterForServiceUser` permission is evaluated; when omitted, the permission dimension is reported as not-checked and readiness is org-level only.

## Preconditions and safety

- Target org authenticated via `sf` CLI, Service Cloud license, `sf` CLI ≥ 2.139.6.
- **Read-only** — no `safe_to_write` guard is needed; the skill issues only SOQL/Tooling queries.

## Run

`analyze.sh` gathers observable signals and maps them to a state:

| Signal | Source | Meaning |
|---|---|---|
| V2 capability | `SELECT Id FROM PermissionSet WHERE PermissionsCommandCenterForServiceUser = true` probe | If the user-permission column does not exist on the org schema, V2 is not available. |
| Seeded FlexiPage | Tooling: `FlexiPage` where `DeveloperName='CommandCenterForServiceV2_L'` | Present ⇒ the org preference was enabled and the page was seeded. |
| V2 tab | `TabDefinition` (best-effort) | Cross-checks the seed; a seed/tab mismatch indicates a partial provision. |
| Supervisor permission | `PermissionSetAssignment` joined on `PermissionSet.PermissionsCommandCenterForServiceUser` | Whether the named supervisor can use V2. |
| Legacy config | Tooling: `OmniSupervisorConfig` count | Informational for the classic path. |

## Behavior

**States and recommended next action:**

| State | Meaning | Recommended skill |
|---|---|---|
| `v2_ready` | Capability + seed present (and supervisor has permission, if checked) | verify only (coordinator proceeds to V2 verification) |
| `v2_permission_missing` | V2 enabled but the named supervisor lacks `CommandCenterForServiceUser` | Manual — assign `CommandCenterForServiceUser` (headless-capable via PermissionSet; packaging pending) |
| `v2_seed_incomplete` | Capability present but the FlexiPage/tab provisioning is inconsistent | Manual — re-check in Setup → Omni-Channel → Supervisor Settings (no supported public write API) |
| `v2_available_not_enabled` | Org supports V2 but the preference is off | Manual — enable in Setup → Omni-Channel → Supervisor Settings (no supported Metadata/Tooling write API) |
| `legacy_selected` | V2 capability absent | `service-omni-supervisor-config-deploy` |
| `ambiguous` | A required signal could not be read through a supported API | none — **blocks**, do not guess |

`ambiguous` is the only state that exits non-zero: the review's rule is to block rather than infer when state cannot be proven read-only. All other states exit 0 with `status:"detected"`.

## Output contract

A single JSON object: `status` (`detected` | `blocked`), `state` (one of the six above), `recommended_action`, `recommended_skill`, `signals` (`v2_capability`, `seed_flexipage_present`, `v2_tab_present`, `supervisor{identifier,checked,has_command_center_permission}`, `legacy_omnisupervisorconfig_count`), `manual_actions`, `blocking_issue`.

## Limitations

- The `CommandCenterForServiceV2` org preference has no supported public read; its state is **inferred** from the seeded FlexiPage (the platform seeds on the ON-flip). This is called out in `signals` and is why a bare capability-without-seed reads as `v2_available_not_enabled`.
- The release gater cannot be read directly; capability is inferred from the presence of the user-permission column on the org schema.
- Tab detection is best-effort; when the tab query cannot run, `v2_tab_present` is `"unknown"` and state is derived from the remaining signals.
- Read-only: it never enables V2, seeds pages, assigns permissions, or deploys config.

## References

| File | When to read |
|---|---|
| `references/api-notes.md` | The three-dimensional V2 gate, why each signal is a proxy, and the exact queries used |

© forcedotcom · Apache-2.0 · forcedotcom/sf-skills

Similar skills

All skills for Backend and APIs →

From the same set232

The whole set →
agentforce-persona-generate agentforce-persona-generate — a skill for Claude Code and Codex that structures AI agent personas for Salesforce Agentforce. Encodes identity, voice, tone, and guardrails directly into .agent files. CX Codex +1 146installs education-cloud-student-recruitment-agent-configure education-cloud-student-recruitment-agent-configure is a Claude Code skill that configures the Student Recruitment Agent in Salesforce Education Cloud for admissions queries, tour bookings, and application filing. CX Codex +1 141installs service-omni-channel-setup-coordinate service-omni-channel-setup-coordinate automates Omni-Channel deployment on Salesforce: provisions agents, queues, channels, routing configs and permissions, detects what exists, creates only what is missing. CX Codex +1 140installs service-agentforce-human-escalation-configure service-agentforce-human-escalation-configure configures Agentforce handoff to a human through an Omni-Channel queue and checks the resulting setup. Use it for fallback routing and failure-threshold rules. CX Codex +1 135installs experience-lwc-widget-assess experience-lwc-widget-assess is a Claude Code skill that assesses whether a Lightning web component can be represented as an HXL declarative widget. CX Codex +1 129installs life-sciences-fieldsalesrep-coordinate life-sciences-fieldsalesrep-coordinate runs all five Life Sciences Cloud setup stages for a field sales rep back to back, checking each one before moving to the next. CX Codex +1 128installs experience-lwc-widget-migrate The experience-lwc-widget-migrate Claude Code skill turns a named Lightning web component (LWC) into a declarative HXL / Agentforce widget. It runs when a request calls for rebuilding or migrating an existing LWC as a widget. CX Codex +1 126installs education-cloud-academic-calendar-generate education-cloud-academic-calendar-generate builds an Education Cloud academic year with terms and sessions from dates in a prompt or document. Use it when setting up a new academic calendar. CX Codex +1 124installs

Project sponsors

Companies that keep this analytics open