Service Helpagent Coordinate

service-helpagent-coordinate: Service Cloud Help Agent, guided setup

Use this skill to stand up a Service Cloud Help Agent (an Agentforce Service Agent) on a Salesforce org from Claude Code, following the same guided flow as the Help Agent Quick Setup wizard. This is a coordinate skill: it orchestrates existing skills against a canonical spec — it does not author a new agent primitive.

Why this skill exists

Salesforce's official Help Agent template-creation API is not yet shipped. Without it, Claude has no built-in concept of "Help Agent" and would otherwise generate a generic agent. assets/help-agent-spec.md substitutes for the missing API: its agent script is the canonical template the eventual Quick Start UI will produce. Treat the spec as source of truth for the agent's lineage (topics, actions, instructions).

Scope

In scope:

• Guided, four-checkpoint Help Agent setup (identity → grounding → channel → go-live)
• Knowledge grounding via Agentforce Data Library (ADL)
• Web Chat / Help Portal channel setup and Experience Cloud site embed
• Readiness checks (licenses, Einstein Agent User, Data Cloud permission sets)

Out of scope — delegate elsewhere:

• OAuth / External Client App setup → integration-connectivity-connected-app-configure
• Raw agent authoring with no Help Agent lineage → agentforce-adlc:agentforce-generate
• Metadata deploy/retrieve → platform-metadata-deploy

Prerequisites

• Claude Code + Salesforce CLI installed and an authenticated org (see repo README.md)
• MCP servers registered: salesforce-api-context, metadata-experts, sobject-reads
• Salesforce Skills installed into .agents/skills/ (or .claude/skills/)
• A Salesforce org with the required features enabled (or enable-able via metadata): Agentforce, Einstein Generative AI, Knowledge, Experience Cloud, and Data Cloud. Any org shape that meets this bar works — production, sandbox, scratch, or Developer Edition. The readiness check in assets/help-agent-spec.md §4.0 detects each feature and enables what can be enabled; it stops with a clear message if a required capability is missing and cannot be turned on.

Skills this coordinates

The spec feeds these existing skills — do not author a new Help Agent skill:

Agentforce authoring safety preflight (MANDATORY, hard gate)

This plugin-local preflight overrides any conflicting ordering or direct Agentforce CLI examples in assets/help-agent-spec.md. Run it once for the selected org and live plugin session before the existing readiness check, creating an Einstein Agent User, enabling features, generating metadata, creating or inspecting an Agentforce Data Library, loading references/agent-script.md, or starting any authoring, provisioning, deployment, publication, or activation operation. Resolving the target-org alias is the only work allowed before this gate.

The load-bearing order is:

agentforce-adlc:agentforce-generate capability check
                    ↓
non-destructive org authoring-capability probe
                    ↓
agentforce-adlc:agentforce-generate authoring delegation
                    ↓
later readiness, generation, ADL, and lifecycle operations

Step 1 — Resolve the owning capability

agentforce-adlc:agentforce-generate is the plugin-qualified identity of the agentforce-generate skill owned by the separate agentforce-adlc plugin. Salesforce CLI availability does not prove that the plugin or skill is available.

1. Make a no-op Skill-tool dispatch to agentforce-adlc:agentforce-generate whose request says: Capability availability probe only; return without reading project files, running CLI commands, or changing local or org state. This qualified dispatch is the authoritative live-session capability check; never probe or delegate to an unqualified agentforce-generate, because a different workspace or flat skill could satisfy that name. The dispatch checks registration only and is not permission to begin the owning workflow. An Unknown skill: agentforce-adlc:agentforce-generate result means the owning capability is not registered in this session. Any normal skill response, including a usage/argument response, means it is invocable.
2. Only when the qualified dispatch is unknown, run the plugin-local, read-only installed-plugin registry check:

   python3 "${CLAUDE_PLUGIN_ROOT}/scripts/helpagent_dependency_preflight.py"

The helper invokes the documented claude plugin list --json registry operation internally, validates exact plugin IDs whose component before @ is agentforce-adlc, and emits only a sanitized classification; never print or relay the raw registry JSON because unrelated plugin configuration may contain sensitive values. This registry result is guidance only: a cache directory, an installed entry, or installed_enabled does not replace the qualified Skill dispatch as proof of live-session availability. Do not infer installation from a relative cache path; installed plugin paths are marketplace- and version-dependent.

1. Stop at Help Agent — Agentforce dependency preflight, then honor the helper's registryState exactly:

• installed_enabled: explain that agentforce-adlc is installed and enabled but its skill is not registered in this session. Tell the user to run /reload-plugins (or restart the host if reload still does not expose it), then resume this Help Agent task.
• installed_disabled: explain that agentforce-adlc is installed but disabled. Recommend enabling the exact sanitized pluginId returned by the helper (normally claude plugin enable agentforce-adlc@claude-plugins-official), wait for explicit approval before changing plugin state, then tell the user to run /reload-plugins and resume this Help Agent task.
• missing: explain that Agentforce authoring requires the missing agentforce-adlc plugin. Recommend /salesforce-development:plugin-install agentforce-adlc, wait for explicit approval before invoking that guarded install flow, and follow its source/nonce confirmation exactly. After installation, tell the user to run /reload-plugins before resuming. Do not treat a successful install as same-session skill availability.
• inconclusive: report that installation state cannot be resolved. Give install/enable + reload guidance as alternatives, but do not mutate plugin state or guess that the capability exists.

At this stop, retain and report the selected org, the checkpoint where the user entered, confirmed identity/grounding/channel choices, the local project path, and every durable identifier already produced by an earlier run (Einstein Agent User, Agentforce Data Library/library ID, rag_feature_config_id, agent/bundle DeveloperName, channel, deployment, and site IDs). Do not delete, recreate, roll back, or discard valid prerequisite work. The preflight itself creates no durable state, so resumption starts at the named dependency checkpoint with those facts.