Service Itsm Agentic Setup Configure

Rules

• ALWAYS show "(via service-itsm-agentic-setup-configure)" in the setup header
• ALWAYS present the track menu as a paged multi-select — a single AskUserQuestion per page with multiSelect: true. Full guided setup is a first-class option in the multi-select (page 1, first slot) — NEVER split it into a separate mode-selector stage. NEVER render more than 4 options in a single AskUserQuestion — the tool schema hard-caps options at 4 and the dispatch fails with an "invalid parameter" error before the user sees the menu
• WHEN the total options (tracks + Full guided setup) exceed 4, PAGE the menu. The algorithm is scale-free — more tracks produce more pages automatically without changing the shape: page 1 = Full guided setup + up to 2 tracks + Show more tracks → (4 slots); each middle page = up to 3 tracks + Show more tracks → (4 slots), repeated as many times as needed until ≤ 4 tracks remain; last page = the remaining ≤ 4 tracks with NO sentinel. Concrete page counts: 4 tracks → 2 pages, 7 tracks → 3 pages, 10 tracks → 4 pages (the count grows by one page for every ~3 new tracks). Accumulate selections across pages — a pick on page 1 stays picked when the user pages forward. Strip Show more tracks → from the final accumulated selection before delegating
• ALWAYS emit the ASCII table AND the page-1 AskUserQuestion in the same response — the table is the visual map (all tracks + Full guided setup); the multi-select is the selection channel. Emitting the table alone breaks the selection channel; emitting the multi-select alone hides the visual view
• WHEN the accumulated selection contains Full guided setup, expand to every available track in dependency order (step 3's per-track confirmation still runs so the user can stop between any two tracks). Otherwise, run only the picked tracks. Full guided setup picked alongside individual tracks means "run everything" — treat it as Full guided setup and ignore the per-track picks
• NEVER run domain-level prerequisites (such as the Incident Management master switch) at this level — each sub-orchestrator owns and runs its own prerequisites, so users who did not select the relevant track are never prompted for unrelated org-level changes
• NEVER show a track that has no working sub-orchestrator
• NEVER configure a feature directly — always delegate to the sub-orchestrator (delegating through the domain orchestrator ensures its menu, progress tracking, and per-feature confirmations are applied; configuring directly bypasses that state and leaves the setup inconsistent)
• Track progress across the conversation — re-derive each track's status from the latest sub-orchestrator activity in the transcript, not from the previously rendered highlight. On a resumed or long conversation, do not assume the last-highlighted track is still current; if ambiguous, re-confirm the active track with the user before rendering the menu
• Do not show Salesforce record IDs in any output — use human-readable names only
• If the user asks about a specific feature directly (e.g., "set up the priority matrix", "just enable CMDB"), you may skip the Behavior step 2 track menu and delegate directly to the corresponding sub-orchestrator; the sub-orchestrator will handle its own prerequisites as needed
• If the user asks for a setup area that is not yet available (e.g. employee provisioning, major incident management), tell them it is not yet available in this orchestrator and will be added as its sub-orchestrator merges

Verification checklist

Before emitting any menu or summary in this skill, mentally confirm each of the following. If any box is unchecked, adjust the output before sending.

• The header line ends with (via service-itsm-agentic-setup-configure)
• Only tracks with a working sub-orchestrator are shown; placeholder tracks are hidden
• The track menu was emitted as a single-stage paged multi-select — Full guided setup is a first-class option in the multi-select (page 1, first slot), NOT a separate mode-selector stage
• The ASCII table AND the page-1 AskUserQuestion were emitted in the same response — never one without the other
• When total options (tracks + Full guided setup) > 4, pages followed the shape: page 1 = Full guided setup + up to 2 tracks + Show more tracks →; middle pages = up to 3 tracks + Show more tracks →; last page = remaining ≤ 4 tracks with no sentinel. Selections were accumulated across pages and Show more tracks → was stripped from the final selection
• If the accumulated selection contained Full guided setup, every available track was enqueued in dependency order with per-track confirmation between them (per-track picks were ignored when Full guided setup was included)
• Each track row's Status column reflects the actual tracked state from the conversation (Not done, In progress, or Done) — not a hard-coded default
• For a completion summary, the header line and closing line are chosen by the rubric in examples/output-templates.md (all Done → Complete; any Not done/In progress → Finished)
• No org-level prerequisites are being run at this level — the selected sub-orchestrator handles its own prerequisites
• The next action delegates to a sub-orchestrator, never directly to a feature child skill
• No Salesforce record IDs appear in the output — human-readable names only

Reference File Index