メニュー
Personal Rootly dashboard. Shows your open action items, your active incidents (where you're a responder), and your upcoming on-call shifts. Use to start the day or to context-switch back into incident work.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Set up the Rootly plugin. Verifies MCP server connection via OAuth2 or API token and guides through configuration. Run this after installing the plugin.
Manage incident action items from the terminal. Subcommands - list (default - your open action items) or add <incident> "<summary>" (create one on an incident). Use to capture follow-ups during or after an incident without opening the Rootly UI.
Draft a stakeholder-facing status update for an active incident, then post it after explicit confirmation. Useful for incident commanders pushing public-status-page or internal updates without opening the Rootly UI. Write action - never posts without confirming.
Offer to cover someone else's on-call shift. Lists upcoming shifts on a team or schedule and creates an override placing you on the chosen one after explicit confirmation. Write action - never executes without confirming.
Request someone to cover one of your upcoming on-call shifts. Lists your shifts, helps identify a candidate based on availability, and creates an override after explicit confirmation. Write action - never executes without confirming.
Triage a Rootly alert by short ID. Pulls the alert record, its event timeline, related alerts in the same group, and any incident the alert is attached to. Use when a page comes in and you want context before opening Rootly.
| name | my |
| description | Personal Rootly dashboard. Shows your open action items, your active incidents (where you're a responder), and your upcoming on-call shifts. Use to start the day or to context-switch back into incident work. |
| disable-model-invocation | true |
| allowed-tools | ["mcp__rootly__*"] |
You are building a personal status board for the current Rootly user. Read-only, focused, and quick to scan.
Call mcp__rootly__getCurrentUser. Capture:
user_id (UUID) — for filtering downstream callsname and email — for the headerIf getCurrentUser fails, stop with a clear auth error message.
You may issue these tool calls in parallel where the model supports it. Keep each call narrow — we want a fast dashboard, not a full audit.
a. Open action items
mcp__rootly__listAllIncidentActionItems (first page, page_size = 50).assigned_to_user_id (or equivalent field) matches the user, with status not in done/closed/cancelled.b. Active incidents you're on
mcp__rootly__listIncidents with filter_status=started and filter_user_id=<user_id> if supported, or with the user's team via filter_team_ids if individual filtering isn't available.c. Upcoming shifts
mcp__rootly__listShifts for the current user, scoped to the next 7 days.mcp__rootly__list_shifts and filter client-side.## [User name]'s Rootly Dashboard
*[email] — [primary team if known]*
### Active Incidents ([N])
[For each: severity badge, INC-XXXX, title, your role, started X ago]
- 🔴 [INC-XXXX] [title] — your role: [responder/IC/observer], started [duration] ago
- 🟡 [INC-YYYY] [title] — your role: [responder], started [duration] ago
[If zero: "No active incidents you're responding to."]
### Open Action Items ([N])
[Cluster by incident, max 10 items]
#### [INC-XXXX] [title]
- [ ] [description] — due [date or "no due date"]
- [ ] [description]
[If zero: "No open action items assigned to you."]
### Upcoming On-Call ([N] shifts in the next 7 days)
- [Schedule name]: [start] → [end] ([role/level if available])
- [Schedule name]: [start] → [end]
[If currently on call:]
**Currently on call**: [Schedule name] until [end time].
[If zero: "No on-call shifts in the next 7 days."]
---
### Quick links
- `/rootly:status` — service health overview
- `/rootly:oncall` — full team on-call schedule
- `/rootly:action add <incident> "<desc>"` — capture a follow-up
- `/rootly:swap` — request a shift swap