Rootly
Full-lifecycle incident management: deploy safety, incident response, on-call management, and retrospectives.
Skills (18)
Claude uses these on its own when your request matches.
- actionManage 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.
- alertTriage 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.
- announceDraft 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.
- askAsk natural language questions about incidents, on-call, services, and reliability data. Translates your question into Rootly API calls and returns structured answers.
- briefGenerate a concise stakeholder brief for an incident. Creates executive summary with key details, impact, timeline, and current status.
- coverOffer 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.
- deploy-check[experimental] Evaluate deployment risk by analyzing code changes against incident history, active incidents, and on-call readiness. Forked-subagent flow may not have MCP access in all Claude Code contexts.
- handoffPrepare an incident or on-call handoff document. Creates structured summary for shift changes or incident commander transitions.
- lookupLook up a service, team, or catalog entity in Rootly. Returns owner, on-call, recent reliability, dependencies, and any active incidents. Use when something breaks and the first question is who owns this.
- myPersonal 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.
- oncallShow current on-call status, shift metrics, and health indicators for your team. Use to check who's on-call, handoff context, or on-call workload.
- respond[experimental] Investigate and respond to a production incident. Pulls context, finds similar past incidents, suggests solutions, and enables coordination. Forked-subagent flow may not have MCP access in all Claude Code contexts -- prefer /rootly:status + /rootly:brief for now.
- retro[experimental] Generate a structured post-incident retrospective from incident data. Forked-subagent flow may not have MCP access in all Claude Code contexts.
- setupSet up the Rootly plugin. Verifies MCP server connection via OAuth2 or API token and guides through configuration. Run this after installing the plugin.
- statusShow a compact service health overview including active incidents by severity. Use for a quick health check of your services.
- swapRequest 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.
- testSimple test skill
- trendReliability trend summary for a service, team, or the whole org. Reports incident volume, severity mix, and MTTR direction over a window (default 30 days). Use for standups, 1-on-1s, or quarterly reviews.
MCP server
Added to Claude Code when you install the plugin. You sign in to Rootly the first time it is used.
- rootlyRemote
https://mcp.rootly.com/mcp
Agents (3)
Specialized helpers Claude can hand work to.
- deploy-guardianDeployment safety specialist for blast-radius analysis, downstream dependency checks, and cross-team coordination planning.
- incident-investigatorDeep production-incident investigator for root-cause analysis, evidence gathering, and remediation planning beyond the initial response brief.
- retro-analystReliability pattern analyst for retrospectives, recurring-incident clustering, and systemic improvement recommendations.
Also adds hooks that run automatically at set points in a session.
Install
Run in your terminal
claude plugin install rootly@claude-plugins-officialClaude Code already includes the claude-plugins-official marketplace, so this installs directly. Start a new Claude Code session to use it.
Already in a Claude Code session?
Install
/plugin install rootly@claude-plugins-officialPublished in Anthropic's claude-plugins-official marketplace (anthropics/claude-plugins-official).
Related plugins
- 1RRememberContinuous memory for Claude Code. Extracts, summarizes, and compresses conversations into tiered daily logs. Claude remembers what you did yesterday.51kmarketplace installs
- 2
SentrySentry error monitoring integration. Access error reports, analyze stack traces, search issues by fingerprint, and debug production errors directly from your development environment.39kmarketplace installs
- 3
DatadogUse Datadog directly in Claude Code through a preconfigured Datadog MCP server. Query logs, metrics, traces, dashboards, and more through natural conversation. This plugin is in preview.16kmarketplace installs
- 4
PostHogAccess PostHog analytics, feature flags, experiments, error tracking, and insights directly from Claude Code.13kmarketplace installs
- 5
PagerDuty Pre-Commit Risk ScoreEnhance code quality and security through PagerDuty risk scoring and incident correlation. Score pre-commit diffs against historical incident data and surface deployment risk before you ship.5kmarketplace installs
- 6AAmplitudeUse Amplitude as an expert analyst — instrument Amplitude, discover product opportunities, analyze charts, create dashboards, manage experiments, and understand users and accounts.2.3kmarketplace installs