AGENT SKILL

ask

Ask natural language questions about incidents, on-call, services, and reliability data. Translates your question into Rootly API calls and returns structured answers.

License 许可
MIT
最近更新
2026-11-13
Stars
★ 29
Forks
156

01 前言 Front Matter

name
ask
description
Ask natural language questions about incidents, on-call, services, and reliability data. Translates your question into Rootly API calls and returns structured answers.
allowed-tools
[ "mcp__rootly__*" ]
argument-hint
[ "your question" ]
disable-model-invocation
true

03 SKILL.md 正文

Natural Language Query

You are answering a natural language question about the user's incident, on-call, or reliability data using Rootly's MCP tools.

Workflow

1. Understand the Question

Parse the user's question from $ARGUMENTS. Identify what data they need.

2. Discover Available Tools

Call mcp__rootly__list_endpoints to see the full list of available Rootly MCP tools and their capabilities. This helps you select the right tools for the query.

3. Execute Queries

Select the most appropriate tools for the question. You may need multiple calls to fully answer the question. Common patterns:

  • "How many incidents last week?" -> mcp__rootly__search_incidents with date filters
  • "Who's on call?" -> mcp__rootly__get_oncall_handoff_summary
  • "What happened with [service]?" -> mcp__rootly__search_incidents filtered by service
  • "Show me critical incidents" -> mcp__rootly__search_incidents filtered by severity
  • "Any patterns in auth service failures?" -> mcp__rootly__search_incidents + mcp__rootly__find_related_incidents

4. Present Answer

Provide a clear, structured answer with supporting data. Include:

  • Direct answer to the question
  • Supporting data in tables or lists where helpful
  • Source attribution (which tools/queries produced the data)

5. Limitations

Be explicit about what you can't answer. If the question requires data that isn't available through the Rootly MCP tools, say so clearly rather than guessing or hallucinating. For example:

  • "I can't answer questions about infrastructure metrics -- Rootly tracks incidents, not system metrics."
  • "This question requires data from [other system]. I can only query Rootly incident and on-call data."

04 同仓库更多 Skills

CognitionAI
CognitionAI/devin-marketplace

business-data

暂无简介

★ 29
CognitionAI
CognitionAI/devin-marketplace

workflow

Creates durable, resumable workflows using Vercel's Workflow SDK. Use when building workflows that need to survive restarts, pause for external events, retry on failure, or coordinate multi-step operations over time. Triggers on mentions of "workflow", "durable functions", "resumable", "workflow sdk", "queue", "event", "push", "subscribe", or step-based orchestration.

★ 29
CognitionAI
CognitionAI/devin-marketplace

workflow

Vercel Workflow SDK expert guidance. Use when building durable workflows, long-running tasks, API routes or agents that need pause/resume, retries, step-based execution, or crash-safe orchestration with Vercel Workflow.

★ 29
CognitionAI
CognitionAI/devin-marketplace

verification

Full-story verification — infers what the user is building, then verifies the complete flow end-to-end: browser → API → data → response. Triggers on dev server start and 'why isn't this working' signals.

★ 29
CognitionAI
CognitionAI/devin-marketplace

vercel-storage

Vercel storage expert guidance — Blob, Global Config (formerly Edge Config), and Marketplace storage (Neon Postgres, Upstash Redis). Use when choosing, configuring, or using data storage with Vercel applications.

★ 29
CognitionAI
CognitionAI/devin-marketplace

vercel-services

Configure and troubleshoot Vercel Services for multiple frontends and backends in one project. Use when composing a polyglot or multi-service application on one Vercel deployment; defining the `services` key, service-targeted rewrites, or service bindings in `vercel.json`; or running all services with `vercel dev`.

★ 29