alert-investigation

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Alert investigation

警报调查

You are investigating a specific triggered alert. Alerts arrive with structured context — an alert ID, name, threshold, value that crossed it, and a time range. Your job is to explain why it fired, assess scope, and recommend action.
你正在调查一个特定的触发警报。警报会附带结构化上下文——警报ID、名称、阈值、触发阈值的数值以及时间范围。你的任务是解释警报触发的原因,评估影响范围,并给出行动建议

Prerequisites

前提条件

This skill uses the following LaunchDarkly observability MCP tools:
  • query-logs
    — query log records
  • query-traces
    — query distributed traces
  • query-error-groups
    — query error groups
  • query-sessions
    — query sessions
  • query-aggregations
    — query aggregated/time-bucketed metrics
  • get-keys
    — discover available attribute keys before filtering
本技能使用以下LaunchDarkly可观测性MCP工具:
  • query-logs
    — 查询日志记录
  • query-traces
    — 查询分布式链路追踪数据
  • query-error-groups
    — 查询错误组
  • query-sessions
    — 查询会话数据
  • query-aggregations
    — 查询聚合/时间桶化指标
  • get-keys
    — 在过滤前发现可用的属性键

Workflow

工作流程

  1. Parse the alert context. The first turn of the conversation carries alert variables:
    alertID
    ,
    alertName
    ,
    alertValue
    ,
    group
    ,
    groupValue
    ,
    query
    ,
    thresholdWindow
    ,
    timeRange
    , plus a product-specific link. Use these, don't re-derive them.
  2. Load the per-product companion. Based on the alert's product type, load the matching companion:
    logs.md
    ,
    traces.md
    ,
    errors.md
    ,
    sessions.md
    , or
    metrics.md
    . Each captures the per-product investigation shape.
  3. Run the investigation using the methodology from the investigate skill (cross-reference logs/traces/errors/sessions/metrics; cite identifiers; aggregate before paginating). Scoped to the alert's time range and filter.
  4. Produce a structured diagnosis. See output template below.
  1. 解析警报上下文。对话的第一轮会携带警报变量:
    alertID
    alertName
    alertValue
    group
    groupValue
    query
    thresholdWindow
    timeRange
    ,以及一个产品特定链接。直接使用这些变量,无需重新推导。
  2. 加载对应产品的配套文档。根据警报的产品类型,加载匹配的配套文档:
    logs.md
    traces.md
    errors.md
    sessions.md
    metrics.md
    。每个文档都定义了对应产品的调查框架。
  3. 开展调查。使用调查技能中的方法(交叉引用日志/链路追踪/错误/会话/指标数据;引用标识符;分页前先聚合)。调查范围限定在警报的时间范围和过滤条件内。
  4. 生成结构化诊断结果。参考下方的输出模板。

Output template

输出模板

Alert investigations have a consistent structure so consumers (notification channels, dashboards) can parse them.
undefined
警报调查需采用统一结构,以便接收方(通知渠道、仪表盘)能够解析。
undefined

What triggered

触发原因

<1-2 sentences naming the alert, the threshold, and the value that crossed it.>
<1-2句话说明警报名称、阈值以及触发警报的数值。>

Likely cause

可能原因

<Root-cause narrative citing specific evidence: trace IDs, log timestamps, error group IDs, flag keys, deploy timing.>
<引用具体证据的根本原因说明:链路追踪ID、日志时间戳、错误组ID、标志键、部署时间。>

Scope

影响范围

<Who or what is affected. Number of users, services, sessions, error groups. Time window of impact.>
<受影响的对象或范围。用户数量、服务数量、会话数量、错误组数量。影响的时间窗口。>

Next steps

后续步骤

<1-3 concrete actions the on-call or owner should take. Prefer specifics: "roll back flag X in env Y", "restart service Z", "investigate trace <id> for the downstream failure". Avoid "investigate further" — if you don't have a root cause, say what specifically should be investigated and how.>
undefined
<1-3条待命人员或负责人应采取的具体行动。优先给出具体内容:“在环境Y中回滚标志X”、“重启服务Z”、“调查链路<id>中的下游故障”。避免使用“进一步调查”——如果无法确定根本原因,请说明具体需要调查的内容和方式。>
undefined

When to load which companion

何时加载对应配套文档

  • logs.md
    — log alert, log pattern alert
  • traces.md
    — latency alert, trace-error-rate alert, span-specific alert
  • errors.md
    — error-rate alert, new-error-group alert, crash-rate alert
  • sessions.md
    — session-health alert, user-facing-error-rate alert
  • metrics.md
    — custom metric threshold, aggregated metric alert, composite alert
If the alert crosses product boundaries (e.g. a metric alert driven by error data), load both companions.
  • logs.md
    — 日志警报、日志模式警报
  • traces.md
    — 延迟警报、链路错误率警报、特定跨度警报
  • errors.md
    — 错误率警报、新错误组警报、崩溃率警报
  • sessions.md
    — 会话健康警报、用户端错误率警报
  • metrics.md
    — 自定义指标阈值、聚合指标警报、复合警报
如果警报跨产品边界(例如由错误数据驱动的指标警报),则加载两个配套文档。

Guidelines

指导原则

  • Stay tight. Alert investigations feed notifications — keep the output structured and scannable. No preamble ("Here is my analysis..."), no repeated framing.
  • Cite identifiers. Every claim in the diagnosis should reference a specific trace ID, error group ID, session ID, or log timestamp.
  • If the alert appears to be noise, say so explicitly — "This alert fired because of <X>, but the underlying behavior is within normal variance because <Y>". Noise is a legitimate outcome; don't invent root causes.
  • Don't redo the investigation you just did. The diagnosis output should let the on-call act without re-querying.
  • 简洁紧凑。警报调查结果会用于通知——保持输出结构化且易于扫描。无需开场白(“以下是我的分析...”),无需重复框架内容。
  • 引用标识符。诊断中的每一项结论都应引用具体的链路追踪ID、错误组ID、会话ID或日志时间戳。
  • 如果警报看起来是误报,请明确说明——“此警报触发是因为<X>,但底层行为在正常波动范围内,原因是<Y>”。误报是合理的结果;不要编造根本原因。
  • 不要重复刚完成的调查。诊断输出应让待命人员无需重新查询即可采取行动。