Nightingale Agent bronze

alert-mute-copilot

One-stop assistant for creating, editing, and troubleshooting Nightingale (n9e) alert mute rules (alert_mute). Use it when the user asks to "create a mute rule / mute an alert / silence an alert / do-not-disturb during a maintenance window / set up periodic muting / mute every early morning / adjust or extend a mute / troubleshoot why a mute isn't working". Muting takes effect during the event evaluation stage (muted events are neither persisted nor notified); to configure "which events get notified to whom", use notification rules (→ notify-rule-copilot); to investigate "why didn't I get a notification", go to alert troubleshooting (→ alert-rule-troubleshoot).

alert-rule-troubleshoot

This skill should be used when the user reports that an alert rule is "not firing", "no alert was sent", "the rule didn't trigger", "the rule isn't working", "it should have alerted but didn't", "why didn't I get an alert", "alert rule not firing", or wants to diagnose why a specific alert rule failed to produce an event/notification. Use this skill to troubleshoot "why an alert rule did not fire as expected", as opposed to taking an existing alert and finding its root cause (for the latter, use ops-troubleshooting). Only supported on Release 22 and above.

alert-subscribe-copilot

One-stop assistant for creating, editing, and troubleshooting Nightingale (n9e) alert subscription rules (alert_subscribe). Use when the user asks to "create a subscription rule / subscribe to alerts / forward alert events / CC another team / escalate alerts (notify someone else after N minutes unhandled) / receive alerts across business groups / troubleshoot a subscription not taking effect". A subscription is a "copy + secondary routing" of events at the notification stage; to configure "who an event directly notifies" use notification rules (→ notify-rule-copilot), and to stop receiving alerts use muting (→ alert-mute-copilot).

analyze-dashboard

Analyze the data health of a given dashboard on Nightingale (n9e) over a time window. Use when the user asks to "analyze what problems a dashboard has", "check whether the xx dashboard has been normal over the last 24 hours", "inspect this dashboard", or "does this dashboard have any anomalies". Distinct from modifying a dashboard (modify-dashboard) and creating a dashboard (create-dashboard).

• Analyze what data problems the etcd dashboard has within 24 hours
• Check whether the Linux host monitoring dashboard has been normal over the last hour
• Inspect this dashboard
• Has the host web01 in this dashboard had any anomalies over the last day

categraf-deploy-guide

Answers "how do I deploy the categraf collector". Trigger scenarios: the user asks "how to install categraf / how to deploy categraf / run categraf with Docker / install categraf on Windows / how to register categraf as a system service / report categraf to Nightingale / how to write categraf config.toml / how to verify that categraf is collecting data". Covers binary + systemd, Docker, Windows, K8s tips, key configuration, and common verification commands. This skill is instructional/guidance-oriented, calls no tools, and outputs ready-to-paste commands and configuration snippets.

create-alert-rule

**Create alert rules**. Prefer reusing the validated rules in integrations (standard components like Linux/MySQL/Redis/Kafka/PostgreSQL/Elasticsearch all ship ready-made rule packs); import as many rules as the user needs—one rule, a batch, or a whole pack. Only hand-write a custom rule when integrations has nothing that fits. Supports all data sources: Prometheus / Loki / ES / OpenSearch / MySQL / PG / TDengine / ClickHouse / Doris / VictoriaLogs / Host. ⚠️ **Do NOT use this skill for bulk YAML imports**—when the user provides a URL or a YAML file, awesome-prometheus-alerts, node-exporter.yml, and the like, use import-prom-rule instead. Triggers: create an alert / add an alert / help me set up a CPU alert / add a set of alert rules for MySQL / configure common alerts for a host / I want to monitor a metric.

• Configure a set of common alert rules for the host
• Add a set of alert rules for MySQL
• Help me create an alert for CPU usage exceeding 80%
• Add a MySQL slow query alert rule
• Add a memory alert for the host, fire when it exceeds 90%

create-dashboard

Create monitoring dashboards. Use this when the user asks to create a dashboard, a monitoring board, or a Dashboard.

doc-qa

This skill should be used when the user asks "how-to" or factual questions about Nightingale (n9e) — UI/where-to-click, business groups/subscription rules/mute rules/edge mode, Token usage, notification pipeline, self-healing trigger conditions; OR about categraf input plugin field meanings, metric names, defaults, environment variables, config syntax (e.g. "how to write [[instances]]", "unit of ping_average_response_ms"); OR about the n9e / categraf / fe source code — this skill carries an embedded, searchable snapshot of the three repositories, so use it whenever the user asks "can you read the source code / the code directory", or asks how a feature is implemented, what a file or function does, or where something lives in the codebase. NOT for actively troubleshooting an alert or querying metrics.

generate-message-template

Generate or modify Nightingale (n9e) alert notification message templates. Use when the user asks to write a notification template, change the message format, add hostname/recovery value/severity, or create DingTalk/Feishu/Lark/email/SMS/voice templates.

host-health-diagnose

Help the user determine whether a machine is truly down / the agent is hung / the network is flapping / it is under maintenance. Triggers this skill when the user asks "why is this machine unreachable", "is the host-unreachable alert a false positive", "is categraf stuck", "the heartbeat stopped but I can still ping it", etc. Core stance: **an unreachable agent != a down host**. Concluding "down" just because target_up==0 / BeatTime stopped is a common source of false positives.

host-onboard-diagnose

Diagnose onboarding failures where "categraf is installed/running but the host does not show up in the Nightingale host list, or shows unknown / has no metrics". Triggers when the user asks "why doesn't my newly installed host appear", "all the OS values in the host list are unknown", "I installed 3 collectors via Helm but only see 1", "the agent won't register", or "categraf is installed but the host doesn't show". **Mutually exclusive** with host-health-diagnose: that one handles "was onboarded before, now lost contact", while this skill handles "never got onboarded at all". Core stance: **a missing host is not a single cause, but rather one segment of the onboarding pipeline being broken**. Looking only at heartbeat.enable and telling the user to change categraf is a common pitfall (many users change it and still can't see the host, because the problem is in omit_hostname / ident shell / TLS / token / edge redis / multi-cluster routing).

import-prom-rule

**Bulk import of a Prometheus alert rule YAML file** (create a whole set of rules at once). Dedicated to handling a remote URL or local YAML text, automatically parsing the three formats `groups` / a plain `rules` array / a single rule. ⚠️ **Do not use this skill for single-rule creation** — when the user describes a single alert requirement in natural language, use create-alert-rule instead. Triggers: import / import / bulk / URL / .yml file / .yaml file / awesome-prometheus-alerts / node-exporter.yml / prometheus rule file.

• Help me import https://raw.githubusercontent.com/.../node-exporter.yml
• Create all the alerts in this yaml
• Import the mysql file from awesome-prometheus-alerts
• Bulk-create a set of redis alert rules from this file ...

modify-dashboard

Modify an existing monitoring dashboard on Nightingale (n9e). Use when the user asks to change a dashboard's variables, check and fix variables, modify charts/series (change PromQL, legend, unit, add/remove series), rename a chart, or change the chart type (e.g., turn a stat chart into a timeseries chart). Distinct from "creating a dashboard from scratch" (that is create-dashboard).

• Change the default value of the ident variable on this dashboard to web01
• Check whether this dashboard's variables have any issues, and fix them while you're at it
• Change the query of the CPU usage chart to only look at total cores
• Add a swap usage series to the memory chart
• Change this panel's unit to percent
• Change the chart in the first row from a stat to a timeseries chart

modify-task-tpl

Helps users generate, modify, or troubleshoot Nightingale (n9e) alert self-healing scripts (task_tpl / ibex scripts). Use when the user asks to "write a self-healing script for disk cleanup / restarting a service / cleaning logs / dumping a process / reloading nginx", or asks "how does a self-healing script get the parameters passed from the alert", "what format is stdin in", "what should I set timeout to", "why is is_recovered always false", "why can't my self-healing script get the k8s namespace", "what do I do when a script stays running forever". This skill focuses on the **script body layer**—if the user wants to change alert rules, recipients, or notification templates, direct them to the corresponding skill.

notify-channel-copilot

Helps users modify, create, or troubleshoot Nightingale (n9e) notify channels (notify_channel). Use it when the user asks to change the URL, request body, signature, headers, proxy, TLS, @-mentions, or recipient fields of channels such as DingTalk/Feishu/WeCom/email/SMS/voice/Webhook, or asks "how do I integrate platform X" or "why can't it send / why am I getting 9499 / Bad Request". This skill focuses on **the channel-layer configuration**—if the user is changing "message content/fields/rendering", switch to generate-message-template instead.

notify-rule-copilot

One-stop assistant for creating, editing, copying, and troubleshooting Nightingale (n9e) notify rules (notify_rule). Use it when the user asks to "create a notify rule / add a notification policy / configure how alerts are delivered / edit and adjust a notify rule / tiered notification / route by business group or label / take different actions during vs. outside working hours / don't call on recovery / fix a rule that isn't matching" — it is especially good at decomposing natural-language routing requirements into a correct NotifyConfig array. This skill focuses on the routing layer of notify rules: it does not touch the notification media themselves (→ notify-channel-copilot), does not touch message templates (→ generate-message-template), and does not investigate "why nothing was sent" (→ alert-rule-troubleshoot flow B).

ops-troubleshooting

This skill should be used when the user asks to "troubleshoot", "diagnose", "debug alert", "investigate incident", "locate a fault", "investigate an alert", "diagnose a problem", "fix an issue", "check alerts", "analyze alerts", "root cause analysis", "check metrics", "check logs", or discusses monitoring/alerting/observability issues in the Nightingale (n9e) platform.

promql-generator

Generate PromQL queries from natural language

query-alert-events

Query alert events in a Nightingale (n9e) environment. Use this when the user asks to view alerts, query active alerts, search historical alerts, view alert details, or count alert events.

query-datasource

Query data from various datasources in a Nightingale (n9e) environment. Supports Prometheus metric queries, Elasticsearch/Loki log queries, and SQL datasource queries such as ClickHouse/MySQL/PostgreSQL/TDengine/Doris. Use when the user asks to query metrics, view monitoring data, search logs, or run PromQL or SQL queries.

skill-creator

Create/edit Nightingale AI Skills. Use when the user wants to create a new skill, codify a troubleshooting or operations workflow into a reusable skill, build a skill that can run scripts (Python/Bash), or modify/improve/optimize an existing self-built skill. Use this skill whenever the user says things like "make a skill", "save this workflow as a skill", "teach the AI a new trick", "tweak that skill of mine", "let the AI learn to troubleshoot following these steps", etc.

sql-generator

Generate SQL query statements from natural language (supports MySQL/Doris/ClickHouse/PostgreSQL)