signoz-explaining-dashboards
Explain what an existing SigNoz dashboard shows in plain operational language — the panels, queries, variables, and what to watch for on each. Make sure to use this skill whenever the user asks "explain this dashboard", "what does my [X] dashboard show", "walk me through the panels", "what should I watch for on this dashboard", or "help me understand this dashboard", or otherwise asks for an interpretation of a dashboard's contents — even if they don't say "explain" explicitly. Also use it when someone is onboarding to a service and wants to understand what its existing observability looks like.
SigNoz · 已有 AI 审核记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add SigNoz/agent-skills --skill signoz-explaining-dashboards技能说明
name: signoz-explaining-dashboards description: > Explain what an existing SigNoz dashboard shows in plain operational language: the panels, queries, variables, and what to watch for on each. Make sure to use this skill whenever the user asks "explain this dashboard", "what does my [X] dashboard show", "walk me through the panels", "what should I watch for on this dashboard", or "help me understand this dashboard", or otherwise asks for an interpretation of a dashboard's contents, even if they don't say "explain" explicitly. Also use it when someone is onboarding to a service and wants to understand what its existing observability looks like.
Dashboard Explain
Prerequisites
This skill calls SigNoz MCP server tools (signoz_get_dashboard,
signoz_list_dashboards). Before running the workflow, confirm the
signoz_* tools are available. If they are not, the SigNoz MCP server
is not installed or configured; run signoz-mcp-setup first to initialize or
repair the MCP connection. Do not guess at a dashboard's contents from its
title alone.
When to use
Use this skill when the user asks to:
- Understand, explain, or interpret an existing dashboard
- Get a walkthrough of what panels show and why they matter
- Know what to watch for or what healthy/unhealthy looks like on a dashboard
- Understand the variables, filters, or queries on a dashboard
Do NOT use when:
- User wants to modify an existing dashboard →
signoz-modifying-dashboards
Instructions
Step 1: Identify the target dashboard
Use a supplied id or a dashboard resource that includes its id directly.
For any name-only request, call signoz_list_dashboards and resolve the name to
an id, matching on spec.display.name. Cover the whole listing: narrow with
the filter argument, re-run unfiltered when it comes back empty, and page by
raising offset by limit until you have covered total. Never pass a
dashboard name to signoz_get_dashboard or conclude it is missing from the
first page.
If multiple dashboards match, present the candidates and ask which one to explain.
Step 2: Fetch the full dashboard configuration
Call signoz_get_dashboard with the dashboard id. This is mandatory; you
need the complete JSON to explain the dashboard accurately. Never guess based on
the title alone.
Examine the response to understand:
spec.display.name,.description,tags: the dashboard identity and author-provided contextspec.variables: dashboard-level filters (dropdowns the user can change)spec.panels(a map keyed by panel id): the panels, their plugin kinds, titles, and queriesspec.layouts: Grid entries placing panels in the 12-column grid viacontent.$ref- each Grid's
spec.display.title: the section a panel belongs to
Step 3: Build the explanation
Structure your explanation in this order:
1. Overview: one paragraph summarizing the dashboard's purpose, what it
monitors, and what data sources it draws from (metrics, traces, logs). Mention
the tags if they provide useful context.
2. Variables and filters: explain each variable:
- Name (
spec.name, the$handlequeries reference) and what it filters; for asignoz/DynamicVariablethat isplugin.spec.nameonplugin.spec.signal - Kind:
signoz/DynamicVariable(auto-populated from telemetry),signoz/QueryVariable(query-driven dropdown),signoz/CustomVariable(configured choices), or aTextVariable(free-form input) - Whether it supports multi-select (
allowMultiple) and an "ALL" option - Note if any panels do NOT reference a variable in their
filter.expression: changing that variable dropdown would not affect those panels, which can be confusing
3. Panel-by-panel walkthrough. Group panels by Grid section: walk
spec.layouts in order, using each Grid's spec.display.title as the section
header and following its spec.items (by y then x) to the panels they
$ref. For a single untitled Grid, walk panels in position order and organize
by logical theme. For each panel:
- Title and panel type in plain words, from the plugin
kind:signoz/TimeSeriesPanel,signoz/NumberPanel(single value),signoz/TablePanel,signoz/BarChartPanel,signoz/PieChartPanel,signoz/HistogramPanel,signoz/ListPanel(raw rows) - What it shows: interpret the panel's one query in plain language. For
signoz/BuilderQuery, explain the signal, aggregation,filter.expression, andgroupBy. For asignoz/CompositeQuery, explain each member and how the formula combines them. For ClickHouse SQL or PromQL, translate the query intent into plain English. - What to watch for: describe what healthy looks like and what patterns indicate trouble. Be specific: "sustained usage above 80% means..." not just "watch if it's high". Anchor advice to the actual metric being queried, not generic domain knowledge.
- Unit: mention
plugin.spec.formatting.unitso the user knows how to read the values
For panels with complex queries:
- Formulas (inside a composite): explain each member (A, B, ...) separately, then explain what the formula computes and why
- Functions (rate, derivative, clampMin/Max, timeShift): explain the transform in plain terms (e.g., "rate converts the raw counter into a per-second value")
4. Dashboard health observations. After the walkthrough, note any structural issues you spotted:
- Panels with no query, or a composite whose members are all disabled
- Panels in
spec.panelsthat no grid item references (they never render) - Variables defined but not referenced in any panel filter
- Panels missing thresholds where they would be useful (e.g., utilization panels without a saturation warning line)
- Counters displayed without a rate function (raw counters produce ever-increasing ramps, not operational rates)
- Very wide step intervals that could hide spikes
- Panels with high-cardinality groupBy that may pro