agent-skills

Look up information in SigNoz documentation. Make sure to use this skill whenever the user asks "how do I", "where in the docs", "what does the docs say about", "find docs for", or otherwise needs reference material on SigNoz instrumentation, OpenTelemetry setup, self-hosted deployment, API endpoints, auth headers, or troubleshooting steps — even if they don't say the word "docs" explicitly. Docs lookup only — for actions inside SigNoz, the agent will pick the matching `signoz-*` action skill.

Initialize or repair SigNoz MCP server configuration for Claude Code, Codex, Cursor, VS Code/GitHub Copilot, Claude Desktop, Gemini CLI, Devin CLI, Windsurf, Zed, Antigravity CLI, OpenCode, or another MCP client. Use this skill before any SigNoz docs, query, dashboard, alert, or view workflow when `signoz_*` tools are unavailable, or when the user says "setup SigNoz MCP", "configure SigNoz plugin", "wrong region", "change SigNoz region", "MCP auth failed", or asks to connect SigNoz Cloud or a self-hosted MCP endpoint, even if they do not mention the plugin.

Generate, write, or run an ad-hoc query against SigNoz observability data — metrics, logs, traces, or exceptions — without wrapping it in a dashboard panel or alert. Make sure to use this skill whenever the user asks "show me error rates", "query logs for timeout errors", "what's the p99 latency for the cart service", "how many requests hit the payment endpoint", "find slow traces", "errors in the last hour", or otherwise asks an exploratory question that needs live observability data — even if they don't say "query" or "search" explicitly.

Create a new SigNoz dashboard from a natural-language intent — import a curated template (PostgreSQL, Redis, JVM, k8s, hostmetrics, APM, LLM, etc.) when one fits, or build a custom dashboard from scratch with metric / trace / log panels. Make sure to use this skill whenever the user says "create a dashboard for…", "set up monitoring for…", "build me a dashboard…", "I need observability for…", "import a dashboard template", or asks to track / visualize a service, database, cluster, or AI/LLM platform — even if they don't explicitly say "dashboard". Also use it when someone wants to "monitor", "watch", or "see metrics for" a technology and the natural answer is a dashboard.

Use when the user wants to create, list, get, update, rename, or delete a SigNoz saved Explorer view. Trigger on phrases like "save this query as a view", "save this filter", "bookmark this search", "list my saved views", "show me views for traces/logs/metrics/meter", "rename the X view", "update my saved view to also filter Y", "delete the X view", or any request to manage Explorer saved views — even if they don't say "view" explicitly. Also use when someone wants to share a recurring Explorer query with their team and asks how to "save" or "bookmark" it.

Create a new SigNoz alert rule from a natural-language intent — threshold, anomaly, log-volume, error-rate, latency, or absent-data alerts across metrics, logs, traces, and exceptions. Make sure to use this skill whenever the user says "alert me when…", "notify me if…", "set up monitoring for…", "page me on…", "create an alert for…", or asks for a new alert/notification rule, even if they don't say the word "alert" explicitly. Also use it when someone asks to be notified about error rates, latency spikes, log volume, CPU/memory pressure, or anomalous behavior on a service or host.

Describe what an existing SigNoz alert rule does in plain language — the signal it watches, the threshold and evaluation behavior, the notification routing, and a one-line fire-frequency summary so the user knows whether the alert has been active. Make sure to use this skill whenever the user asks "what does this alert do", "explain alert X", "walk me through this rule", "how does my [Y] alert work", "is this alert configured correctly", or otherwise asks for an interpretation of an existing alert's configuration. Static explanation only — for diagnosing a specific firing incident, use `signoz-investigating-alerts`.

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.

Diagnose why a SigNoz alert fired by correlating the alert's own signal with neighbor signals (error rate, latency, throughput, CPU/memory), traces, and logs around the fire window — and rank likely causes. Make sure to use this skill whenever the user asks "why did this alert fire", "what caused alert X", "investigate this alert", "RCA for the alert that paged me", "what's wrong with [service]" in the context of a recent fire, or otherwise asks for a root-cause analysis of a firing or recently-fired alert. Read-only — does not modify any alert or notification.

Modify an existing SigNoz dashboard — add or remove panels, edit a panel's query, threshold, or unit, rename the dashboard, change a panel type (graph ↔ table ↔ value), rearrange the layout, add or edit variables, or update tags. Make sure to use this skill whenever the user says "add a panel to my dashboard", "change the query on this panel", "remove the latency widget", "rename my dashboard", "update the filters", "rearrange the layout", "add a variable", "change panel type from graph to table", or otherwise asks to change something on a dashboard that already exists — even if they don't say "modify" or "edit" explicitly.

Run the full end-to-end observability setup for a service after its telemetry is already flowing into SigNoz — sequence SLI/SLO capture, data exploration (RED/USE), focused dashboards, saved Explorer views, burn-rate and absent-data alerts, and a tuning loop into one opinionated, SLO-aware workflow. Make sure to use this skill whenever the user says "set up observability after ingestion", "now that data is flowing, give me dashboards and alerts", "onboard this service to SigNoz end-to-end", "I want the full monitoring setup for X", or asks to go from raw telemetry to a complete dashboard + alerts + views package — even if they don't say "observability" explicitly. This is the orchestration layer: for a single artifact (just a dashboard, just one alert, just a saved view, or one static threshold alert, or a one-off query) use signoz-creating-dashboards, signoz-creating-alerts, signoz-managing-views, or signoz-generating-queries directly.

Write raw ClickHouse SQL for a SigNoz dashboard panel — timeseries, value, or table widgets that the builder UI cannot express (custom joins, window functions, regex extraction over log bodies, aggregations beyond builder syntax). Trigger when the user explicitly asks for a "ClickHouse query", a "raw SQL panel", a "custom SQL widget", or describes a SigNoz dashboard panel whose query needs SQL the builder cannot produce. Anchored to dashboard-panel SQL specifically. For ad-hoc data exploration that does not need to land in a panel, use `signoz-generating-queries` instead.