Investigation and monitor creation guide for AI agent observability. Activates when the user asks about monitoring AI agents, setting up alerts on agent behavior, investigating agent traces, or creating agent monitors.

Build a Connection Auth Rules for a Monte Carlo connection type. Fetches live connector schemas and transform steps from the apollo-agent repo.

This skill determines which Monte Carlo skill or workflow best fits the user's current context. It activates reactively for ambiguous or multi-step data-related messages, gathers signals, and routes to the right skill or workflow.

This workflow orchestrates the full lifecycle of a data incident by sequencing existing Monte Carlo skills. It does not contain investigation or remediation logic itself — each step loads the relevant skill's SKILL.md which has the actual instructions.

This workflow guides users through improving their monitoring coverage by sequencing existing Monte Carlo skills. It does not contain coverage analysis or monitor creation logic itself — each step loads the relevant skill's SKILL.md which has the actual instructions.

Investigate data incidents and find root causes using Monte Carlo's observability data. Guides the agent through systematic investigation: alert lookup, lineage tracing, ETL checks, query analysis, and data profiling. Activates when a user asks about data issues, incidents, alerts, or why data looks wrong.

Check the health of a data table/asset using Monte Carlo. Activates on "how is table X", "check health of X", "is X healthy", "status of X", "check on X table", or any health/status question about a data asset.

Guides users through setting up and running automated alert triage for their Monte Carlo environment. Activates when a user asks to triage alerts, set up automated triage, run agentic triage, or investigate recent alert activity. Covers MCP setup, the stages of a triage workflow, and how to customise each stage to match how their team responds to alerts manually.

Guides AI agents through creating Monte Carlo monitors via MCP tools. Activates when a user asks to create, add, or set up a monitor for a table, field, metric, or data quality rule. Produces monitors-as-code (MaC) YAML that can be applied via the Monte Carlo CLI or CI/CD. All creation tools run in dry-run mode and return YAML -- they do not directly create monitors.

Analyze data coverage and create monitoring for critical use cases. Activates when the user asks about monitoring coverage, data coverage gaps, use case analysis, or wants to understand what's monitored vs. not.

Diagnoses pipeline performance issues -- slow jobs, expensive queries, latency trends -- using Monte Carlo's cross-platform observability. Uses a tiered investigation approach: discover problems, bridge to affected tables, then drill into root causes. Activates when a user asks about slow pipelines, expensive queries, or performance regressions.

Identifies storage waste patterns (unread tables, zombies, dead-ends) and recommends safe cleanup actions with cost savings estimates. Uses lineage to verify downstream dependencies before recommending removal. Activates when a user asks about storage costs, unused tables, or warehouse cleanup.

Analyze a Monte Carlo metric monitor and recommend configuration improvements to reduce alert noise. Fetches a monitor's report, identifies alert patterns, and suggests sensitivity, segment, and schedule changes.