| name | monte-carlo-performance-diagnosis |
| description | Diagnoses data-pipeline slowness with Monte Carlo observability across Airflow, dbt, Databricks, and warehouse engines (slow jobs, costly queries, compute regressions). Use when the user asks why a pipeline is slow or what burns compute. Not for data-quality incidents (monte-carlo-analyze-root-cause), storage-cost analysis, or creating monitors. |
| version | 1.0.1 |
| risk | unknown |
| source | https://github.com/monte-carlo-data/mc-agent-toolkit/tree/main/skills/performance-diagnosis |
| source_repo | monte-carlo-data/mc-agent-toolkit |
| source_type | community |
| date_added | 2026-07-01T00:00:00.000Z |
| license | Apache-2.0 |
| license_source | https://github.com/monte-carlo-data/mc-agent-toolkit/blob/main/LICENSE |
Monte Carlo Performance Diagnosis Skill
Diagnose data pipeline performance issues using Monte Carlo's cross-platform observability data. This skill works across Airflow, dbt, Databricks, and warehouse query engines to find bottlenecks, detect regressions, and identify root causes using a tiered investigation approach: discover problems → bridge to affected tables → drill into root causes.
Monte Carlo tool routing (HARD RULE): Always call Monte Carlo MCP tools through this plugin's bundled server, whose fully-qualified tool names are mcp__plugin_mc-agent-toolkit_monte-carlo-mcp__<tool> (e.g. mcp__plugin_mc-agent-toolkit_monte-carlo-mcp__get_alerts). Bare tool names used in this skill (get_alerts, search, get_table, …) refer to that bundled server. If the session also has a separately-configured monte-carlo-mcp server, do not route to it — it may point at a different endpoint or credentials.
Tiered methodology lives in this SKILL.md (Steps 1–4). Use the Read tool on this file (not MCP resources).
When to Use
Activate when the user:
- Asks about slow pipelines, jobs, or queries
- Wants to find expensive or costly queries
- Mentions performance regressions or degradation
- Asks "why is this pipeline slow?" or "what's using the most compute?"
- Wants to compare performance over time or find bottleneck tasks
- Asks about failed or futile query patterns
Do NOT activate when the user is:
- Investigating data quality issues → use the
prevent skill
- Looking at storage costs → use the
storage-cost-analysis skill
- Creating monitors → use the
monitoring-advisor skill
- Just querying data or exploring table contents
Prerequisites
The following MCP tools must be available via the bundled Monte Carlo MCP server (mcp__plugin_mc-agent-toolkit_monte-carlo-mcp__*):
Discovery tools (Tier 1):
| Tool | Purpose |
|---|
get_jobs_performance | Find slow/failing jobs across Airflow, dbt, Databricks |
get_top_slow_queries | Find slowest query groups by total runtime |
