Skip to content

monte-carlo-data/mc-agent-toolkit / skills/performance-diagnosis

monte-carlo-performance-diagnosis

Verified

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.

FileKindSize
README.mdmarkdown2.3 KB
SKILL.mdskill md7.8 KB
references/investigation-tiers.mdmarkdown3.7 KB
references/query-analysis.mdmarkdown2.7 KB
# Performance Diagnosis Skill

Diagnoses data pipeline performance issues using Monte Carlo's cross-platform observability.

## What it does

- Finds slow jobs and expensive queries across Airflow, dbt, and Databricks
- Uses a tiered investigation approach: discover problems, bridge to tables, drill into root causes
- Detects regressions via change timeline correlation (query changes + volume shifts + failures)
- Identifies failed/futile query patterns with pre-computed root cause analysis
- Tracks latency trends to spot gradual degradation

## MCP Tools Required

Connect to Monte Carlo's MCP server (`integrations.getmontecarlo.com/mcp`). The skill uses these tools:

| Tool | Tier | Purpose |
|------|------|---------|
| `get_jobs_performance` | Discovery | Find slow/failing jobs |
| `get_query_perf_profile` | Discovery | Find most expensive queries |
| `get_tables_for_job` | Bridge | Convert job MCONs to table MCONs |
| `get_tasks_performance` | Diagnosis | Find bottleneck tasks within a job |
| `get_change_timeline` | Diagnosis | Unified "what changed?" timeline |
| `get_query_rca` | Diagnosis | Root cause analysis for query failures |
| `get_query_latency_distribution` | Diagnosis | Latency trend over time |
| `get_asset_lineage` | Diagnosis | Trace upstream/downstream impact |
| `get_warehouses` | Supporting | List available warehouses |

## Example prompts

- "Why is our nightly pipeline so slow?"
- "Find the most expensive queries in our Snowflake warehouse"
- "What changed that made the orders model take twice as long?"
- "Are there any failing query patterns we should fix?"
- "Show me the latency trend for our ETL jobs"

## Investigation flow

```
Tier 1: Discovery          Tier 2: Diagnosis
(no MCONs needed)          (MCONs from Tier 1 or user)

get_jobs_performance ──┐
                       ├──► get_tables_for_job ──► get_tasks_performance
get_query_perf_profile ──┘                           get_change_timeline
                                                   get_query_rca
                                                   get_query_latency_distribution
                                                   get_asset_lineage
```

Typical investigation: 3-7 tool calls. Stop as soon as you have a root cause with evidence.

See `references/investigation-tiers.md` for detailed tool usage.
writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deploymentStars: 322kUpdated Claude CodeCodexVerifiedInstall
xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release.Stars: 118kUpdated Claude CodeCodexVerifiedInstall