monte-carlo-data/mc-agent-toolkit / skills/generate-validation-notebook
generate-validation-notebook
VerifiedGenerate SQL validation notebooks for dbt changes. Pass a GitHub PR URL or local dbt repo path.
| File | Kind | Size |
|---|---|---|
| README.md | markdown | 2.7 KB |
| SKILL.md | skill md | 23.8 KB |
| scripts/generate_notebook_url.pyexecutable | script | 4.7 KB |
| scripts/resolve_dbt_schema.pyexecutable | script | 5.4 KB |
README.md
View on GitHub# Generate Validation Notebook Skill
Automatically generate SQL validation notebooks for dbt model changes. Given a GitHub PR or local dbt repository, this skill identifies modified models and produces a Monte Carlo SQL Notebook with targeted validation queries comparing baseline and development data.
## What it does
1. Identifies changed dbt models from a PR diff or local branch
2. Analyzes each model's schema, config, segmentation fields, and time axis
3. Generates SQL validation queries (row counts, distribution checks, NULL rates, before/after comparisons, uniqueness checks)
4. Packages everything into a Monte Carlo SQL Notebook with parameterized database references
5. Outputs an import URL that opens the notebook directly in Monte Carlo's notebook interface
## Prerequisites
- Claude Code or any MCP-capable editor
- [GitHub CLI](https://cli.github.com/) (`gh`) — required for PR mode, must be authenticated
- Python 3 with `pyyaml` installed (`pip install pyyaml`)
- [MC Bridge](https://docs.getmontecarlo.com/docs/mc-bridge) running and connected to your warehouse
## Setup
### Via the mc-agent-toolkit plugin (recommended)
Install the plugin for your editor — see the [main README](../../README.md) for instructions. The skill is bundled automatically.
### Standalone
Copy the skill to your local skills directory:
```bash
cp -r skills/generate-validation-notebook ~/.claude/skills/generate-validation-notebook
```
## Usage
### PR mode
```
/mc-generate-validation-notebook https://github.com/your-org/dbt/pull/123
```
Fetches the PR diff from GitHub, identifies changed models, and generates validation queries.
### Local mode
```
/mc-generate-validation-notebook .
```
Uses `git diff` against the base branch to find changed models in the current repository.
### Options
- `--mc-base-url <URL>` — Monte Carlo base URL (defaults to `https://getmontecarlo.com`)
- `--models <model1,model2,...>` — only generate for specific models (by filename, without `.sql`)
## What gets generated
The notebook includes:
- **Parameter cells** — `prod_db` and `dev_db` for selecting databases
- **Markdown summary** — PR metadata, changed models, usage instructions
- **SQL validation queries** organized by pattern:
- Row counts (single and comparison)
- Segmentation distribution
- Changed field distribution
- NULL rate checks
- Uniqueness checks
- Time-axis continuity
- Before/after comparisons
- Sample data previews
Up to 10 changed models are processed per invocation.
## Supported warehouses
Generated SQL uses ANSI-compatible syntax that works across Snowflake, BigQuery, Redshift, and Athena. Minor adjustments may be needed for specific warehouse quirks.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| deprecation-and-migrationaddyosmani/agent-skillsManages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when migrating a database schema in production, such as renaming or dropping a column without downtime (expand/contract). Use when deciding whether to maintain or sunset existing code. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| performance-optimizationaddyosmani/agent-skillsOptimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| Agent Cost Reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |
| Agent Cost Reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |