By bauplanlabs
Manage Bauplan data lakehouses end-to-end: safely ingest S3 data via Write-Audit-Publish with quality gates and atomic merges, explore schemas/tables/profiles using Python SDK, create SQL/Python transformation pipelines, generate Polars-based quality expectations, assess data fitness for business questions, and debug failed jobs with pinned snapshots and Git fixes.
npx claudepluginhub bauplanlabs/bauplan-skills --plugin bauplanAssesses whether a business question can be answered with data available in a Bauplan lakehouse. Maps business concepts to tables and columns, checks data quality on the relevant subset, validates semantic fit, and renders a verdict: answerable, partially answerable, or not answerable. Produces a structured feasibility report. Use when a user brings a business question, asks 'can we answer this', wants to know if the data supports an analysis, or before building a one-off analysis or pipeline.
Creates bauplan data pipeline projects with SQL and Python models. Use when starting a new pipeline, defining DAG transformations, writing models, or setting up bauplan project structure from scratch.
Generates data quality check code for bauplan pipelines and ingestion workflows. Invoked by the bauplan-data-pipeline and bauplan-safe-ingestion skills, or directly by the user. Produces expectations.py for pipelines or validation logic for WAP scripts. Output is always code, never reports.
Diagnose a failed Bauplan job, pin the exact data state, collect evidence, apply a minimal fix, and rerun. Evidence first, changes second.
Explores data in a Bauplan lakehouse safely using the Bauplan Python SDK. Use to inspect namespaces, tables, schemas, samples, and profiling queries; and to export larger result sets to files. Read-only exploration only; no writes or pipeline runs.
Ingest data from S3 into Bauplan safely using branch isolation and quality checks before publishing. Use when loading new data from S3, importing parquet/csv/jsonl files, or when the user needs to safely load data with validation before merging to main.
The recommended setup for developing on Bauplan with AI coding assistants. This repo provides two things that work together:
Install the skills for your AI assistant of choice, and copy or integrate the context file into your own repo for the baseline context. Both are part of the same workflow — AI-assisted development on Bauplan.
/plugin marketplace add https://github.com/BauplanLabs/bauplan-skills
Restart Claude Code to make sure the changes are visible.
/plugin
Select Browse and install plugins → select bauplan-skills → press Space to select bauplan → press i to install.
Restart Claude Code.
Copy CLAUDE.md from this repo into the root of your project, or merge its contents into your existing CLAUDE.md:
curl -o CLAUDE.md https://raw.githubusercontent.com/BauplanLabs/bauplan-skills/main/CLAUDE.md
This gives Claude Code the baseline context it needs — safety rules, CLI vs SDK guidance, authentication setup, and pointers to the skills — even before any skill is triggered.
Inside Codex, run the skill installer pointing at the Bauplan skills directory:
$skill-installer https://github.com/BauplanLabs/bauplan-skills/tree/main/plugins/bauplan/skills
Codex will fetch and install the Bauplan skills automatically. Restart Codex once the installer completes.
To verify the installation, run /skills and select List skills — you should see the Bauplan skills listed.
Codex uses AGENTS.md as its project context file. Copy it into the root of your project:
curl -o AGENTS.md https://raw.githubusercontent.com/BauplanLabs/bauplan-skills/main/CLAUDE.md
Go to Settings > Cursor Settings > Rules, Skills, Subagents.
From there you have two options:
If you already use Claude Code with Bauplan skills installed: enable the Include third-party Plugins, Skills and Other Configs toggle. Bauplan skills will appear automatically — no additional import needed.
If you only use Cursor: in the Skills section, click New and prompt the agent to import Bauplan skills from:
https://github.com/BauplanLabs/bauplan-skills/tree/main/plugins/bauplan/skills
Cursor supports granular rules, but AGENTS.md works too. Copy it into the root of your project:
curl -o AGENTS.md https://raw.githubusercontent.com/BauplanLabs/bauplan-skills/main/CLAUDE.md
| Skill | Description |
|---|---|
bauplan-explore-data | Read-only exploration of lakehouse tables, schemas, and profiling |
bauplan-data-assessment | Assess whether a business question can be answered with available data |
bauplan-data-pipeline | Create data pipeline projects with SQL and Python models |
bauplan-safe-ingestion | Ingest data from S3 with branch isolation and quality checks (WAP) |
bauplan-debug-and-fix-pipeline | Diagnose and fix failed pipeline jobs |
bauplan-data-quality-checks | Generate data quality check code for pipelines and ingestion |
MIT
Quick insights from dlt pipeline data. Connect to a pipeline, profile tables, plan charts, and assemble marimo dashboards.
The most comprehensive SAP Datasphere plugin for Claude. 18 specialized skills covering exploration, data modeling, integration, BW Bridge migration, security architecture, CLI automation, business content activation, catalog governance, performance optimization, and troubleshooting — all through natural language. Powered by 45 MCP tools with enterprise-grade security.
DataHub development and interaction toolkit with connector planning, PR review, catalog search, metadata enrichment, lineage tracing, data quality management, and connection setup skills
Claude Code skill pack for Databricks (24 skills)
Share bugs, ideas, or general feedback.
Data analysis expert for SQL queries, BigQuery operations, and data insights. Use proactively for data analysis tasks and queries.
Data engineering and ETL tools. Includes 3 specialized agents, 4 commands, and 19 skills.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claim