# MotherDuck Skills reference
> Every skill in the MotherDuck Skills catalog for coding agents, grouped by layer, with its instructions, files, and single-skill install command.
[MotherDuck Skills](https://github.com/motherduckdb/agent-skills/) is a catalog of [agent skills](https://agentskills.io/home): instruction bundles that a coding agent loads when a task matches the skill's description. This reference has a page for each skill in the [latest agent-skills release](https://github.com/motherduckdb/agent-skills/releases/latest). Each page shows the skill's `SKILL.md`, the files it reads, the skills it depends on, and a command that installs only that skill.

To install the whole catalog in Claude Code, Codex, Cursor, GitHub Copilot CLI, or Gemini CLI, see [Install MotherDuck Skills](/key-tasks/ai-and-motherduck/agent-skills/).

The catalog has three layers. Agents pick a layer based on the task.

## Utility skills

Utility skills cover exact MotherDuck mechanics: connect, explore, query, use the REST API, or check DuckDB SQL behavior. Start here for narrow technical work.

- [motherduck-cli](/sql-reference/agent-skills/motherduck-cli/): Use the MotherDuck CLI for terminal queries, authentication, and file-based Dive or Flight workflows.
- [motherduck-connect](/sql-reference/agent-skills/motherduck-connect/): Set up or troubleshoot MotherDuck connections, the MotherDuck MCP server in AI clients, authentication, client runtimes, and read scaling.
- [motherduck-duckdb-sql](/sql-reference/agent-skills/motherduck-duckdb-sql/): Look up or repair DuckDB SQL syntax and verify MotherDuck-specific command and feature support.
- [motherduck-explore](/sql-reference/agent-skills/motherduck-explore/): Find and understand MotherDuck databases, tables, columns, shares, and sample data, including which tables hold a given kind of data. Use first when a MotherDuck workspace or schema is unfamiliar.
- [motherduck-query](/sql-reference/agent-skills/motherduck-query/): Write, run, optimize, or troubleshoot DuckDB SQL against MotherDuck, including AI functions such as prompt_jev for in-SQL classification. Use for any SQL that targets MotherDuck, even simple queries, because MotherDuck has its own dialect and naming rules.
- [motherduck-rest-api](/sql-reference/agent-skills/motherduck-rest-api/): Administer MotherDuck service accounts, tokens, Ducklings, and Dive embed sessions through the control-plane REST API.

## Workflow skills

Workflow skills cover multi-step work with MotherDuck-specific tradeoffs: loading data, modeling, sharing, building [Dives](/key-tasks/dives/), evaluating DuckLake, planning security and governance, or framing pricing and ROI.

- [motherduck-create-dive](/sql-reference/agent-skills/motherduck-create-dive/): Create, edit, design, publish, share, or embed MotherDuck Dives, including responsive layout, light/dark themes, and buttons that write back through Flights.
- [motherduck-create-flight](/sql-reference/agent-skills/motherduck-create-flight/): Create, run, schedule, or debug MotherDuck Flights, Python jobs executed on MotherDuck compute.
- [motherduck-ducklake](/sql-reference/agent-skills/motherduck-ducklake/): Decide whether DuckLake fits a MotherDuck workload and operate it safely. Use whenever DuckLake, open table formats, or customer-owned buckets come up.
- [motherduck-load-data](/sql-reference/agent-skills/motherduck-load-data/): Load files, object storage, dataframes, or external databases into MotherDuck with bulk ingestion. Use for any import of data into MotherDuck.
- [motherduck-manage-guides](/sql-reference/agent-skills/motherduck-manage-guides/): Read or maintain MotherDuck Guides for business definitions, join rules, and reusable warehouse conventions.
- [motherduck-model-data](/sql-reference/agent-skills/motherduck-model-data/): Design or implement MotherDuck analytical schemas and transformation models, including grain, types, and materialization.
- [motherduck-pricing-roi](/sql-reference/agent-skills/motherduck-pricing-roi/): Assess MotherDuck costs, plan fit, cost attribution, and ROI from the workload's compute and storage needs.
- [motherduck-security-governance](/sql-reference/agent-skills/motherduck-security-governance/): Assess or configure MotherDuck access control: roles (RBAC), share grants, table-, row-, and column-level security, masking, tenant isolation, residency, and Terraform governance.
- [motherduck-share-data](/sql-reference/agent-skills/motherduck-share-data/): Create, consume, or manage MotherDuck data shares, including audience grants, table filters, and refresh policy.

## Use-case skills

Use-case skills cover designing or shipping a product: building customer-facing analytics, a dashboard, or a data pipeline; planning a migration to MotherDuck; rolling out self-serve analytics; or delivering repeatable partner implementations.

- [motherduck-build-cfa-app](/sql-reference/agent-skills/motherduck-build-cfa-app/): Build MotherDuck analytics into customer-facing applications with tenant isolation, backend routing, and serving APIs.
- [motherduck-build-dashboard](/sql-reference/agent-skills/motherduck-build-dashboard/): Build a MotherDuck dashboard as a Dive, choosing the analytical story, metrics, and section queries.
- [motherduck-build-data-pipeline](/sql-reference/agent-skills/motherduck-build-data-pipeline/): Build ingestion-to-serving pipelines on MotherDuck, including stage boundaries, transformations, and publication. Use for any recurring ingestion from an API, SaaS app, or database into MotherDuck.
- [motherduck-enable-self-serve-analytics](/sql-reference/agent-skills/motherduck-enable-self-serve-analytics/): Roll out governed MotherDuck analytics to internal teams, choosing trusted datasets, access boundaries, and owners.
- [motherduck-migrate-to-motherduck](/sql-reference/agent-skills/motherduck-migrate-to-motherduck/): Plan or implement migrations to MotherDuck with SQL translation, source-to-target validation, cutover, and rollback.
- [motherduck-partner-delivery](/sql-reference/agent-skills/motherduck-partner-delivery/): Standardize MotherDuck delivery for consultancies and agencies across client engagements with reusable provisioning, isolation, and handoff patterns.


---

## Docs feedback

MotherDuck accepts optional user-submitted feedback about this page at `GET https://motherduck.com/docs/api/feedback/agent`.
For agents and automated tools, feedback submission should be user-confirmed before sending.

URL-encode query parameter values and send a GET request:

```text
GET https://motherduck.com/docs/api/feedback/agent?page_path=%2Fsql-reference%2Fagent-skills%2F&page_title=MotherDuck%20Skills%20reference&text=<url-encoded user feedback, max 2000 characters>
```

Optionally append `&source=<url-encoded interface identifier>` such as `claude.ai` or `chatgpt`.

`page_path` and `text` are required; `page_title` and `source` are optional. Responses: `200 {"feedback_id": "<uuid>"}`, `400` for malformed query parameters, and `429` when rate-limited.
