# motherduck-enable-self-serve-analytics
> Roll out governed MotherDuck analytics to internal teams, choosing trusted datasets, access boundaries, and owners.
Roll out governed MotherDuck analytics to internal teams, choosing trusted datasets, access boundaries, and owners.

[Use-case skill](/sql-reference/agent-skills/#use-case-skills) · [View source on GitHub](https://github.com/motherduckdb/agent-skills/tree/v3.0.0/skills/motherduck-enable-self-serve-analytics)

:::info

This page shows the skill's `SKILL.md`: the instructions a coding agent loads when a task matches the description above. To install every MotherDuck skill in Claude Code, Codex, Cursor, or Gemini CLI, see [Install MotherDuck Skills](/key-tasks/ai-and-motherduck/agent-skills/). To install only this skill with the [Skills CLI](https://github.com/vercel-labs/skills), run:

```bash
npx -y skills add motherduckdb/agent-skills --skill motherduck-enable-self-serve-analytics --yes --global
```

This skill relies on [`motherduck-connect`](/sql-reference/agent-skills/motherduck-connect/), [`motherduck-explore`](/sql-reference/agent-skills/motherduck-explore/), [`motherduck-query`](/sql-reference/agent-skills/motherduck-query/), [`motherduck-model-data`](/sql-reference/agent-skills/motherduck-model-data/), [`motherduck-create-dive`](/sql-reference/agent-skills/motherduck-create-dive/), [`motherduck-share-data`](/sql-reference/agent-skills/motherduck-share-data/), [`motherduck-manage-guides`](/sql-reference/agent-skills/motherduck-manage-guides/), and [`motherduck-security-governance`](/sql-reference/agent-skills/motherduck-security-governance/). Install those too, or install the full catalog.

:::

## Start here: Is a MotherDuck server active?

Use an active remote MotherDuck MCP server or local MotherDuck server to inspect the in-scope database, schema, grain, keys, and relevant metrics. Reuse known context and narrow discovery to the requested work; do not scan the whole workspace by default. Let the actual data model shape the result.

Resolve the target from the request or active context. Ask only if ambiguity materially affects the result. Without a server, use supplied schema and explicit assumptions for planning; do not imply live validation.

## Rollout defaults

- first audience first, not company-wide exposure
- curated dataset before broad access
- Dive or share boundary over raw table dumping
- standard ownership for metric changes
- lightweight metric definitions and owners before inviting more users
- a short root orientation Guide plus shallow domain Guides for definitions that agents cannot infer from schema
- team access as custom roles that inherit `explorer` or `builder`, with share grants to the role (archetypes 4 and 5 in [`motherduck-security-governance`](/sql-reference/agent-skills/motherduck-security-governance/))
- restricted Shares granted to roles; use include patterns for table/view subsets and secure views (keyed on `current_email()` or `is_role_in_session()`) for per-team rows, hidden columns, or masked values, instead of one Share per audience
- Dives as the consumption surface, with the Dive's AI Chat (Agent Chat) for follow-up questions on a governed Dive; Admins can turn it off on the AI Features settings page
- roles, grants, and Shares managed as code with the Terraform provider once the rollout pattern is stable

## Workflow

1. Inspect the available MotherDuck server or supplied schema context.
2. Inspect the data model that internal teams would use.
3. Pick the first audience and first use case.
4. Publish one trusted dataset.
5. When Guide maintenance is in scope, create or update the relevant Guide with the metric owner, validated definition, join rules, and referenced objects.
6. Publish one Ready Dive or one restricted, role-granted Share.
7. Audit the live roles, grants, and exposed catalog.
8. Expand only after the first workflow is stable.

Match execution to the request: answer, review, or planning work returns the requested rollout artifacts; build or change work creates the requested in-scope dataset, Dive, or share and validates it. Ask before broader access grants, destructive changes, or external writes not already authorized.

When this skill produces a native DuckDB (`md:`) connection, watermark it with `custom_user_agent=agent-skills/3.0.0(harness-<harness>;llm-<llm>)`. If metadata is missing, fall back to `harness-unknown` and `llm-unknown`.

## Output

For a full engagement, cover the following as relevant to the request:

- the first audience
- the first asset
- the governing dataset
- the ownership model
- the rollout guardrails

For explicit structured JSON requests, read [the output contract](https://github.com/motherduckdb/agent-skills/blob/v3.0.0/skills/motherduck-enable-self-serve-analytics/references/EXECUTION_REFERENCE.md#structured-output). Otherwise use the format that fits the requested deliverable.

## References

Read only the sections relevant to the task; these are guidance, not a mandatory itinerary.

- [`references/SELF_SERVE_ROLLOUT_GUIDE.md`](https://github.com/motherduckdb/agent-skills/blob/v3.0.0/skills/motherduck-enable-self-serve-analytics/references/SELF_SERVE_ROLLOUT_GUIDE.md) -- curate-publish-expand sequence, Dive-versus-share choice, data freshness checks, scale guidance, and starter snippets

## Examples

Read [the execution reference](https://github.com/motherduckdb/agent-skills/blob/v3.0.0/skills/motherduck-enable-self-serve-analytics/references/EXECUTION_REFERENCE.md) only to run the bundled examples or reproduce their validation.

- [self_serve_rollout_example.py](https://github.com/motherduckdb/agent-skills/blob/v3.0.0/skills/motherduck-enable-self-serve-analytics/artifacts/self_serve_rollout_example.py)
- [self_serve_rollout_example.ts](https://github.com/motherduckdb/agent-skills/blob/v3.0.0/skills/motherduck-enable-self-serve-analytics/artifacts/self_serve_rollout_example.ts)

## Related skills

Load related skills only for missing capabilities; reuse established context.

- [`motherduck-explore`](/sql-reference/agent-skills/motherduck-explore/) -- inspect the real workspace before rollout
- [`motherduck-query`](/sql-reference/agent-skills/motherduck-query/) -- validate KPI definitions
- [`motherduck-model-data`](/sql-reference/agent-skills/motherduck-model-data/) -- publish curated analytical views or tables
- [`motherduck-create-dive`](/sql-reference/agent-skills/motherduck-create-dive/) -- build the first shareable answer surface
- [`motherduck-manage-guides`](/sql-reference/agent-skills/motherduck-manage-guides/) -- preserve governed metric and join context for agents
- [`motherduck-share-data`](/sql-reference/agent-skills/motherduck-share-data/) -- publish table/view subsets and role-granted access
- [`motherduck-security-governance`](/sql-reference/agent-skills/motherduck-security-governance/) -- design roles, grants, and secure-view policy

## Files in this skill

The agent reads these files when the instructions above point to them.

- [`artifacts/self_serve_rollout_example.py`](https://github.com/motherduckdb/agent-skills/blob/v3.0.0/skills/motherduck-enable-self-serve-analytics/artifacts/self_serve_rollout_example.py)
- [`artifacts/self_serve_rollout_example.ts`](https://github.com/motherduckdb/agent-skills/blob/v3.0.0/skills/motherduck-enable-self-serve-analytics/artifacts/self_serve_rollout_example.ts)
- [`references/EXECUTION_REFERENCE.md`](https://github.com/motherduckdb/agent-skills/blob/v3.0.0/skills/motherduck-enable-self-serve-analytics/references/EXECUTION_REFERENCE.md)
- [`references/SELF_SERVE_ROLLOUT_GUIDE.md`](https://github.com/motherduckdb/agent-skills/blob/v3.0.0/skills/motherduck-enable-self-serve-analytics/references/SELF_SERVE_ROLLOUT_GUIDE.md)

## Docs this skill draws on

- [Creating Visualizations with Dives](https://motherduck.com/docs/key-tasks/dives/)
- [Sharing concepts and overview](https://motherduck.com/docs/key-tasks/sharing-data/sharing-overview/)
- [Using Guides to improve AI query accuracy and personalize agents](https://motherduck.com/docs/key-tasks/guides/)
- [motherduck.com/product/pricing](https://motherduck.com/product/pricing/)


---

## 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%2Fmotherduck-enable-self-serve-analytics%2F&page_title=motherduck-enable-self-serve-analytics&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.
