# Document Dataset

> A Claude skill from dremio/cli.

- **Type:** Skill
- **Install:** `agentstack add skill-dremio-cli-document-dataset`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [dremio](https://agentstack.voostack.com/s/dremio)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** Apache-2.0
- **Upstream author:** [dremio](https://github.com/dremio)
- **Source:** https://github.com/dremio/cli/tree/main/plugins/dremio/skills/document-dataset

## Install

```sh
agentstack add skill-dremio-cli-document-dataset
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

---
name: document-dataset
description: Generate a comprehensive markdown documentation card for a Dremio dataset
user_invocable: true
triggers:
  - "document dataset"
  - "describe table"
  - "dataset documentation"
  - "data dictionary"
  - "what is this table"
  - "table info"
---

# Document Dataset

Generate a complete documentation card for a Dremio dataset including schema, lineage, sample data, and metadata.

## Agent Rules

- Use `--fields` to reduce output size (e.g., `drs schema describe  --fields columns.name,columns.type`)
- Use `drs describe ` to check parameter schemas before calling unfamiliar commands
- Paths must be dot-separated; quote components containing dots: `"my.source".table`

## Step 1: Get Column Schema

```bash
drs schema describe 
```

This returns:
- Column names and data types
- Nullable flags
- Nested/complex type structures (LIST, STRUCT, MAP)

Record every column — this forms the core of the documentation card.

## Step 2: Get Lineage

```bash
drs schema lineage 
```

This shows:
- **Upstream dependencies** — source tables and views this dataset reads from
- **Downstream dependents** — views and reflections built on top of this dataset
- **Transformation chain** — the path from raw sources to this dataset

## Step 3: Get Sample Data

```bash
drs schema sample 
```

This returns a small set of representative rows. Use this to:
- Understand actual data formats (date patterns, enum values, ID formats)
- Identify columns that are mostly null or have unexpected values
- Show realistic examples in the documentation

## Step 4: Get Wiki and Tags

```bash
drs schema wiki 
```

This returns:
- **Wiki content** — user-authored descriptions attached to the dataset in Dremio
- **Tags/labels** — categorization tags applied in the Dremio catalog

## Step 5: Check Reflections

```bash
drs reflect list 
```

Document any reflections:
- Reflection type (raw vs aggregate)
- Status (active, refreshing, failed)
- Columns included
- Refresh schedule

## Step 6: Assemble the Documentation Card

Combine all gathered information into a markdown card with this structure:

```markdown
# 

**Path:** ``
**Source:** 
**Tags:** 

## Description

## Schema

| Column | Type | Nullable | Description |
|--------|------|----------|-------------|
|  |  |  |  |
|  |  |  |  |

## Sample Data

## Lineage

**Upstream:** 
**Downstream:** 

## Reflections

| Name | Type | Status | Columns |
|------|------|--------|---------|
|  | raw/agg | active |  |

## Notes

- 
```

## Tips

- For **nested types** (STRUCT, LIST), expand sub-fields in the schema table with dot notation: `address.city`, `address.zip`.
- For **large tables** (100+ columns), group columns by prefix or functional area.
- If sample data reveals **PII** (emails, phone numbers, SSNs), note this in the documentation and flag for the data owner.
- Cross-reference with `drs access grants ` if the user wants access info included.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [dremio](https://github.com/dremio)
- **Source:** [dremio/cli](https://github.com/dremio/cli)
- **License:** Apache-2.0

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-dremio-cli-document-dataset
- Seller: https://agentstack.voostack.com/s/dremio
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.