data-inspect
/data-inspect
Show the active dataset's schema — tables, columns, row counts, and relationships. Optionally drill into a specific table. Use this skill whenever the user invokes `/data` or `/data {table}`, or asks questions like "what tables do I have?", "show me the schema", "what's in this dataset?", "what columns are in the users table?", "show me table structure", "list tables", "describe the data", "what's in my database?", or any request to inspect, browse, or understand the structure of the active dataset. Also trigger when users mention "schema", "columns", "tables", "data dictionary", "data structu
- Author
- ai-analyst-lab ↗
- Repository
- ai-analyst ↗
- Licence
- MIT
- Last repository change
- 30.09.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 30.09.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Show the active dataset's schema — tables, columns, row counts, and relationships. Optionally drill into a specific table. Use this skill whenever the user invokes `/data` or `/data {table}`, or asks questions like "what tables do I have?", "show me the schema", "what's in this dataset?", "what columns are in the users table?", "show me table structure", "list tables", "describe the data", "what's in my database?", or any request to inspect, browse, or understand the structure of the active dataset. Also trigger when users mention "schema", "columns", "tables", "data dictionary", "data structu
Triggers from the description
Original author description
Show the active dataset's schema — tables, columns, row counts, and relationships. Optionally drill into a specific table. Use this skill whenever the user invokes `/data` or `/data {table}`, or asks questions like "what tables do I have?", "show me the schema", "what's in this dataset?", "what columns are in the users table?", "show me table structure", "list tables", "describe the data", "what's in my database?", or any request to inspect, browse, or understand the structure of the active dataset. Also trigger when users mention "schema", "columns", "tables", "data dictionary", "data structu
How it works
- Purpose
- When to Use
- Instructions
- Anti-Patterns
SKILL.md preview
---
name: data-inspect
description: |
Show the active dataset's schema — tables, columns, row counts, and relationships. Optionally drill into a specific table. Use this skill whenever the user invokes `/data` or `/data {table}`, or asks questions like "what tables do I have?", "show me the schema", "what's in this dataset?", "what columns are in the users table?", "show me table structure", "list tables", "describe the data", "what's in my database?", or any request to inspect, browse, or understand the structure of the active dataset. Also trigger when users mention "schema", "columns", "tables", "data dictionary", "data structure", or when they need to understand what data they're working with before starting an analysis. This is a foundational command that should be offered proactively when users seem unsure about available data or table structure. DISAMBIGUATION: this is the `/data` SCHEMA inspector (structure — tables, columns, types, row counts). For a dataset-wide health + relationships overview ("tell me about this data"), use `data-map`; for interactive browsing/sampling, use `/explore`; for deep statistical profiling (distributions, anomalies), use `data-profiling`.
---
# Skill: Data Inspect
## Purpose
Show the active dataset's schema — tables, columns, row counts, and relationships. Optionally drill into a specific table.
## When to Use
Invoke as `/data` to see the full schema summary, or `/data {table}` to see column details for a specific table.
## Instructions
### Start here
**Before doing ANYTHING else:**
1. Read `.knowledge/active.yaml` to determine the active dataset name
2. If no active dataset exists, jump to Mode 3 (No Active Dataset)
3. Otherwise, read `.knowledge/datasets/{active}/schema.md` for schema information
**Why this matters:** Users often have multiple datasets connected. You MUST use the active one from the config file, never guess or use a different dataset.
---
### Mode 1: `/data` (full schema overview)
**When:** User invokes `/data` or asks "what tables do I have?" / "show me the schema"
**Steps:**
1. ✅ Confirm you've already read `.knowledge/active.yaml` and `schema.md` (see above)
2. Extract from schema.md:
- Dataset display name
- Connection type and location
- Table list with: name, row count, column count, primary key
3. Display in this condensed format:
```
Active Dataset: {display_name}
Connection: {type} ({database}.{schema} or file path)
Tables:
users ~50,000 rows 8 columns user_id (PK)
products 500 rows 7 columns product_id (PK)
events ~6.5M rows 9 columns event_id (PK)
sessions ~1.4M rows 8 columns session_id (PK)
orders ~30-50K rows 6 columns order_id (PK)
order_items — rows 4 columns order_id + product_id (composite PK)
Use `/data {table}` for column details.
```
**Format notes:**
- Left-align table names
- Show approximate row counts (use `~` for estimates)
- Show column count
- Show primary key or composite key
- Keep it visually scannable — this is a quick reference, not exhaustive detail
---
### Mode 2: `/data {table}` (table detail)
**When:** User invokes `/data {table}` or asks "what columns are in X?" / "show me the X table structure"
**Steps:**
1. ✅ Confirm you've already read `.knowledge/active.yaml` and `schema.md` (see above)
2. Find the section for the requested table in schema.md
3. **If table doesn't exist:** Jump to Mode 4 (Table Not Found)
4. **If table exists:** Display:
- Table name and description
- Row count
- Full column listing: name, type, nullable, description
- Primary key(s)
- Foreign key relationships (both FROM this table and TO this table)
- Any important notes about the table (grain, completeness, quirks)
**Format example:**
```
Active Dataset: {dataset_name}
Table: users
Description: User dimension table with demographics and signup info
Row count: ~25,000 rows
Primary Key: user_id
Columns:
user_id BIGINT NOT NULL Unique user identifier
email VARCHAR NOT NULL User email address
signup_date DATE NULL Date user first registered
country VARCHAR NULL User's country
membership_tier VARCHAR NULL Premium, Standard, Free
Relationships:
← orders.customer_id (one user, many orders)
← events.user_id (one user, many events)
→ memberships.user_id (join for membership details)
Use `/data {another_table}` to inspect another table.
```
---
### Mode 3: No Active Dataset
**When:** `.knowledge/active.yaml` has no `active_dataset` field OR the dataset directory doesn't exist
**Display:**
```
No active dataset configured.
To get started:
• Run `/connect-data` to connect a new dataset
• Run `/datasets` to see all available datasets
• Run `/switch-dataset {name}` to activate an existing dataset
```
**Do NOT:** Try to query databases, load CSV files, or guess which data source to use. Without an active dataset, halt and prompt the user.
---
### Mode 4: Table Not Found
**When:** User requests `/data {table}` but the table doesn't exist in the active dataset's schema.md
**Steps:**
1. Confirm the table truly doesn't exist (check schema.md thoroughly, look for typos/case differences)
2. Display a helpful error message:
```
Table '{table}' not found in {dataset_name}.
Available tables:
users, orders, products, events, sessions
Did you mean:
• /data {closest_match}
• /switch-dataset {other_dataset} if you're looking for different data
• /connect-data if the table should exist but isn't loaded
Use `/data` to see the full schema.
```
**Do NOT:** Query databases or try to load data from other sources. The skill reads from cached schema files only.
## Anti-Patterns
1. **Never query the database just to show schema** — read from the cached schema.md file for speed. Schema files are pre-generated during dataset connection and profiling.
2. **Never show the full schema.md raw** — always format into the condensed table view. Users want quick scannable reference, not walls of markdown.
3. **Read `.knowledge/active.yaml` first** — users often have several datasets connected, and the active pointer is the only source of truth for which one to show.
4. **Never query actual data** — this skill shows structure only (schema, relationships). For data exploration, use the `/explore` skill or Data Explorer agent.
5. **Never fabricate table information** — if schema.md doesn't have row counts, say "~rows not profiled". If descriptions are missing, show what's available. Don't make up details.
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · ai-analyst-lab/ai-analyst | 87 | MIT |
| ai-analyst-lab/ai-analyst-plugin | 100 | MIT |
Database snapshot: 13.11.2026 · package version 95d17409437a (SHA-256 digest of the entire package)
Downloads in the last 30 days: 1 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 87explore
Quick, interactive data exploration without the full pipeline. Use this skill whenever a user wants to explore data, understand what's in a dataset, browse tables or columns, check data distributions, spot patterns, or get familiar with data before analysis. Trigger on phrases… - 100data-map
Produce a cross-table data health map for the active dataset: row counts, date alignment, join rates, relationships, opening hypothesis. Trigger on dataset-wide open questions: "tell me about this data", "what's in here", "give me an overview", "map out the data", "what do I… - 100profiling-tables
Deep-dive data profiling for a specific table. Use when the user asks to profile a table, wants statistics about a dataset, asks about data quality, or needs to understand a table's structure and content. Requires a table name. - 100flux-schema
Design and build database schema — tables, columns, types, indexes, constraints, relationships. Given a domain description, output the schema and write the files. Use when asked to "design schema", "database design", "create tables", or "data model". - 90explore
Use when the user wants to discover, find, or browse data assets in the Alation catalog, data products, or marketplaces. Triggers: search catalog, find tables, list data sources, browse schemas, show columns, what data do we have, what tables exist, explore database, describe… - 100schema-exploration
Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks about database schema, table structure, column types, what tables exist, ERD, foreign keys, or how entities relate.