schema-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…

npx skills add https://github.com/langchain-ai/deepagents --skill schema-exploration

Schema Exploration Skill

Workflow

1. List All Tables

Use sql_db_list_tables tool to see all available tables in the database.

This returns the complete list of tables you can query.

2. Get Schema for Specific Tables

Use sql_db_schema tool with table names to examine:

  • Column names - What fields are available
  • Data types - INTEGER, TEXT, DATETIME, etc.
  • Sample data - 3 example rows to understand content
  • Primary keys - Unique identifiers for rows
  • Foreign keys - Relationships to other tables

3. Map Relationships

Identify how tables connect:

  • Look for columns ending in "Id" (e.g., CustomerId, ArtistId)
  • Foreign keys link to primary keys in other tables
  • Document parent-child relationships

4. Answer the Question

Provide clear information about:

  • Available tables and their purpose
  • Column names and what they contain
  • How tables relate to each other
  • Sample data to illustrate content

Example: "What tables are available?"

Step 1: Use sql_db_list_tables

Response:

The Chinook database has 11 tables:
1. Artist - Music artists
2. Album - Music albums
3. Track - Individual songs
4. Genre - Music genres
5. MediaType - File formats (MP3, AAC, etc.)
6. Playlist - User-created playlists
7. PlaylistTrack - Tracks in playlists
8. Customer - Store customers
9. Employee - Store employees
10. Invoice - Customer purchases
11. InvoiceLine - Individual items in invoices

Example: "What columns does the Customer table have?"

Step 1: Use sql_db_schema with table name "Customer"

Response:

The Customer table has these columns:

- CustomerId (INTEGER) - Primary key, unique customer ID
- FirstName (NVARCHAR) - Customer's first name
- LastName (NVARCHAR) - Customer's last name
- Company (NVARCHAR) - Company name (optional)
- Address, City, State, Country, PostalCode - Location fields
- Phone (NVARCHAR) - Phone number
- Fax (NVARCHAR) - Fax number
- Email (NVARCHAR) - Email address
- SupportRepId (INTEGER) - Foreign key to Employee table

Sample data shows customers like:
- Luís Gonçalves from Brazil
- Leonie Köhler from Germany
- François Tremblay from Canada

Example: "How do I find revenue by artist?"

Step 1: Identify tables needed

  • Artist (has artist names)
  • Album (links artists to tracks)
  • Track (links albums to sales)
  • InvoiceLine (has sales data)
  • Invoice (has revenue totals)

Step 2: Map relationships

Artist (ArtistId)
  ↓ 1:many
Album (ArtistId, AlbumId)
  ↓ 1:many
Track (AlbumId, TrackId)
  ↓ 1:many
InvoiceLine (TrackId, UnitPrice, Quantity)

Response:

To find revenue by artist, you'll need to:
1. Start with the Artist table
2. JOIN to Album on ArtistId
3. JOIN to Track on AlbumId
4. JOIN to InvoiceLine on TrackId
5. SUM the revenue (UnitPrice * Quantity)
6. GROUP BY artist name

This requires the query-writing skill to execute.

Quality Guidelines

For "list tables" questions:

  • Show all table names
  • Add brief descriptions of what each contains
  • Group related tables (e.g., music catalog, transactions, people)

For "describe table" questions:

  • List all columns with data types
  • Explain what each column contains
  • Show sample data for context
  • Note primary and foreign keys
  • Explain relationships to other tables

For "how do I query X" questions:

  • Identify required tables
  • Map the JOIN path
  • Explain the relationship chain
  • Suggest next steps (use query-writing skill)

More skills from langchain-ai

langgraph-docs
langchain-ai
Access LangGraph documentation to build stateful agents and multi-agent workflows. Fetches official LangGraph Python docs covering state machines, graph-based agent design, and human-in-the-loop patterns Prioritizes relevant documentation by query type: implementation guides for how-to questions, concept pages for theory, tutorials for end-to-end examples, and API references for technical details Automatically selects 2–4 most relevant documentation URLs and retrieves their content to answer...
official
langgraph-human-in-the-loop
langchain-ai
Pause graph execution for human review, approval, or validation, then resume with their input. Requires three components: a checkpointer (InMemorySaver or PostgresSaver), a thread ID in config, and JSON-serializable interrupt payloads interrupt(value) pauses and surfaces data; Command(resume=value) resumes and returns that value to the paused node All code before interrupt() re-executes on resume, so side effects must be idempotent (use upsert, not insert) Supports approval workflows,...
official
web-research
langchain-ai
Use this skill for requests related to web research; it provides a structured approach to conducting comprehensive web research
official
langchain-oss-primer
langchain-ai
ALWAYS START HERE for any LangChain, Deep Agents, or LangGraph agent building project. Required starting point before choosing other skills or writing any…
official
skill-creator
langchain-ai
Guide for creating effective skills that extend agent capabilities with specialized knowledge, workflows, or tool integrations. Use this skill when the user…
official
social-media
langchain-ai
Drafts platform-specific social media posts with research-backed content and generated companion images. Supports LinkedIn posts (1,300 characters with professional tone) and Twitter/X threads (280 characters per tweet with 1/🧵 format) Requires delegating research to a subagent before writing, then reading findings to ensure accuracy and relevance Generates eye-catching social images automatically using generate_social_image tool with bold, high-contrast compositions optimized for small...
official
deep-agents-memory
langchain-ai
Pluggable memory and file backends for Deep Agents with ephemeral, persistent, and hybrid routing options. Four backend types: StateBackend (thread-scoped, ephemeral), StoreBackend (cross-session persistent), FilesystemBackend (real disk access for local dev), and CompositeBackend (route different paths to different backends) FilesystemMiddleware provides six file operation tools: ls , read_file , write_file , edit_file , glob , grep CompositeBackend uses longest-prefix matching to route...
official
deep-agents-orchestration
langchain-ai
Orchestrate subagents, plan multi-step tasks, and require human approval for sensitive operations. Delegate work to specialized subagents via the task tool; custom subagents support isolated tool sets and system prompts, while the default "general-purpose" subagent inherits main agent configuration Plan and track complex workflows with write_todos , organizing tasks across pending, in-progress, and completed states; requires a thread_id for persistence across invocations Implement...
official