data-inspect

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

CRITICAL: Always 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"