Claude Skill

database-explorer

Explore PostgreSQL, MySQL, MongoDB, Redis, and SQLite schemas and sample data safely (read-first). Use when understanding data models or diagnosing query issues.

LLM Mart · 0 points · 0 0 0

Virus-scanned Reviewed automatically before listing.

Full trust report

Download navinspire-ia-navin-navin_skills_database-explorer-e9c73a3.zip · 0 KB

navinspire-ia/navin 31 4 forks AGPL-3.0 Updated 4d ago

Part of navinspire-ia/navin — 182 skills

Install

skills CLI npx skills add https://github.com/Navinspire-ia/navin/tree/main/navin/skills/database-explorer

Claude Code claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install navinspire-ia-navin@llmmart

Git git clone https://github.com/Navinspire-ia/navin.git

The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole navinspire-ia/navin collection as a plugin from our marketplace. Git is the plain clone.

Skill manifest

Database Explorer

Overview

Map schemas before writing queries. Prefer read-only roles and limits.

Tools

Prefer the built-in db_query tool: it queries SQLite files in the workspace directly (sqlite_path) and named connections (PostgreSQL, Supabase, MySQL, MariaDB) configured under tools.database.connections. Connections are read-only unless allowWrites is set. Fall back to CLI clients (psql, mysql, sqlite3) or MCP servers only when a connection is not configured.

Workflow

Identify engine + connection method (db_query connection, CLI, URL in env, MCP Supabase, etc.).
List databases/schemas/tables - never dump entire prod tables.
Sample with LIMIT / projections; avoid SELECT * on huge tables.
Summarize: entities, keys, relations, row-count estimates.
Flag PII columns; do not paste sensitive rows into chat.

Rules

Writes/DDL on shared DBs need human-approval.
Credentials from env/secret stores only (secrets-manager).

Files (navin)

SKILL.md 1.2 KB

---
name: database-explorer
description: Explore PostgreSQL, MySQL, MongoDB, Redis, and SQLite schemas and sample data safely (read-first). Use when understanding data models or diagnosing query issues.
metadata: {"navin":{"emoji":"🗄️","category":"data"}}
---

# Database Explorer

## Overview

Map schemas before writing queries. Prefer read-only roles and limits.

## Tools

Prefer the built-in `db_query` tool: it queries SQLite files in the workspace directly (`sqlite_path`) and named connections (PostgreSQL, Supabase, MySQL, MariaDB) configured under `tools.database.connections`. Connections are read-only unless `allowWrites` is set. Fall back to CLI clients (psql, mysql, sqlite3) or MCP servers only when a connection is not configured.

## Workflow

1. Identify engine + connection method (`db_query` connection, CLI, URL in env, MCP Supabase, etc.).
2. List databases/schemas/tables - never dump entire prod tables.
3. Sample with `LIMIT` / projections; avoid `SELECT *` on huge tables.
4. Summarize: entities, keys, relations, row-count estimates.
5. Flag PII columns; do not paste sensitive rows into chat.

## Rules

- Writes/DDL on shared DBs need `human-approval`.
- Credentials from env/secret stores only (`secrets-manager`).