database-architect — Claude Code skill: what it does, how to install
Turns Claude Code into a database architect for greenfield and legacy systems. It guides database selection, schema design, partitioning, and safe migration plans.
npx claude-code-templates@latest --skill database/database-architectWhat database-architect does
The skill guides Claude Code through a structured four-step process for data layer architecture. First, the agent collects access patterns, domain entities, and anticipated scale. Then it recommends database engines, covering relational systems like PostgreSQL, time-series engines like ClickHouse, or graph databases. Finally, it designs table structures and indexing strategies.
Built-in safety rules enforce rollback plans and backups before any destructive migration takes place. Staging validation is mandatory. Attempting to use this skill for tuning an isolated query without schema permissions fails to deliver value: its workflows assume the data model can change. The logic covers partitioning, normalization trade-offs, and multi-tenant storage.
What it helps with
- select the right database engine for specific workload patterns
- design normalized or denormalized schemas with constraints
- define composite, partial, and full-text indexing strategies
- plan staging-validated database migrations with rollback paths
Example prompts for the agent
- Design a PostgreSQL schema for an e-commerce platform handling high read volume, including partition and index plans
- Evaluate whether to use ClickHouse or TimescaleDB for telemetry data and propose the table structure
- Draft a zero-downtime migration strategy with rollback steps to transition our document store to PostgreSQL
How to install database-architect
1claude-code-templates
npx claude-code-templates@latest --skill database/database-architect2Skills CLI (Vercel)
npx skills add davila7/claude-code-templates --skill database-architect -a claude-code3Manually: put the files in place
~/.claude/skills/database-architect/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/database-architect/
Manually: put the files in place
.agents/skills/database-architect/SKILL.mdFor all projects use ~/.agents/skills/
Manually: put the files in place
.cursor/skills/database-architect/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install davila7/claude-code-templates database-architect2Manually: put the files in place
.github/skills/database-architect/SKILL.mdPlatform CLI
gemini skills install https://github.com/davila7/claude-code-templates --path cli-tool/components/skills/database/database-architectManually: put the files in place
.devin/skills/database-architect/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about database-architect
How to install database-architect in Claude Code?
Run npx skills add davila7/claude-code-templates --skill database-architect -a claude-code in your terminal. This downloads and registers the skill in Claude Code.
What does the database-architect skill do?
It assists with selecting database engines, modeling conceptual and physical schemas, configuring indexing, and designing caching layers. It also creates migration workflows complete with backup and rollback strategies.
When should you avoid using database-architect?
Do not use it if you only need isolated query tuning without permission to alter schemas or infrastructure. It is also not meant for designing application-level feature code.
