database-architect

Expert database architect specializing in data layer design from scratch, technology selection, schema modeling, and scalable database architectures. Masters SQL/NoSQL/TimeSeries database selection, normalization strategies, migration planning, and performance-first design. Handles both greenfield architectures and re-architecture of existing systems. Use PROACTIVELY for database architecture, technology selection, or data modeling decisions.

Quality

55%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/database-architect/SKILL.md

The canonical home for this skill is jbvc/database-architect

Quality

Content

17%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body reads as an encyclopedic capability catalog rather than actionable skill instructions: it re-states database knowledge Claude already has, offers no executable code or commands, and packs all reference material into one file. Workflow sequencing exists but lacks validation feedback loops for risky database operations.

Suggestions

Strip conceptual enumerations Claude already knows (index types, ACID, isolation levels, ORM lists) and replace them with a concise decision workflow plus 1-2 executable templates (e.g., a Mermaid ERD skeleton, a zero-downtime migration checklist with validation steps).

Move the long technology/category catalogs into a references file (e.g., references/tech-selection.md) and keep SKILL.md as a lean overview that links out one level deep.

Add explicit validation checkpoints to the migration/schema-change workflow (validate in staging → rollback triggers → only proceed on success) to lift workflow clarity.

Dimension	Reasoning	Score
Conciseness	The ~255-line body is a dense catalog of capabilities, technology lists, and conceptual enumerations Claude already knows (e.g., B-tree/Hash/GiST indexes, ACID properties, isolation levels) — heavy padding with no executable artifacts that earn their tokens.	1 / 3
Actionability	Almost entirely descriptive lists with no executable code, commands, or copy-paste-ready guidance; even migration/schema sections enumerate concepts rather than instruct, leaving Claude without concrete actions.	1 / 3
Workflow Clarity	The 'Instructions' and 'Response Approach' sections give a numbered sequence, but destructive/batch database operations (migrations, schema changes) lack explicit validate→fix→retry checkpoints, capping the score per the rubric.	2 / 3
Progressive Disclosure	Content is organized into clearly labeled sections, but everything lives inline in one monolithic file with no bundle files or one-level-deep references to split the heavy reference material, so navigation/discovery is limited.	2 / 3
	Total	6 / 12 Passed

Description

92%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, concrete description with explicit 'Use PROACTIVELY' trigger guidance and good keyword coverage. Its main weakness is broad scope that overlaps with sibling database skills, slightly raising conflict risk.

Suggestions

Sharpen the trigger clause to distinguish from database-optimizer/database-admin (e.g., 'Use for greenfield data layer design or re-architecture, NOT for query tuning or operations').

Consider leading with the highest-signal concrete verbs so the core action is unambiguous before the breadth of sub-capabilities.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: 'data layer design from scratch, technology selection, schema modeling, and scalable database architectures' plus 'normalization strategies, migration planning, and performance-first design' — clearly concrete rather than vague.	3 / 3
Completeness	Explicitly answers both what (architecture/design tasks) and when via 'Use PROACTIVELY for database architecture, technology selection, or data modeling decisions', matching the anchor for explicit triggers.	3 / 3
Trigger Term Quality	Covers natural terms users would say — 'database architecture, technology selection, or data modeling decisions' — with strong keyword coverage (SQL/NoSQL/TimeSeries, schema, migrations).	3 / 3
Distinctiveness Conflict Risk	The niche is reasonably distinct (architecture/design over tuning/ops), but 'database architecture, technology selection, or data modeling decisions' is broad enough to overlap with database-optimizer, database-admin, and backend-architect, so it could trigger for adjacent skills.	2 / 3
	Total	11 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: rmyndharis/antigravity-skills
Path: skills/database-architect/SKILL.md
Commit: e63f7dd

Reviewed: about 5 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.