database-architect

Expert database architect specializing in data layer design from scratch, technology selection, schema modeling, and scalable database architectures.

Quality

24%

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 database-architect in rmyndharis/antigravity-skills

Quality

Content

13%Scale 1-5

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

This skill reads like a comprehensive resume or knowledge base dump rather than actionable instructions for Claude. It spends the vast majority of its token budget listing technologies and concepts Claude already knows, while providing almost no concrete examples, executable code, or specific workflows. The content would benefit enormously from being reduced to ~50 lines of actionable guidance with concrete examples.

Suggestions

Remove the entire 'Capabilities' section (or move to a separate reference file) — Claude already knows what PostgreSQL, B-tree indexes, and ACID properties are. Replace with specific decision frameworks or heuristics Claude wouldn't know.

Add concrete, executable examples: a sample schema design output, a migration script template, a technology selection decision matrix with specific thresholds (e.g., 'if write-heavy >10K TPS, consider X over Y').

Add explicit validation checkpoints to the workflow, especially for migration planning: backup verification, staging validation, rollback testing, data integrity checks with specific commands or queries.

Restructure as a concise overview (~50-80 lines) with clear references to bundle files for detailed content like technology comparison matrices, schema design patterns, and migration checklists.

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~300+ lines. Extensively lists concepts Claude already knows (ACID properties, CAP theorem, normalization forms, index types, JOIN types, etc.). The massive 'Capabilities' section is essentially a textbook table of contents that adds no actionable value — Claude already knows what B-tree indexes and window functions are.	1 / 5
Actionability	Almost entirely abstract descriptions and bullet-point lists of concepts. No concrete code examples, no executable commands, no specific schema snippets, no sample SQL or migration scripts. The 'Instructions' section is four vague steps. The 'Example Interactions' are just prompt suggestions, not worked examples with outputs.	2 / 5
Workflow Clarity	The 4-step 'Instructions' and 10-step 'Response Approach' provide a rough sequence but are extremely high-level with no validation checkpoints. Migration planning is mentioned but lacks concrete validation steps, rollback triggers, or feedback loops. For a skill involving destructive operations (migrations, schema changes), the absence of explicit validation steps is a significant gap.	2 / 5
Progressive Disclosure	Monolithic wall of text with no bundle files and no references to external documents. Hundreds of lines of capability listings are inlined that should be in separate reference files or omitted entirely. No navigation structure beyond flat section headers.	1 / 5
	Total	6 / 20 Passed

Description

36%Scale 1-5

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

The description reads more like a resume headline than a functional skill description. It uses first-person-adjacent framing ('Expert database architect specializing in...') rather than third-person action verbs, lacks concrete actions, and entirely omits trigger guidance for when Claude should select this skill. The domain is identifiable but the description needs significantly more specificity and an explicit 'Use when...' clause.

Suggestions

Replace the persona-style framing with concrete action verbs in third person, e.g., 'Designs database schemas, selects appropriate database technologies (SQL/NoSQL), creates ERD diagrams, and plans migration strategies.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about database design, schema modeling, choosing between PostgreSQL/MySQL/MongoDB, data modeling, table relationships, or building a data layer from scratch.'

Include specific technology names and file/concept keywords users would naturally mention, such as 'SQL, NoSQL, PostgreSQL, MongoDB, Redis, indexing, normalization, ERD, migrations, ORM.'

Dimension	Reasoning	Score
Specificity	Names the domain (database architecture) and lists broad areas like 'technology selection, schema modeling, and scalable database architectures,' but these are high-level categories rather than concrete actions. No specific verbs describing what the skill actually does (e.g., 'designs ERD diagrams,' 'generates migration scripts,' 'recommends indexing strategies').	2 / 5
Completeness	Provides a vague 'what' (database architecture specialization) but completely lacks any 'when' clause or trigger guidance. There is no 'Use when...' or equivalent explicit guidance for when Claude should select this skill.	2 / 5
Trigger Term Quality	Includes some relevant keywords like 'database,' 'schema modeling,' 'data layer,' and 'scalable database architectures,' but misses many natural user phrases such as 'SQL,' 'NoSQL,' 'PostgreSQL,' 'MongoDB,' 'database design,' 'table structure,' 'migrations,' 'ORM,' or 'data model.'	3 / 5
Distinctiveness Conflict Risk	Somewhat specific to database architecture, but terms like 'data layer design' and 'scalable architectures' are broad enough to overlap with general backend development, system design, or infrastructure skills.	3 / 5
	Total	10 / 20 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/database-architect/SKILL.md
Commit: 57c135b

Reviewed: 3 days 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.