database-design

Database design principles and decision-making. Schema design, indexing strategy, ORM selection, serverless databases.

Quality

67%

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 ./.agents/skills/database-design/SKILL.md

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

Quality

Content

68%Weight 40%Scale 1-5

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

The body is a model of conciseness with a well-designed content map, but it relies on reference files that are missing from the bundle and lacks validation feedback loops for destructive database operations.

Suggestions

Ship the six referenced files (database-selection.md, orm-selection.md, schema-design.md, indexing.md, optimization.md, migrations.md) in ./references/ so the content map's links resolve.

Add an explicit validation/verification step to the migration workflow (e.g., run scripts/schema_validator.py, review errors, re-validate before applying) to lift workflow_clarity above the destructive-operation cap of 3.

Inline a minimal, concrete decision rule for database/ORM selection (e.g., "SQLite for local/simple, Postgres for relational scale, Turso/Neon for serverless") so actionability does not depend entirely on the missing reference files.

Dimension	Reasoning	Score
Conciseness	Lean and efficient throughout — a short content-map table, a tight principle list, checklist, and anti-patterns with zero padding or explanation of concepts Claude already knows.	5 / 5
Actionability	Concrete decision guidance exists (anti-patterns like "SELECT *", "Store JSON", the pre-design checklist) but the actual selection logic is delegated to reference files that are not present in the bundle, leaving key details missing.	3 / 5
Workflow Clarity	A pre-design Decision Checklist gives a rough sequence, but database/migration work is destructive and the body provides no validate→fix→retry feedback loop, capping workflow clarity at 3 per the rubric.	3 / 5
Progressive Disclosure	Excellent structure — a content-map table with file, description, and when-to-read columns clearly signals one-level-deep references — but the six referenced .md files are absent from ./references/, so navigation is partially broken.	4 / 5
	Total	15 / 20 Passed

Description

66%Weight 40%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 names the domain and several concrete capabilities clearly, but the description field itself omits explicit "when to use" trigger guidance (relegated to a separate when_to_use field), capping completeness.

Suggestions

Fold a concise "Use when..." trigger clause into the description field itself (e.g., "Use when designing schemas, choosing an ORM, or planning migrations") so completeness is not capped at 3.

Add the natural trigger terms currently only in when_to_use ("migrations", "queries", "Prisma", "Drizzle", "SQL files") to broaden trigger-term coverage to 5.

Tighten the abstract opener "Database design principles and decision-making" to lead with concrete actions rather than a generic framing.

Dimension	Reasoning	Score
Specificity	Lists several specific capabilities — "Schema design, indexing strategy, ORM selection, serverless databases" — beyond the abstract opener "Database design principles and decision-making", with only minor coverage gaps.	4 / 5
Completeness	The description field gives a clear "what" but no "Use when..." trigger clause — per the rubric a missing explicit trigger caps completeness at 3 even though the capability list is solid.	3 / 5
Trigger Term Quality	Good keyword coverage of natural terms ("database design", "schema", "indexing", "ORM", "serverless databases"), but missing common variations and product names (migrations, queries, Prisma/Drizzle) that live only in when_to_use.	4 / 5
Distinctiveness Conflict Risk	The database-design niche is mostly distinct with clear DB-specific triggers; only minor overlap risk with a general SQL skill keeps it below 5.	4 / 5
	Total	15 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: vudovn/ag-kit
Path: .agents/skills/database-design/SKILL.md
Commit: 211561c

Reviewed: 11 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.