database-design

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

Quality

61%

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

65%

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

The body is admirably concise and well-organized around a content map, checklist, and anti-patterns, but its actionability and workflow clarity depend on referenced files that are missing, and the promised progressive-disclosure targets are absent from the bundle.

Suggestions

Create the six referenced files (database-selection.md, orm-selection.md, schema-design.md, indexing.md, optimization.md, migrations.md) under a references/ directory so the content map resolves.

Add a validation/checkpoint step to the decision workflow, e.g. confirming schema choices against the chosen database's constraints before proceeding.

Inline at least a minimal decision rule (e.g. one-line criteria for SQLite vs PostgreSQL vs serverless) so the skill is actionable even before the reference files are read.

Dimension	Reasoning	Score
Conciseness	The body is lean and token-efficient — a short table, a checklist, bullets, and anti-patterns — with no padding or explanation of concepts Claude already knows; the only flourish ("Learn to THINK, not copy SQL patterns") is a single punchy line.	3 / 3
Actionability	It offers concrete decision guidance (the checklist items and specific anti-patterns like "SQLite may suffice") but delegates the substantive decision criteria to six referenced files that are not present, so the actual executable guidance is incomplete.	2 / 3
Workflow Clarity	The Decision Checklist provides a sequenced set of pre-design decisions, but there are no validation checkpoints or feedback loops; the rubric notes database operations warrant feedback loops and their absence caps this at 2.	2 / 3
Progressive Disclosure	The content-map table is a well-signaled, one-level-deep reference design, but none of the six referenced files (database-selection.md, orm-selection.md, schema-design.md, indexing.md, optimization.md, migrations.md) actually exist in the bundle, so navigation leads nowhere.	2 / 3
	Total	9 / 12 Passed

Description

57%

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 cleanly names a distinct database-design niche with several specific sub-areas, but it reads as a topic list rather than a set of concrete actions and omits an explicit "Use when..." trigger clause in the description field itself.

Suggestions

Rewrite the description with concrete action verbs, e.g. "Design database schemas, choose ORMs, plan safe migrations, and optimize queries."

Append an explicit trigger clause to the description, e.g. "Use when designing schemas, choosing between Prisma/Drizzle/Kysely, planning migrations, or tuning query performance."

Surface user-natural tool names (Prisma, Drizzle, SQL) directly in the description text rather than only in when_to_use.

Dimension	Reasoning	Score
Specificity	The description names the domain and several specific areas ("Schema design, indexing strategy, ORM selection, serverless databases") but as noun phrases rather than concrete action verbs like "design schemas, choose ORMs, optimize queries"; it lists multiple sub-topics yet is not phrased as explicit actions.	2 / 3
Completeness	The description clearly answers "what" (database design principles and decision-making areas) but contains no "Use when..." or equivalent explicit trigger clause; per the rubric a missing trigger clause caps completeness at 2, even though a separate when_to_use field exists.	2 / 3
Trigger Term Quality	It includes some natural terms a user might say ("database", "schema", "indexing", "ORM"), but the strongest user-facing triggers ("Prisma", "Drizzle", "SQL", "migrations", "queries") live only in the separate when_to_use field, not in the description text itself.	2 / 3
Distinctiveness Conflict Risk	The database-design niche is clear and specific (schema design, indexing, ORM selection, serverless databases), making it unlikely to trigger for unrelated skills.	3 / 3
	Total	9 / 12 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: 04514f0

Reviewed: about 13 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.