designing-database-schemas

Process use when you need to work with database schema design. This skill provides schema design and migrations with comprehensive guidance and automation. Trigger with phrases like "design schema", "create migration", or "model database".

Quality

47%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/database/database-schema-designer/skills/designing-database-schemas/SKILL.md

Quality

Content

27%

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

This skill reads more like a database design textbook chapter than an efficient skill file for Claude. It extensively explains concepts Claude already knows (normalization forms, relationship types, basic data types) while lacking the executable, copy-paste-ready DDL examples that would make it truly actionable. The monolithic structure with no supporting bundle files means all content competes for context window space.

Suggestions

Remove explanations of concepts Claude already knows (normalization definitions, what foreign keys are, relationship type descriptions) and replace with a concise reference table of project-specific conventions and preferences only.

Add at least one complete, executable DDL example (e.g., a small e-commerce schema) instead of prose descriptions in the Examples section.

Split detailed topics (index strategy, multi-tenancy patterns, event sourcing patterns, data type reference) into separate bundle files and reference them from the main SKILL.md.

Add validation checkpoints: e.g., 'Run the DDL against a test database to verify it executes without errors' and 'Test key queries against the schema to verify index coverage' before delivering the final output.

Dimension	Reasoning	Score
Conciseness	The skill is extremely verbose at ~150+ lines, explaining fundamental database concepts Claude already knows well (normalization forms, what foreign keys are, one-to-many vs many-to-many relationships, what 1NF/2NF/3NF mean). Much of this is textbook-level database knowledge that wastes context window tokens.	1 / 3
Actionability	The skill provides specific data type recommendations and concrete SQL snippets (e.g., `NUMERIC(12,2)`, `TIMESTAMPTZ`, CHECK constraints, RLS policies), but lacks complete executable DDL examples. The examples section describes schemas in prose rather than providing copy-paste-ready SQL. No actual migration file template is shown despite being listed as an output.	2 / 3
Workflow Clarity	The 10-step process is clearly sequenced and logically ordered (identify entities → normalize → define relationships → types → constraints → indexes → denormalize → generate DDL). However, there are no validation checkpoints — no step to verify the schema compiles, no feedback loop for testing against sample queries, and no verification that the generated DDL actually runs without errors.	2 / 3
Progressive Disclosure	The content is a monolithic wall of text with no bundle files to reference. All content — normalization theory, data type guidance, indexing strategy, multi-tenancy patterns, event sourcing patterns — is inlined in a single file. These distinct topics (index strategy, multi-tenancy, event sourcing) should be split into separate reference files.	1 / 3
	Total	6 / 12 Passed

Description

67%

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 covers the basics with explicit trigger phrases and a clear domain focus on database schema design and migrations. However, it lacks specificity in concrete actions, uses filler language ('comprehensive guidance and automation'), and the opening 'Process use when' is awkward and grammatically incorrect. The trigger terms are reasonable but could be expanded with more natural user language variations.

Suggestions

Replace vague phrases like 'comprehensive guidance and automation' with specific concrete actions such as 'create table definitions, define relationships and constraints, generate SQL migration files, normalize data models'.

Expand trigger terms to include more natural user phrases like 'database tables', 'SQL schema', 'foreign keys', 'entity relationship', 'alter table', or 'database structure'.

Fix the awkward opening 'Process use when' — rewrite in proper third person voice, e.g., 'Designs database schemas and generates migration files.'

Dimension	Reasoning	Score
Specificity	Names the domain (database schema design) and mentions some actions ('schema design', 'migrations', 'guidance and automation'), but lacks specific concrete actions like 'create tables', 'define relationships', 'generate SQL migration files', or 'normalize data models'.	2 / 3
Completeness	Explicitly answers both 'what' (schema design and migrations with guidance and automation) and 'when' (trigger phrases like 'design schema', 'create migration', 'model database'). The trigger guidance is explicit.	3 / 3
Trigger Term Quality	Includes some relevant trigger phrases ('design schema', 'create migration', 'model database'), but misses common natural variations users would say like 'database tables', 'SQL schema', 'ERD', 'entity relationship', 'foreign keys', 'normalize', '.sql files', or 'alter table'.	2 / 3
Distinctiveness Conflict Risk	Somewhat specific to database schema design, but 'migrations' could overlap with general database management or ORM-related skills. The term 'model database' is somewhat ambiguous and could conflict with data modeling or database administration skills.	2 / 3
	Total	9 / 12 Passed

Validation

81%

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 — 9 / 11 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	9 / 11 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 0b821b5

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.