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".
52
58%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/database/database-schema-designer/skills/designing-database-schemas/SKILL.mdQuality
Discovery
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 of what the skill does and when to use it, including explicit trigger phrases. However, it lacks specificity in the concrete actions it performs and uses filler language like 'comprehensive guidance and automation.' The opening 'Process use when' phrasing is awkward and the description would benefit from more concrete capability listing and broader trigger term coverage.
Suggestions
Replace vague phrases like 'comprehensive guidance and automation' with specific concrete actions such as 'create tables, define relationships, generate migration files, manage indexes'.
Expand trigger terms to include common user phrases like 'SQL schema', 'database tables', 'ERD', 'entity relationship', 'add column', 'alter table', or 'foreign key'.
Fix the awkward opening 'Process use when' to use 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 like 'schema design and migrations' and 'guidance and automation', but doesn't list multiple specific concrete actions (e.g., create tables, define relationships, generate migration files, add indexes). | 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'), providing clear trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes some relevant trigger phrases like 'design schema', 'create migration', and 'model database', but misses common natural variations users might say such as 'database tables', 'SQL schema', 'ERD', 'entity relationship', 'foreign key', 'add column', or 'alter table'. | 2 / 3 |
Distinctiveness Conflict Risk | Focuses on database schema design which is a reasonably specific niche, but the vague mention of 'comprehensive guidance and automation' and broad terms like 'model database' could overlap with general database skills or ORM-related skills. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides comprehensive database schema design guidance with good domain-specific recommendations (data types, indexing strategies, multi-tenancy patterns) but suffers from explaining concepts Claude already knows (normalization forms, relationship types) and lacks executable code examples. The workflow is logically sequenced but missing validation checkpoints, and the content would benefit from being split across files with concrete DDL code blocks.
Suggestions
Replace prose descriptions of normalization forms and relationship types with a brief reference, and add complete, executable DDL code blocks (e.g., a full e-commerce schema CREATE TABLE script) instead of prose-based examples.
Add explicit validation checkpoints in the workflow, such as 'Run the DDL against a test database to verify syntax' and 'Query information_schema to confirm all foreign keys and indexes were created correctly.'
Extract the error handling table, detailed examples (e-commerce, multi-tenant, event sourcing), and resources into separate reference files to keep SKILL.md as a concise overview with pointers.
Remove explanations of basic concepts like what 1NF/2NF/3NF are and what one-to-many relationships mean—Claude knows these. Focus instead on project-specific conventions and non-obvious decisions.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-structured but includes explanations Claude already knows (normalization forms, what 1NF/2NF/3NF mean, basic relationship types like one-to-many). The data type recommendations and constraint patterns are useful domain-specific guidance, but the normalization tutorial and relationship definitions are unnecessary padding for Claude. | 2 / 3 |
Actionability | The skill provides specific data type recommendations, constraint patterns, and concrete examples (e.g., NUMERIC(12,2) for money, CITEXT for email), but lacks executable DDL code blocks. The examples section describes schemas in prose rather than providing copy-paste-ready SQL. The instructions are detailed but read more like a textbook than executable guidance. | 2 / 3 |
Workflow Clarity | The 10-step process is clearly sequenced and logically ordered (entities → keys → normalization → relationships → types → constraints → indexes → denormalization → DDL output). However, there are no validation checkpoints—no step says 'verify the schema compiles,' 'test with sample data,' or 'validate foreign key integrity before proceeding.' For a skill that generates DDL scripts, missing validation/verification steps is a notable gap. | 2 / 3 |
Progressive Disclosure | The content is a monolithic document with no references to supporting files. At ~120 lines covering schema design, normalization, indexing, multi-tenancy, event sourcing, and error handling, some of this content (e.g., the detailed examples, error handling table, resources) could be split into separate reference files. However, the sections are well-organized with clear headers, which partially compensates. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
81%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 | |
- Commit
4801da6
- Reviewed
Table of Contents
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.