database-designer

Use when the user asks to design database schemas, plan data migrations, optimize queries, choose between SQL and NoSQL, or model data relationships.

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./engineering/skills/database-designer/SKILL.md

Quality

Content

55%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 has an excellent, validated multi-step workflow but is weighed down by verbose inlined reference material and commands that point to scripts missing from the bundle. Most detailed tables and SQL patterns should move into the existing reference files and be linked.

Suggestions

Move the query-generation patterns, multi-database decision matrix, and sharding/replication tables into the existing reference files (e.g. index_strategy_patterns.md, database_selection_decision_tree.md) and link them, rather than inlining them.

Provide the referenced scripts (schema_analyzer.py, index_optimizer.py, migration_generator.py) in a scripts/ directory, or replace the bash commands with a description of what the scripts should do so the workflow is honest about its current state.

Link all four reference files from the body (currently only database-design-reference.md is referenced) so the normalization guide, index patterns, and decision tree are discoverable instead of duplicating their content inline.

Dimension	Reasoning	Score
Conciseness	The ~310-line body inlines large tutorial-style material Claude largely already knows — JOIN/CTE/window-function/aggregation patterns, multi-database decision matrices, sharding and replication tables — that reads as padded reference content rather than skill-specific guidance.	2 / 5
Actionability	Concrete `python3` commands with flags and sample asset paths look executable, but the referenced scripts (schema_analyzer.py, index_optimizer.py, migration_generator.py) are absent from the bundle with no scripts/ directory, so the commands do not run as written; the inline SQL is copy-paste ready.	3 / 5
Workflow Clarity	The four-step Tool Workflow (analyze → optimize → generate → verify) is clearly sequenced, and step 4 is an explicit verification loop that re-runs analysis on the target schema and runs --validate-only, satisfying the destructive/batch validation requirement.	5 / 5
Progressive Disclosure	Four reference files and three asset files exist and are real, but only database-design-reference.md is linked from the body while the other three references go unused, and substantial content that belongs in those references is inlined as tables and SQL tutorials.	3 / 5
	Total	13 / 20 Passed

Description

80%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.

A focused, trigger-rich description that names several concrete database actions and an explicit "Use when" clause. It is held back from a top score by missing common synonyms/extensions and modest overlap with closely related database skills.

Suggestions

Add natural synonyms and file extensions users actually say, e.g. "indexes", "DDL", or ".sql", to broaden trigger coverage.

Lead with a one-phrase capability statement ("Designs, optimizes, and migrates database schemas") before the "Use when" clause so both what and when are explicit.

Narrow the scope or add a distinguishing clause (e.g. "for greenfield schema design and migrations") to reduce overlap with sibling SQL/schema skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "design database schemas", "plan data migrations", "optimize queries", "choose between SQL and NoSQL", "model data relationships" — giving comprehensive, specific coverage rather than a single generic action.	5 / 5
Completeness	The "when" is explicit and concrete ("Use when the user asks to...") and the "what" is recoverable from the verbs, but there is no standalone capability noun-phrase, so it stops just short of the explicit both-what-and-when anchor.	4 / 5
Trigger Term Quality	Strong natural keyword coverage ("design database schemas", "optimize queries", "SQL and NoSQL", "model data relationships") but omits common synonyms and file extensions like "indexes", "DDL", or ".sql" that a user might actually say.	4 / 5
Distinctiveness Conflict Risk	It occupies a clear database niche with distinct triggers, but its breadth (design, migration, optimization, SQL/NoSQL choice, modeling) overlaps noticeably with the sibling sql-database-assistant and database-schema-designer skills it cross-references.	4 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: alirezarezvani/claude-skills
Path: engineering/skills/database-designer/SKILL.md
Commit: 19392f7

Reviewed: ~6 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.