Name: database-designer
Rating: 49.6 (1 reviews)
Author: alirezarezvani

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

53%

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 ./.gemini/skills/database-designer/SKILL.md

The canonical home for this skill is database-designer in alirezarezvani/claude-skills

Quality

Content

45%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 skill has a well-sequenced workflow with validation checkpoints, but it ships none of the referenced tools or sample assets, making the core "run these" workflow non-executable, and it bloats the context window with generic database knowledge that should live in reference files.

Suggestions

Ship the referenced scripts (schema_analyzer.py, index_optimizer.py, migration_generator.py) and assets (sample_schema.sql/json, sample_query_patterns.json) referenced in the workflow, or remove the "run these — do not analyze by hand" directive if the tools are unavailable.

Move the generic SQL patterns, index/EXPLAIN/N+1, connection pooling, sharding, replication, and multi-DB comparison sections into references/ files, keeping only the tool workflow and migration/expansion-contract guidance in SKILL.md.

Provide a concrete rollback-verification step in the workflow (e.g., re-run `schema_analyzer.py` on the post-migration schema and assert the first-pass findings are resolved) rather than leaving rollback as prose advice.

Dimension	Reasoning	Score
Conciseness	The ~310-line body is noticeably verbose, inlining large amounts of general database knowledge Claude already has — generic SQL JOIN/CTE/window-function/aggregation examples, index-type tables, EXPLAIN reading, N+1 detection, connection pooling, and sharding/replication matrices — padded against a smaller core of genuinely skill-specific content.	2 / 5
Actionability	The tool workflow gives detailed, concrete commands (e.g., `python3 schema_analyzer.py --input schema.sql --generate-erd ...`), but the referenced scripts and sample assets (schema_analyzer.py, index_optimizer.py, migration_generator.py, assets/*.json) do not exist in the bundle, so the commands are not actually runnable as written.	3 / 5
Workflow Clarity	A clear 4-step sequence (analyze → optimize → migrate → verify) with an explicit validation/feedback loop in step 4 and a `--validate-only` checkpoint; the destructive/batch cap does not apply since validation is present, though the verify step and rollback checklists could be more concrete.	4 / 5
Progressive Disclosure	Despite a clearly signaled one-level reference ("→ See references/database-design-reference.md") and section headers, roughly 200 lines of general reference material that belongs in separate files is inlined in SKILL.md, and the referenced bundle files (scripts/, assets/, references/) do not exist, leaving navigation broken.	2 / 5
	Total	11 / 20 Passed

Description

62%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 has solid trigger phrasing and concrete actions but is purely a "Use when..." clause with no explicit capability statement, leaving the "what" only implied. Overlap with sibling database skills limits distinctiveness.

Suggestions

Lead with a concrete capability sentence (e.g., "Designs and optimizes database schemas, generates ERDs and zero-downtime migrations.") before the "Use when..." clause so the "what" is explicit.

Add natural trigger synonyms users actually say — "indexes", "DDL", "ERD", "query performance" — to broaden trigger coverage.

Sharpen distinctiveness from sibling skills (e.g., sql-database-assistant, migration-architect) by narrowing triggers to schema-architecture decisions rather than day-to-day query work.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — "design database schemas", "plan data migrations", "optimize queries", "choose between SQL and NoSQL", "model data relationships" — but frames them as trigger conditions rather than direct capability statements, and omits core skill actions the body emphasizes (ERD generation, normalization analysis).	4 / 5
Completeness	The "when" is explicit and strong ("Use when the user asks to...") but there is no standalone capability statement declaring what the skill does; the "what" is only weakly implied through the folded-in trigger actions, landing it between the "only when present" (2) and "both what and when" (4) anchors.	3 / 5
Trigger Term Quality	Includes natural phrases users would say ("design database schemas", "optimize queries", "plan data migrations") but misses common variations and synonyms a user might actually use ("indexes", "DDL", "ERD", "database performance", file extensions like .sql).	4 / 5
Distinctiveness Conflict Risk	The database-design niche is specific, but "optimize queries" and "plan data migrations" overlap with the query-writing and migration-architect skills the body itself cross-references, so it could still trigger for closely related skills.	3 / 5
	Total	14 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 5 missing	Warning

	Total	15 / 16 Passed

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

Reviewed: ~5 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.