CtrlK
BlogDocsLog inGet started
Tessl Logo

database-design

Designs database schemas, indexing strategies, query optimization, and migration patterns for SQL and NoSQL databases. Use when designing tables, optimizing queries, fixing N+1 problems, planning migrations, or when asked about database performance, normalization, ORMs, or data modeling.

68

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

65%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 is highly actionable — dense, executable, WRONG/CORRECT-contrasted code across SQL, ORMs, and NoSQL — and cleanly sectioned. Its weaknesses are redundancy with what Claude already knows (normalization forms, index types, textbook N+1), a workflow checklist lacking validation feedback loops for destructive migration operations, and a total absence of progressive disclosure across bundle files.

Suggestions

Trim textbook exposition Claude already knows (1NF/2NF/3NF definitions, the index-type cheat table, generic N+1 explanations) down to one-line reminders, keeping only the project-specific WRONG/CORRECT patterns and the anti-patterns table — this would move conciseness toward anchor 4-5.

Add explicit validation feedback loops to the workflow and migration sections, e.g., a step 'Run EXPLAIN ANALYZE and verify no Seq Scan on large tables before/after adding an index' and 'Test rollback on a staging copy before deploying each migration', with fix-and-retry guidance — required for destructive/batch database operations.

Split the SKILL.md into a lean overview plus one-level-deep reference files (e.g., references/nosql.md, references/orm-patterns.md, references/migrations.md) with clearly signaled links, instead of inlining all SQL, ORM, and NoSQL content in one ~390-line file.

DimensionReasoningScore

Conciseness

Prose is minimal and there is no padded filler, but substantial portions restate concepts Claude already knows — the 1NF/2NF/3NF definitions, the B-tree/Hash/GIN/GiST/BRIN index-type table, and textbook N+1 and OFFSET-vs-cursor examples. It is mostly efficient but could be significantly tightened by trimming known-concept exposition, fitting anchor 3 rather than 4.

3 / 5

Actionability

Nearly every section provides copy-paste-ready executable code: PostgreSQL DDL, trigger functions, index DDL, EXPLAIN ANALYZE reading guidance, SQLAlchemy and Prisma eager-loading/batching, and Redis cache-aside patterns, with WRONG/CORRECT pairs covering common cases. This matches anchor 5's 'fully executable; copy-paste ready' bar.

5 / 5

Workflow Clarity

The 8-step progress checklist gives a clear sequence and step 8 ('Validate against anti-patterns checklist') is a checkpoint, but the workflow covers database migrations and batch backfills — destructive/batch operations — with no explicit validate-then-fix-then-retry feedback loops (rollback testing appears only as a list rule, not a workflow checkpoint). Per the rubric's cap for database operations without feedback loops, workflow clarity is held at 3 rather than 4.

3 / 5

Progressive Disclosure

Sections are well-organized with clear headers, but the skill is a ~390-line single-file monolith with no references/, scripts/, or assets/ bundle at all. Content that would naturally split into reference files (NoSQL patterns, ORM practices, migration playbook) is fully inlined, matching anchor 3's 'content that should be separate is inline' rather than a well-split anchor-4/5 structure.

3 / 5

Total

14

/

20

Passed

Description

100%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 is a model example of the form: third-person voice, a comprehensive 'what' sentence, and an explicit 'Use when...' clause packed with natural trigger terms including synonyms. It closely mirrors the rubric's good_overall_examples with no weaknesses to penalize.

DimensionReasoningScore

Specificity

"Designs database schemas, indexing strategies, query optimization, and migration patterns for SQL and NoSQL databases" lists four concrete actions plus explicit scope, comprehensively covering the domain. This matches the anchor-5 good examples; there are no minor coverage gaps that would justify a 4.

5 / 5

Completeness

The first sentence explicitly answers 'what' (designs schemas, indexing, query optimization, migrations) and "Use when designing tables... or when asked about database performance..." explicitly answers 'when' with concrete trigger phrases. Both halves are explicit and specific, matching the anchor-5 example structure exactly.

5 / 5

Trigger Term Quality

Natural user phrases like "fixing N+1 problems", "planning migrations", "optimizing queries", "normalization, ORMs, or data modeling" give comprehensive coverage with synonyms (schema design / data modeling). No common variations are missing, so it sits above the anchor-4 'a few natural terms missing' level.

5 / 5

Distinctiveness Conflict Risk

The description claims a clear database niche with distinctive triggers (N+1 problems, normalization, migration planning) that few other skills would match. Overlap risk with generic backend or ORM skills is minimal, fitting the anchor-5 'clear niche with distinct triggers'.

5 / 5

Total

20

/

20

Passed

Validation

100%

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
CloudAI-X/claude-workflow-v2
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.