CtrlK
BlogDocsLog inGet started
Tessl Logo

tessl-labs/prisma-best-practices

Prisma ORM patterns — schema design, migrations, type-safe queries, testing, error handling, and performance

96

1.28x
Quality

95%

Does it follow best practices?

Impact

100%

1.28x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Overview
Quality
Evals
Security
Files

Quality

Discovery

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is an excellent skill description that follows best practices. It uses third person voice, lists comprehensive specific capabilities, includes natural trigger terms developers would use, and provides explicit 'Use when...' guidance covering multiple relevant scenarios. The Prisma-specific focus makes it highly distinctive.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: 'schema design, migrations, type-safe queries, relations, transactions, connection pooling, error handling, testing, raw SQL safety, and performance' - comprehensive coverage of Prisma capabilities.

3 / 3

Completeness

Clearly answers both what (Prisma ORM patterns with specific capabilities listed) AND when with explicit 'Use when...' clause covering multiple scenarios: building/reviewing apps, setting up databases, writing tests, and debugging performance.

3 / 3

Trigger Term Quality

Excellent coverage of natural terms users would say: 'Prisma', 'schema', 'migrations', 'queries', 'database', 'tests', 'query performance', 'debugging'. These are terms developers naturally use when working with Prisma ORM.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive with 'Prisma ORM' as the clear niche. The specific technology focus (Prisma) combined with ORM-specific terminology makes it unlikely to conflict with general database skills or other ORM tools.

3 / 3

Total

12

/

12

Passed

Implementation

92%

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

This is an excellent, highly actionable Prisma skill with comprehensive coverage of schema design, queries, transactions, error handling, and testing. The WRONG vs RIGHT pattern is extremely effective for teaching correct patterns. The main weakness is the monolithic structure—at this length, splitting advanced topics (soft deletes, raw queries, middleware) into separate files would improve progressive disclosure.

Suggestions

Consider splitting advanced topics (soft deletes middleware, raw SQL, batch operations) into a separate ADVANCED.md file with clear links from the main skill

The schema example could be moved to a separate SCHEMA_EXAMPLE.md file, keeping only key rules inline

DimensionReasoningScore

Conciseness

The skill is highly efficient, using WRONG vs RIGHT code patterns that communicate maximum information with minimal explanation. It assumes Claude's competence with Prisma and avoids explaining basic concepts like what an ORM is or how databases work.

3 / 3

Actionability

Every section provides fully executable, copy-paste ready code examples. The schema, queries, transactions, error handling, and test setup are all complete and runnable, not pseudocode.

3 / 3

Workflow Clarity

Multi-step processes like migrations and testing have clear sequences with explicit commands. The testing section includes proper beforeEach/afterAll lifecycle with validation (cleanup order respecting FK constraints). The checklist provides a comprehensive verification step.

3 / 3

Progressive Disclosure

The content is well-organized with clear sections and a helpful checklist, but it's a long monolithic document (~400 lines). Some sections like soft deletes middleware or the full schema could be split into separate reference files. The verifier references at the end suggest external files exist but aren't leveraged for content organization.

2 / 3

Total

11

/

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.

Validation9 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (564 lines); consider splitting into references/ and linking

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

9

/

11

Passed

Reviewed

Table of Contents