prisma-patterns

Prisma ORM patterns for TypeScript backends — schema design, query optimization, transactions, pagination, and critical traps like updateMany returning count not records, $transaction timeouts, migrate dev resetting the DB, @updatedAt skipped on bulk writes, and serverless connection exhaustion.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No known issues

Quality

Content

80%

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

A dense, highly actionable Prisma reference with excellent code examples and tight prose, held back from top marks by missing validation feedback loops on destructive DB operations and a monolithic single-file structure with no progressive disclosure to separate reference files.

Suggestions

Add explicit validation checkpoints to risky workflows, e.g. after `migrate deploy` verify with `migrate status` and rollback/retry guidance on failure.

Split the Anti-Patterns and migration content into referenced files (e.g. ANTI_PATTERNS.md, MIGRATIONS.md) so SKILL.md stays an overview, enabling one-level-deep progressive disclosure.

De-duplicate the adapter-based vs direct PrismaClient setup, which currently appears in both the PrismaClient Singleton and Connection Pool sections.

Dimension	Reasoning	Score
Conciseness	Lean tables for ID strategy, include-vs-select, and transaction selection; dense executable code; no padding explaining what an ORM or migration is. Not score 2 despite minor adapter-vs-direct repetition, because every section delivers distinct value and tokens are not wasted on concepts Claude already knows.	3 / 3
Actionability	Fully executable TypeScript and bash throughout (cursor pagination, $transaction forms, error handling, migrate deploy/diff) with specific Prisma error codes — copy-paste ready, matching the score-3 anchor rather than the pseudocode score-2 anchor.	3 / 3
Workflow Clarity	Sequences are present (expand-and-contract Step 1/2/3, 'Check drift without applying'), but there are no explicit validate→fix→retry feedback loops for destructive/batch DB operations; the scoring notes cap workflow_clarity at 2 for missing feedback loops in database contexts, so it is not score 3.	2 / 3
Progressive Disclosure	Sections are well organized (When to Activate, Core Concepts, Anti-Patterns, Best Practices) so it is above the monolithic score-1 anchor, but this is a ~400-line single file with no bundle files and no external references — content that could be split (detailed migration guide, anti-pattern catalog) is inline, matching the score-2 anchor.	2 / 3
	Total	10 / 12 Passed

Description

82%

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 specific, distinctive description with strong trigger terms and concrete capabilities, weakened only by the absence of an explicit 'Use when...' trigger clause. Adding a short usage-trigger sentence would raise completeness to a top score.

Suggestions

Append an explicit trigger clause, e.g. 'Use when designing or modifying Prisma schema, writing queries/transactions, running migrations, or debugging Prisma behavior in TypeScript backends.'

Keep the named traps but consider moving the longest trap examples into the body so the description stays scannable while still signaling the trap category.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'schema design, query optimization, transactions, pagination' — plus specific named traps like 'updateMany returning count not records' and '$transaction timeouts', matching the multiple-specific-actions anchor rather than the partial score-2 anchor.	3 / 3
Completeness	Clearly answers 'what' but contains no 'Use when...' clause or equivalent explicit trigger guidance; per the judging guidelines a missing trigger clause caps completeness at 2, and it is not score 1 because the 'what' is strong and detailed.	2 / 3
Trigger Term Quality	Natural user-facing terms are well covered: 'Prisma ORM', 'TypeScript backends', 'schema design', 'transactions', 'pagination'. Not the score-2 case (which misses common variations) because the core vocabulary users actually say is present.	3 / 3
Distinctiveness Conflict Risk	'Prisma ORM patterns for TypeScript backends' plus distinctive named traps carve a clear niche unlikely to trigger the wrong skill; not score 2 because it does not overlap generically with adjacent skills. Voice is third person, so no specificity penalty applies.	3 / 3
	Total	11 / 12 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Commit: 754b8dd

Reviewed: 3 days 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.