drizzle-orm

Drizzle ORM patterns: schema definitions, Drizzle Kit migrations, query builders, type branding, custom types, SQLite, Postgres, D1, and Turso/libSQL boundaries. Use when mentioning Drizzle, drizzle-orm, DB schemas, migrations, branded column types, or typed SQL queries.

Quality

93%

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

Quality

Content

87%

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

A lean, source-grounded guidelines skill with executable code examples and clean section organization. Its only gap is the absence of an explicit validation feedback loop for the migration/schema operations it governs.

Suggestions

Add an explicit validate->fix->retry sequence for migrations (e.g. run drizzle-kit generate, review the snapshot/SQL diff, fix schema, regenerate until the diff is clean) to lift workflow_clarity.

Make the migration review checkpoint a numbered checklist mirroring the upstream-grounding decision tree so the verification step is unambiguous.

Consider a short 'Quick start' anchor at the top so the rule sections can be scanned in priority order.

Dimension	Reasoning	Score
Conciseness	Lean and purposeful throughout: rule statements are tight and the explanatory prose (e.g. the $type runtime-overhead "Why" with concrete call counts) covers non-obvious Drizzle internals Claude does not already know, not generic concepts.	3 / 3
Actionability	Provides fully executable, copy-paste-ready TypeScript examples for bad/good $type patterns, customType, and DateTimeString, plus concrete driver-boundary rules (bun:sqlite, better-sqlite3, D1, libSQL/Turso).	3 / 3
Workflow Clarity	The upstream-grounding section gives a sequenced decision tree with a verify step and the migration rule says to review generated SQL and snapshots together, but there is no explicit validate->fix->retry feedback loop for the schema/migration operations the skill describes.	2 / 3
Progressive Disclosure	No bundle files exist, so this scores against body organization: the content is self-contained and split into well-signaled cohesive sections (rules, driver boundaries, $type deep-dive, intermediate representation) with one-level external grounding pointers to the Drizzle/Turso repos.	3 / 3
	Total	11 / 12 Passed

Description

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.

The description is specific, trigger-rich, complete, and clearly scoped to Drizzle ORM. It uses third person and avoids vague fluff, hitting the top anchor on every dimension.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete capabilities ("schema definitions, Drizzle Kit migrations, query builders, type branding, custom types, SQLite, Postgres, D1, and Turso/libSQL boundaries") rather than vague language.	3 / 3
Completeness	Explicitly answers both what ("Drizzle ORM patterns: schema definitions...") and when ("Use when mentioning Drizzle...") with an explicit trigger clause.	3 / 3
Trigger Term Quality	The "Use when mentioning Drizzle, drizzle-orm, DB schemas, migrations, branded column types, or typed SQL queries" clause covers natural terms a user would actually say.	3 / 3
Distinctiveness Conflict Risk	A clear Drizzle-specific niche with distinct triggers; the package-scoped terms (drizzle-orm, Drizzle Kit, D1, Turso/libSQL) make it unlikely to fire for the wrong skill.	3 / 3
	Total	12 / 12 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: EpicenterHQ/epicenter
Path: .agents/skills/drizzle-orm/SKILL.md
Commit: cb12bcc

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.