CtrlK
BlogDocsLog inGet started
Tessl Logo

drizzle-orm

Apply Drizzle ORM patterns for schemas, migrations, queries, branded types, and Postgres or D1 boundaries. Use when working with Drizzle or typed SQL, not raw `bun:sqlite` or non-Drizzle engines.

69

Quality

83%

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

75%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.

A well-structured, mostly lean guidelines skill that leads with concrete bad/good code patterns and grounds API claims in upstream source. It would benefit from executable snippets in the rule-list sections and more explicit validation checkpoints for migration work.

Suggestions

Add a small executable example under 'Schema And Migration Rules' (e.g., a minimal schema export + drizzle() wiring) so the rules have a concrete anchor.

Make the migration verification step an explicit checkpoint: 'Review generated SQL + snapshot, and only apply the migration when both match expectations.'

Consider extracting the $type vs customType deep-dive into a references/ file and linking from a short summary, to keep the overview tighter.

DimensionReasoningScore

Conciseness

Mostly lean and directive with code-backed justifications; minor instances of over-explanation (e.g., restating what $type does) that could be trimmed without loss.

4 / 5

Actionability

Provides copy-paste-ready bad/good code patterns for $type vs customType and JSON transforms, but the Schema/Migration and Query Builder sections are rules-only without executable examples.

4 / 5

Workflow Clarity

The Upstream Grounding flow is sequenced (DeepWiki orientation → verify against local types/migrations/docs) and migration rules include a verification cue ('Review generated SQL and snapshot changes together'), though explicit validate-then-proceed checkpoints are implicit.

4 / 5

Progressive Disclosure

Well-organized into clear section headers with one-level-deep external references (GitHub repo, DeepWiki) clearly signaled; no bundle files exist, so the inline structure is appropriate, though the long $type deep-dive could justify a separate reference.

4 / 5

Total

16

/

20

Passed

Description

92%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.

A strong, third-person description that pairs a comprehensive capability list with an explicit use-when trigger and a clear negative boundary to avoid misfires. Minor keyword-synonym gaps keep trigger term quality just below perfect.

DimensionReasoningScore

Specificity

Lists multiple concrete capability areas — 'schemas, migrations, queries, branded types, and Postgres or D1 boundaries' — giving comprehensive, domain-specific coverage rather than vague language.

5 / 5

Completeness

Explicitly answers both what ('Apply Drizzle ORM patterns for ...') and when ('Use when working with Drizzle or typed SQL, not raw `bun:sqlite` ...') with concrete trigger phrasing.

5 / 5

Trigger Term Quality

Includes natural trigger phrases ('Drizzle', 'typed SQL', 'raw bun:sqlite', 'non-Drizzle engines') that users would say, but omits common variations like 'Drizzle migrations' or 'Drizzle schema'.

4 / 5

Distinctiveness Conflict Risk

The negative boundary ('not raw `bun:sqlite` or non-Drizzle engines') carves a clear niche and actively suppresses overlap with sibling SQLite/DB skills.

5 / 5

Total

19

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
EpicenterHQ/epicenter
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.