CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

drizzle-orm-expert

Expert in Drizzle ORM for TypeScript — schema design, relational queries, migrations, and serverless database integration. Use when building type-safe database layers with Drizzle.

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/drizzle-orm-expert/SKILL.md

The canonical home for this skill is drizzle-orm-expert in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

72%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 highly actionable, code-first reference that would let Claude execute real Drizzle work immediately, with only minor padding (persona intro, 'Why Drizzle' section). Its weaknesses are structural: no validation/verification checkpoints in migration and destructive-operation workflows (capping workflow clarity), and a monolithic single-file layout with no reference files for a skill of this size.

Suggestions

Add validation checkpoints to the migration workflow: after `npx drizzle-kit migrate`, verify applied state (e.g., check the migrations journal or run a smoke query) and loop back on failure, mirroring the Troubleshooting entries as an explicit feedback loop.

Split long peripheral sections into one-level-deep reference files (e.g., references/dialects.md for the Neon/Turso/PlanetScale client setups, references/nextjs.md for the Next.js integration) so SKILL.md stays a lean overview with well-signaled pointers.

Trim the persona opener and the 'Why Drizzle' comparison section — Claude already knows what ORMs and edge runtimes are — and replace them with anything genuinely non-obvious, such as gotchas of the relational query API.

DimensionReasoningScore

Conciseness

The body is dominated by dense, executable code with minimal prose, matching 'Efficient; minor instances of over-explanation that could be trimmed'. The trimmable parts are the persona opener ('You are a production-grade Drizzle ORM expert...') and the 'Why Drizzle' marketing-style comparison ('Zero dependencies... If you know SQL, you know Drizzle') — concepts Claude already knows — but they are a small fraction of the document. Not a 5 because those padded sections do not earn their tokens; not a 3 because there is no systemic over-explanation of basics.

4 / 5

Actionability

Nearly every section is copy-paste-ready, complete code with imports, file paths, and exact commands: full schema definitions, query patterns, transactions, a drizzle.config.ts, the four drizzle-kit commands, and per-dialect client setups. This matches the level-5 anchor: fully executable examples covering the common cases across the skill's stated scope.

5 / 5

Workflow Clarity

Sequences exist (schema → relations → queries → migrations; generate → migrate commands) and the Troubleshooting section gives problem/solution pairs, but no explicit validation or verification checkpoints appear anywhere — no 'verify the migration applied', no error-recovery loop, no confirmation step before destructive operations. Per the rubric, missing validation in database/batch workflows involving destructive operations (drizzle-kit push, deletes) caps workflow clarity at 3; it is above 2 because steps are clearly listed and ordered, unlike the vague 'rough sequence' anchor.

3 / 5

Progressive Disclosure

The skill is a well-organized single file with clear section headers, but at ~355 lines everything is inline with zero external references — per-dialect client setups, Next.js/tRPC integration, performance tuning, and troubleshooting are all content that could live in one-level-deep reference files to keep SKILL.md a lean overview. This matches the level-3 anchor ('Some structure but could be better organized; content that should be separate is inline'). Not a 2, since section headers and navigation within the file are good; not a 4, since no bundle files exist and the length argues for splitting.

3 / 5

Total

15

/

20

Passed

Description

75%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, well-formed description: concrete capabilities, explicit 'Use when' trigger, and clear Drizzle-specific niche. It sits at 'good but not exemplary' (4) across all dimensions — mostly due to a single narrow trigger phrase and a few missing natural synonyms rather than any structural flaw.

DimensionReasoningScore

Specificity

The description lists several concrete capability areas — "schema design, relational queries, migrations, and serverless database integration" — comparable to the level-4 anchor ('Extracts text from PDF files, fills forms, converts pages to images'). It falls short of 5 because coverage within the domain has minor gaps (no mention of Drizzle Kit tooling, performance optimization, or migrations from other ORMs, all of which the body covers).

4 / 5

Completeness

Both parts are explicit: the "what" ("Expert in Drizzle ORM for TypeScript — schema design, relational queries, migrations, and serverless database integration") and the "when" ("Use when building type-safe database layers with Drizzle"). This matches the level-4 anchor ('Has both what and when; when could be more explicit or specific') — the trigger clause is a single, fairly narrow phrase rather than the multiple concrete triggers of a level-5 description.

4 / 5

Trigger Term Quality

Natural terms users would say are present: "Drizzle ORM", "Drizzle", "schema design", "migrations", "serverless database", "type-safe database layers" — matching the level-4 anchor ('PDF files, forms, document extraction'). Not a 5 because common variations users might say are missing, e.g. specific providers (Neon, PlanetScale, Turso), "Drizzle Kit", or "SQL".

4 / 5

Distinctiveness Conflict Risk

The Drizzle-specific naming ("Drizzle ORM", "with Drizzle") gives it a clear niche with minimal wrong-skill triggering, matching 'Mostly distinct; minor overlap risk with closely related skills'. It is not a 5 because generic capability words like "schema design", "migrations", and "serverless database integration" overlap with competing ORM skills (Prisma, TypeORM) if the Drizzle tokens are missed.

4 / 5

Total

16

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

plugins/AI-Agents-Safe-Coding-Skills/skills/drizzle-orm-expert/SKILL.md

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.