CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

drizzle-best-practices

Drizzle ORM patterns -- schema definition, type-safe queries, relations, migrations, transactions, upserts, prepared statements, and connection setup. Use when building or reviewing apps with Drizzle ORM, when setting up a new database with Drizzle, when writing queries or migrations, or when configuring Drizzle for production.

1.60x
Quality

84%

Does it follow best practices?

Impact

98%

1.60x

Average score across 5 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is tessl-labs/drizzle-best-practices

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, Drizzle-specific reference with excellent executable code and current tooling syntax. Its weaknesses are structural: no validation/feedback loop in the migration workflow despite database operations, and a monolithic single-file layout with no progressive disclosure into reference files, plus rule repetition across three formats.

Suggestions

Add validation checkpoints to the migration workflow: review the generated SQL in the ./drizzle output before running 'drizzle-kit migrate', apply migrations to a staging copy first, and state how to recover when a migration fails partway (the rubric caps database/batch workflows without feedback loops at workflow_clarity 3).

Split dialect-specific material (the PostgreSQL schema and connection variants, and the detailed upsert patterns) into a references/ file (e.g., references/dialects.md) linked one level deep, so SKILL.md serves as an overview rather than a monolithic ~430-line file.

Trim the triple repetition of each rule (inline code comment + 'Key rules' bullet + final Checklist): keep the checklist as the single consolidated rule list and compress the per-section bullets to only the rules not already shown in code.

DimensionReasoningScore

Conciseness

The body is dense and mostly code with Drizzle-specific non-obvious rules ('Drizzle does NOT auto-index foreign keys', 'SQLite has foreign keys OFF by default'), assuming Claude's competence rather than explaining basics. It is not 5 because key rules are stated three times each (inline code comments, 'Key rules' bullet lists, and the final Checklist), and the schema section repeats near-identical table definitions for the SQLite and PostgreSQL variants.

4 / 5

Actionability

Every section contains complete, copy-paste-ready TypeScript and shell commands: full schema definitions, current drizzle-kit commands ('npx drizzle-kit generate' / 'migrate' / 'push'), atomic upsert code, transaction patterns, and connection setup with pragmas. This matches the anchor for fully executable guidance covering the common cases; not 4 because there are no significant gaps in the code shown.

5 / 5

Workflow Clarity

The migration sequence is listed (define schema, configure dialect, generate, migrate, commit files) and 'push' is correctly gated to prototyping, but there are no validation checkpoints: no instruction to review the generated SQL before applying, verify migration success, or recover from a failed migration. Per the rubric, database operations lacking feedback loops cap this at 3; it is not 2 because the sequence itself is coherent and well-ordered.

3 / 5

Progressive Disclosure

The body has clear section headers, a summary checklist, and verifier links, so structure is present. However, the entire ~430-line reference (including dialect-specific schema/connection variants and detailed upsert patterns) is inlined in one file with no in-bundle reference files at all (no references/, scripts/, or assets/ exist), so content that could be split out is inline and navigation is single-file only. Not 4 because a file this size with zero one-level-deep reference split exceeds 'minor organization gaps'.

3 / 5

Total

15

/

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 description: specific capability list, explicit multi-scenario 'Use when...' triggers, third-person voice, and a clearly distinct niche. The only minor gap is that a few natural trigger synonyms live in the keywords field rather than the description text.

DimensionReasoningScore

Specificity

The description lists eight concrete, specific capabilities ('schema definition, type-safe queries, relations, migrations, transactions, upserts, prepared statements, and connection setup'), comprehensively covering the skill's scope with no vague filler. This matches the anchor for multiple specific concrete actions with comprehensive coverage, and is not level 4 because no meaningful capability gaps remain.

5 / 5

Completeness

It explicitly answers both questions: the 'what' is the enumerated list of Drizzle ORM patterns, and the 'when' is a concrete 'Use when...' clause with four distinct trigger scenarios. This matches the top anchor exactly; level 4 would require the 'when' to be less explicit or specific, which it is not.

5 / 5

Trigger Term Quality

Good natural-phrase coverage: 'building or reviewing apps with Drizzle ORM', 'setting up a new database', 'writing queries or migrations', 'configuring Drizzle for production' are phrases users would naturally say. It is not 5 because some natural terms and synonyms (e.g., 'drizzle-kit', 'Drizzle queries', 'database schema') appear only in the keywords field, not in the description itself.

4 / 5

Distinctiveness Conflict Risk

'Drizzle ORM' is a clearly named niche with distinct, unambiguous triggers; there is minimal risk of this firing for a non-Drizzle database skill. Not 4 because the overlap risk with generic SQL/ORM skills is negligible given the repeated explicit 'Drizzle' naming.

5 / 5

Total

19

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

relative_links

Relative link issues: 3 suspicious

Warning

Total

14

/

16

Passed

Repository

Voltaire405/kva-landing

Path

.tessl/tiles/tessl-labs/drizzle-best-practices/skills/drizzle-best-practices/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.