CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

drizzle-migrations

Use when changing libs/database/src/schema.ts, adding Drizzle migrations, debugging drizzle-kit drift, or deciding between auto-generated and custom SQL migrations. Includes the post-#867 baseline-reset rule.

67

Quality

84%

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

90%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 tight, command-dense operational guide that assumes Claude's competence and concentrates entirely on repo-specific rules and decision criteria. The main residual gaps are validation steps phrased as manual 'review' rather than executable checks, and an all-in-one layout slightly past the size where pure inline structure is ideal.

DimensionReasoningScore

Conciseness

The body is lean throughout: no explanation of what Drizzle or migrations are, every sentence carries a repo-specific rule or command ('never copy-paste a snapshot file without refreshing both IDs'). Each token earns its place against the 'assumes Claude's competence' anchor.

5 / 5

Actionability

Guidance is copy-paste ready across the board: 'pnpm db:generate', 'pnpm exec drizzle-kit generate --custom --name <name>', 'pg_dump --schema-only', 'pnpm docker:reset', plus concrete decision lists for choosing migration type and concrete drift signals. The common cases (generate, custom SQL, baseline reset) are each covered by specific commands.

5 / 5

Workflow Clarity

The default workflow has a review checkpoint (step 3, 'Review generated SQL and snapshot metadata together') and the drift rule ('stop and assume drift until proven otherwise') provides an error-recovery loop, and the destructive baseline-reset includes 'Review against the schema dump'. However, validation is described as 'review' rather than explicit executable checks (e.g., no command to verify the clean-tree no-op invariant), leaving minor gaps versus the fully-explicit-validation anchor.

4 / 5

Progressive Disclosure

The skill has no bundle files, and at ~90 lines of dense rules it is appropriately organized into well-labeled sections (trigger, workflow, migration type, round-trip rule, invariants, triage, baseline reset) with no content that clearly demands a separate file. It is above the under-50-line threshold where inline-only structure scores 5, and the baseline-reset procedure could arguably live in a reference file, so it sits at 'good structure, minor organization gaps' rather than the clear-overview-with-signaled-references anchor.

4 / 5

Total

18

/

20

Passed

Description

70%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 highly specific, low-conflict trigger description rooted in exact file paths and tool names, with excellent 'when' guidance. Its main weakness is that it never states what the skill actually contains beyond the single baseline-reset rule reference, leaving the 'what' only weakly implied.

Suggestions

Add a short 'what' clause before the 'Use when' list, e.g. 'Operational guide for MoltNet Drizzle database migrations: choosing migration types, keeping snapshots in sync, and resetting the migration baseline.'

Include a few more natural trigger phrases users might type, such as 'pnpm db:generate', 'drizzle snapshot', or 'migration drift'.

Briefly name the core deliverables (migration-type decision rules, snapshot invariants, drift triage) so the description communicates capability, not just trigger conditions.

DimensionReasoningScore

Specificity

The description names several concrete, specific triggers with exact paths and tool names — 'changing libs/database/src/schema.ts, adding Drizzle migrations, debugging drizzle-kit drift, or deciding between auto-generated and custom SQL migrations' — but it never states what the skill itself does, so coverage is several specific items with a gap rather than comprehensive.

4 / 5

Completeness

The 'when' is explicit and rich ('Use when changing... adding... debugging... deciding...'), but the 'what' is only weakly present — 'Includes the post-#867 baseline-reset rule' hints at content without saying what the skill provides. This sits between anchor 2 ('only when' present) and a full what+when pair, matching neither anchor cleanly.

3 / 5

Trigger Term Quality

Natural terms a user on this repo would say are well covered: 'schema.ts', 'Drizzle migrations', 'drizzle-kit drift', 'custom SQL migrations'. A few plausible variations are missing (e.g., 'db:generate', 'snapshot', 'pnpm db:*' commands), keeping it just short of the comprehensive-with-synonyms anchor 5.

4 / 5

Distinctiveness Conflict Risk

The niche is unambiguous: Drizzle migrations for this specific codebase, anchored by an exact file path, tool name, and an issue reference (#867). It would not plausibly trigger any other skill, matching the clear-niche anchor.

5 / 5

Total

16

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

getlarge/themoltnet

Path

.agents/skills/drizzle-migrations/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.