CtrlK
BlogDocsLog inGet started
Tessl Logo

database-migrations

Database migration best practices for schema changes, data migrations, rollbacks, and zero-downtime deployments across PostgreSQL, MySQL, and common ORMs (Prisma, Drizzle, Django, TypeORM, golang-migrate). Use when planning or implementing database schema changes.

67

Quality

81%

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

80%

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

A highly actionable, concise reference of executable migration patterns across multiple databases and ORMs, held back by the absence of explicit error-recovery feedback loops and by its monolithic structure with no progressive disclosure into reference files.

Suggestions

Add an explicit validate→fix→retry loop for migration application (e.g., apply on a prod-sized copy, inspect errors, fix the migration, re-run) to lift workflow clarity past the database-operations cap.

Move the per-ORM detailed sections into one-level-deep reference files (e.g., references/prisma.md, references/django.md) and keep SKILL.md as an overview with clearly signaled links, improving progressive disclosure.

DimensionReasoningScore

Conciseness

The body is action-dense — concrete SQL, bash, and ORM code with minimal prose — and does not explain concepts Claude already knows (no "what is an ORM" filler), so most tokens earn their place.

3 / 3

Actionability

Provides fully executable, copy-paste-ready commands and code for each tool (e.g., `npx prisma migrate deploy`, `CREATE INDEX CONCURRENTLY`, batched `DO $$ … LOOP` blocks), matching the score-3 anchor.

3 / 3

Workflow Clarity

The expand-contract phases and pre-flight safety checklist give a clear sequence with verification, but there is no explicit validate→fix→retry feedback loop; for database operations the rubric caps workflow clarity at 2 when such loops are missing.

2 / 3

Progressive Disclosure

No bundle files exist and the ~430-line SKILL.md is monolithic, with per-ORM sections (e.g., the long Kysely programmatic migrator) that could be split into one-level-deep reference files; it is well-organized but content that should be separate is inline, matching score 2 rather than 3.

2 / 3

Total

10

/

12

Passed

Description

82%

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 specific, well-scoped description with strong trigger terms and a clear niche, weakened only by the absence of an explicit "Use when…" clause that would lift completeness to the top level.

Suggestions

Append an explicit "Use when…" clause listing activation triggers (e.g., "Use when creating or altering tables, running data backfills, or planning zero-downtime schema changes") to satisfy the completeness dimension.

Add a couple of natural user phrasings (e.g., "migrate the database", "add a column without downtime") to broaden trigger-term coverage beyond the current technical vocabulary.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "schema changes, data migrations, rollbacks, and zero-downtime deployments" — plus named databases and ORMs, matching the score-3 anchor for multiple specific concrete actions.

3 / 3

Completeness

It clearly answers "what" but has no "Use when…" clause or equivalent explicit trigger guidance, so per the rubric guideline completeness is capped at 2 rather than 3.

2 / 3

Trigger Term Quality

Natural terms a user would actually say ("database migration", "schema changes", "rollbacks", "zero-downtime deployments", plus PostgreSQL/MySQL and ORM names) give good coverage of common phrasings.

3 / 3

Distinctiveness Conflict Risk

A clear niche (production DB migrations across named tools) with distinct triggers makes it unlikely to fire for the wrong skill.

3 / 3

Total

11

/

12

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
affaan-m/ECC
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.