database-migrations

Buenas prácticas de migración de base de datos para cambios de esquema, migraciones de datos, rollbacks y despliegues de tiempo cero en PostgreSQL, MySQL y ORMs comunes (Prisma, Drizzle, Kysely, Django, TypeORM, golang-migrate).

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

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

A highly actionable, well-sequenced migration guide with strong validation structure, scoring top marks on actionability and workflow clarity. Its weaknesses are conciseness and progressive disclosure: it is a long monolithic file with no reference bundle, where per-ORM detail could be split out.

Suggestions

Split the per-ORM/per-DB sections (Prisma, Drizzle, Kysely, Django, golang-migrate) into separate reference files under references/ and keep SKILL.md as a concise overview with one-level-deep links, improving both progressive disclosure and conciseness.

Tighten redundant code comments and consolidate the repeated safe-column-add pattern that reappears across sections to reduce token load.

Add an explicit feedback-loop note (validate -> fix -> retry) to the batched backfill and expand-contract workflows to make the already-present validation steps more actionable on failure.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining concepts Claude already knows and mostly earns its tokens with actionable patterns, but at ~430 lines covering six ORMs each with workflow + schema + extra examples it is verbose and could be tightened or split. This fits the score-2 anchor of mostly efficient but could be tightened rather than the lean score-3 anchor.	2 / 3
Actionability	Everything is concrete and copy-paste ready — real SQL (CONCURRENTLY, batched DO-$$ loops), real CLI commands (prisma/drizzle/kysely/django/golang-migrate), and complete ORM code. This matches the score-3 anchor of fully executable, specific examples.	3 / 3
Workflow Clarity	Multi-step processes are clearly sequenced (expand-contract Paso 1-4, zero-downtime Fase 1-3) with explicit validation: a pre-flight safety checklist, a "Verificar consistencia de datos" checkpoint in Fase 2, and a dirty-state recovery command ("force VERSION"). This matches the score-3 anchor of clear sequence with validation and error recovery, so the destructive/batch cap at 2 does not apply.	3 / 3
Progressive Disclosure	No bundle files exist and the entire body is inline — ~400 lines of per-ORM/per-DB reference that could be split into separate files, with no one-level-deep references. It is well-organized with clear headers (better than the score-1 wall of text), so it fits the score-2 anchor of structured but with content that should be separate kept inline.	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-targeted description that names concrete actions and tools, giving it strong distinctiveness and trigger coverage. Its main weakness is the absence of an explicit "Use when..." trigger clause, which caps completeness at 2.

Suggestions

Add an explicit "Use when..." ("Usar cuando...") clause naming the trigger situations, e.g. schema changes, data backfills, or zero-downtime deploys, to lift completeness to 3.

Consider including the user-facing phrasings that trigger this skill (e.g. "migración", "rollback", "zero-downtime") in a when-clause rather than only as capabilities.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "cambios de esquema", "migraciones de datos", "rollbacks", "despliegues de tiempo cero" — plus named tools, matching the score-3 anchor for several specific concrete actions. It is third person ("Buenas prácticas de...") so no voice penalty applies; it is not merely naming a domain like the score-2 example.	3 / 3
Completeness	It clearly answers "what" (best practices for schema/data migrations, rollbacks, zero-downtime deploys) but has no "Use when..." clause or equivalent explicit trigger guidance, which the rubric caps at 2. This matches the score-2 anchor of having "what" with "when" only implied.	2 / 3
Trigger Term Quality	Natural terms a user would say are well covered — "migración de base de datos", "rollbacks", "despliegues de tiempo cero", plus concrete tool names (PostgreSQL, MySQL, Prisma, Drizzle, Kysely, Django, TypeORM, golang-migrate). This matches the score-3 anchor of good coverage rather than the sparse score-2 example.	3 / 3
Distinctiveness Conflict Risk	The scope is a clear niche — database migrations tied to specific engines and ORMs — unlikely to trigger for unrelated skills, matching the score-3 anchor. It is far more specific than the generic, overlapping score-2 example.	3 / 3
	Total	11 / 12 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Commit: 4130457

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.