CtrlK
BlogDocsLog inGet started
Tessl Logo

database-migration

Master database schema and data migrations across ORMs (Sequelize, TypeORM, Prisma), including rollback strategies and zero-downtime deployments.

56

Quality

65%

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/database-migration/SKILL.md

The canonical home for this skill is database-migration in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

65%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.

The body is highly actionable with comprehensive executable migration examples, but it is weighed down by generic boilerplate, missing validation feedback loops on destructive operations, and broken/nonexistent bundle references that should hold the inlined detail.

Suggestions

Move the bulk of ORM/schema/data/rollback/zero-downtime code examples into the referenced reference files and keep SKILL.md as a lean overview, so progressive disclosure is real rather than dangling.

Create the missing bundle files (references/orm-switching.md, schema-migration.md, etc., assets/*, scripts/*) and fix the 'resources/' vs 'references/' path mismatch for implementation-playbook.md.

Replace the generic Instructions/Do-not-use boilerplate with an explicit migration workflow that includes validation checkpoints (migrate → verify on staging → on failure, rollback) to satisfy the destructive-operations feedback-loop requirement.

DimensionReasoningScore

Conciseness

Mostly efficient code-forward content, but it includes generic boilerplate ("Clarify goals, constraints, and required inputs", "Apply relevant best practices") and the large volume of inlined examples could be tightened or offloaded to references.

3 / 5

Actionability

Provides fully executable, copy-paste-ready migration code for Sequelize, TypeORM, and Prisma with concrete run/rollback commands, covering the common migration cases comprehensively.

5 / 5

Workflow Clarity

Phased sequences exist (zero-downtime Phase 1-5, column-rename Step 1-3) and one checkpoint example verifies a count, but the primary destructive migration workflow lacks explicit validate→fix→retry feedback loops, capping the score at 3 per the destructive-operations rule.

3 / 5

Progressive Disclosure

Has clear section headers and a Resources section, but large bodies of example code that belong in separate reference files are inlined, and the referenced files (references/*.md, assets/*, scripts/*) do not exist; the body also points to a misnamed 'resources/implementation-playbook.md'.

3 / 5

Total

14

/

20

Passed

Description

66%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.

The description is specific and well-targeted with concrete actions and natural trigger terms, but it lacks an explicit "Use when..." trigger clause, which limits its completeness score. It is otherwise distinct and low-conflict.

Suggestions

Add an explicit 'Use when...' clause naming trigger phrases (e.g., 'Use when migrating between ORMs, changing schemas, or needing zero-downtime DB deploys') to raise completeness.

Include a couple of natural synonyms or file extensions users might say (e.g., 'schema changes', '.prisma', 'migration files') to broaden trigger-term coverage.

Rephrase 'Master' to a third-person descriptive verb form ('Performs', 'Manages') to align with the rubric's preferred voice.

DimensionReasoningScore

Specificity

Names multiple concrete actions — "schema and data migrations", "rollback strategies", "zero-downtime deployments" across three named ORMs — giving strong, specific coverage with only minor gaps (no mention of seeding or replication).

4 / 5

Completeness

Has a clear "what" but no "Use when..." clause or equivalent explicit trigger guidance, capping completeness at 3 per the rubric guideline.

3 / 5

Trigger Term Quality

Includes natural terms users would say ("database migration", "schema migration", "rollback", "zero-downtime") and named ORMs, though a few common synonyms or extensions are absent.

4 / 5

Distinctiveness Conflict Risk

The named ORMs (Sequelize, TypeORM, Prisma) plus rollback/zero-downtime framing carve a mostly distinct niche with only minor overlap risk against general DB-admin skills.

4 / 5

Total

15

/

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.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

referenced_paths_exist

Referenced path issues: 7 missing

Warning

Total

14

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.