CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

database-migrations-sql-migrations

SQL database migrations with zero-downtime strategies for PostgreSQL, MySQL, and SQL Server. Focus on data integrity and rollback plans.

Quality

55%

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-claude/skills/database-migrations-sql-migrations/SKILL.md

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

SKILL.md
Quality
Evals
Security

Quality

Content

28%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 skill body is generic boilerplate: it names plausible deliverables but provides no executable guidance, no migration workflow, and references playbooks that do not exist. A user following it would have no concrete direction for an actual zero-downtime migration.

Suggestions

Replace the abstract Instructions with a concrete expand-contract workflow (e.g., add nullable column -> backfill in batches -> switch reads/writes -> drop old column) with explicit validation gates between phases.

Add executable SQL examples for the core cases: batched backfills, lock-safe index creation per engine, and a tested rollback script template.

Fix the dangling 'implementation playbooks' pointer by creating actual reference files (e.g., references/postgres.md, references/mysql.md) or removing the mention, and cut the fluff Resources/Context sentences.

DimensionReasoningScore

Conciseness

The body is short and does not over-explain known concepts, but it contains vague filler that earns no tokens: 'Focus on production-ready SQL migrations with... enterprise-grade safety mechanisms' in Resources, a Context section that restates the Overview, and boilerplate instructions. Not 4 because these padded passages could be cut without losing information.

3 / 5

Actionability

The Instructions section is pure abstraction ('Clarify goals, constraints, and required inputs. Apply relevant best practices and validate outcomes') with no SQL, commands, or concrete steps anywhere in the body, and 'suggest checking implementation playbooks' points to playbooks that do not exist in the bundle. This matches the 1 anchor: it describes rather than instructs.

1 / 5

Workflow Clarity

The numbered Output Format implies a rough order of deliverables, but no actual migration workflow is sequenced and there are no validation or rollback-execution checkpoints — for a destructive/batch database skill the missing feedback loops cap this at 3, and the near-total absence of defined steps lands it at 2.

2 / 5

Progressive Disclosure

The body has organized sections and no bulky inlined content, but its only pointer to deeper material ('implementation playbooks') is a dangling reference with no file, path, or link, and no bundle files exist. Some structure, but references are not clearly signaled — a 3, not 4.

3 / 5

Total

9

/

20

Passed

Description

61%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 communicates a clear, well-scoped domain with decent natural keywords, but it omits any 'use when' trigger clause and lists scope areas rather than concrete actions. It is serviceable but below the bar set by the good examples.

Suggestions

Append an explicit trigger clause, e.g., 'Use when the user mentions database migrations, schema changes, or zero-downtime deploys on PostgreSQL, MySQL, or SQL Server.'

Convert scope nouns into concrete actions: e.g., 'Write expand-contract migration scripts, generate rollback procedures, and run pre/post-migration validation.'

DimensionReasoningScore

Specificity

Names the domain ('SQL database migrations') with two focus areas ('zero-downtime strategies', 'rollback plans') and three concrete engines, but describes scope rather than listing several concrete actions. It matches the 3 anchor (domain plus 1-2 concrete actions) and not 4, since it never states what the skill actually does (e.g., write migration scripts, design expand-contract phases, validate).

3 / 5

Completeness

The 'what' is clear and specific, but the description contains no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. It is not 2 because the 'what' is concrete rather than vague.

3 / 5

Trigger Term Quality

Natural keywords users would say are present: 'SQL database migrations', 'PostgreSQL', 'MySQL', 'SQL Server', 'rollback plans'. It falls short of 5 because common variations like 'schema change', 'Postgres', 'zero-downtime deploy', or 'migration scripts' are missing.

4 / 5

Distinctiveness Conflict Risk

A clear niche (zero-downtime SQL migrations across three named engines) with minimal conflict risk against generic skills. Not 5 because it could still trigger for framework-oriented migration tasks (Flyway, Alembic, Django/Rails migrations) it does not explicitly scope itself against.

4 / 5

Total

14

/

20

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

plugins/AI-Agents-Safe-Coding-Skills-claude/skills/database-migrations-sql-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.