databases

Work with MongoDB (document database, BSON documents, aggregation pipelines, Atlas cloud) and PostgreSQL (relational database, SQL queries, psql CLI, pgAdmin). Use when designing database schemas, writing queries and aggregations, optimizing indexes for performance, performing database migrations, configuring replication and sharding, implementing backup and restore strategies, managing database users and permissions, analyzing query performance, or administering production databases.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Quality

Content

72%

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

A well-structured, highly actionable reference skill with excellent progressive disclosure and copy-paste-ready examples, weakened mainly by basic CRUD content Claude already knows and by destructive database workflows that lack explicit validation checkpoints.

Suggestions

Remove or condense the 'Common Operations' CRUD block and the redundant 'When to Use This Skill' list (which duplicates the description) to reclaim tokens and lift conciseness toward 3.

Add explicit validation/verification steps to the destructive workflows — e.g., run the migration in a dry-run/preview mode and verify backups can restore — so database operations include feedback loops and workflow clarity can reach 3.

For migrations and backups, show a check-then-apply sequence (validate schema, confirm row counts, test restore on a scratch DB) rather than a single one-shot command.

Dimension	Reasoning	Score
Conciseness	Mostly efficient reference-style content, but the 'When to Use This Skill' section duplicates the frontmatter description and the 'Common Operations' CRUD block (insertOne/find/updateOne/deleteOne and INSERT/SELECT/UPDATE/DELETE) re-teaches basic syntax Claude already knows; could be tightened. Not a 1 because there is no prose padding explaining what databases are.	2 / 3
Actionability	Abundant executable, copy-paste-ready code and commands — connection strings, mongosh/psql invocations, DDL/DML, index creation, and real script calls such as 'python scripts/db_migrate.py --db mongodb --generate "add_user_index"' — all referencing files that exist.	3 / 3
Workflow Clarity	Sequences exist (numbered Atlas setup, migration/backup/perf-check script calls) but database operations — migrations, backups, deletes — are destructive/batch and lack any explicit validation or verify-before-apply checkpoint, so workflow clarity is capped at 2 per the rubric's database-operations guideline. Not a 1 because steps are present and ordered.	2 / 3
Progressive Disclosure	SKILL.md is a concise overview that points to eight verified one-level-deep reference files and three scripts via a dedicated 'Reference Navigation' section with per-file descriptions; detailed CRUD/aggregation/indexing/admin content is appropriately split out rather than inlined.	3 / 3
	Total	10 / 12 Passed

Description

100%

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 strong, well-rounded description: it names the two systems and their concrete capabilities, provides an explicit 'Use when' trigger clause covering many natural scenarios, and stays in third-person voice with a distinct, low-conflict niche.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions — "designing database schemas, writing queries and aggregations, optimizing indexes..., performing database migrations, configuring replication and sharding, implementing backup and restore strategies, managing database users and permissions" — far exceeding the 'names domain and some actions' bar of a 2.	3 / 3
Completeness	Explicitly answers what ("Work with MongoDB... and PostgreSQL..." with capabilities) and when (an explicit "Use when designing database schemas..." clause with many triggers), satisfying the anchor for both; the present 'Use when' clause avoids the cap at 2.	3 / 3
Trigger Term Quality	Covers natural terms users would actually say ("queries and aggregations", "indexes", "migrations", "replication and sharding", "backup and restore", "database users and permissions") alongside the named products MongoDB and PostgreSQL, with no jargon-only or generic phrasing.	3 / 3
Distinctiveness Conflict Risk	A clear niche — two named database systems with database-specific triggers — that is unlikely to fire for non-database skills; voice is third person ("Work with..."), so no specificity penalty applies.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: mrgoonie/claudekit-skills
Path: .claude/skills/databases/SKILL.md
Commit: 80113d8

Reviewed: about 9 hours 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.