managing-database-recovery

Process use when you need to work with database operations. This skill provides database management and optimization with comprehensive guidance and automation. Trigger with phrases like "manage database", "optimize database", or "configure database".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

77%

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 executable commands and a well-sequenced, validated workflow for destructive database operations. Its main weakness is progressive disclosure: relevant bundled scripts are present but never signaled from the body, leaving the skill more monolithic than necessary.

Suggestions

Reference the bundled scripts inline at the relevant steps (e.g. step 7 'See scripts/pitr_restore.sh for PITR', step 8 'See scripts/validate_backup.sh and scripts/test_recovery.sh') so the overview points to detailed tools one level deep.

Trim explanatory prose like RPO/RTO gloss and the 'for databases larger than 10GB' aside where the surrounding commands already imply the guidance.

Consider moving the error-handling table and/or the examples into a references file to keep SKILL.md a lean overview, and link to it explicitly.

Dimension	Reasoning	Score
Conciseness	The body is mostly command-dense and efficient, but includes some prose that could be tightened (e.g. 'ensuring Recovery Point Objective (RPO) and Recovery Time Objective (RTO) targets are met' and 'for databases larger than 10GB'), placing it at the 'mostly efficient but could be tightened' anchor rather than fully lean.	2 / 3
Actionability	Provides fully executable, copy-paste-ready commands throughout (e.g. `pg_basebackup -D /backups/base -Ft -z -P`, `aws s3 cp /backups/base.tar.gz s3://...`, `recovery_target_time = '2024-01-15 14:30:00'`) plus concrete examples, matching the 'fully executable code/commands' anchor.	3 / 3
Workflow Clarity	A clear 10-step sequence with explicit validation checkpoints ('Verify archiving works', 'Test recovery by restoring to a separate server', 'Automate backup verification') and feedback loops via the error-handling table; destructive database operations have validation, satisfying the top anchor and avoiding the cap at 2.	3 / 3
Progressive Disclosure	Sections are well-organized, but directly relevant bundle scripts (scripts/pitr_restore.sh, validate_backup.sh, failover.sh, test_recovery.sh) exist yet are never referenced or signaled in the body, so content that should point to the bundle is described inline, matching the 'references present but not clearly signaled' anchor rather than the well-signaled 3.	2 / 3
	Total	10 / 12 Passed

Description

50%

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 includes explicit trigger guidance but leans on vague, padded language ('comprehensive guidance and automation') and near-duplicate trigger phrases, weakening both specificity and distinctiveness. The 'what' is only weakly answered, capping completeness below the top anchor.

Suggestions

Replace vague phrases like 'comprehensive guidance and automation' with concrete capabilities such as 'Plan and execute PostgreSQL/MySQL backups, WAL archiving, PITR, and disaster recovery testing'.

Diversify trigger phrases beyond the single 'X database' pattern to include natural variations like 'database backup', 'point-in-time recovery', 'restore database', or 'PITR'.

Rewrite in clean third person (e.g. 'Use when...') and lead with the concrete 'what' before the triggers, so both what and when are answered clearly.

Dimension	Reasoning	Score
Specificity	Names the database domain and a few actions ('database management and optimization') but pads with vague fluff ('comprehensive guidance and automation') rather than listing multiple concrete capabilities, so it sits at the 'names domain and some actions' anchor rather than 3.	2 / 3
Completeness	It has an explicit 'Trigger with phrases like' clause covering 'when', but the 'what' is weakly answered with generic phrasing ('provides database management and optimization') rather than a clear concrete description, so it does not reach the 'clearly answers both what AND when' anchor of 3.	2 / 3
Trigger Term Quality	Provides 'manage database', 'optimize database', and 'configure database' which are plausible user phrases, but they are near-identical variants of one pattern and miss common variations, matching the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	The trigger phrases are generic database terms that would overlap with many other database skills; it is somewhat specific to database operations but lacks a distinct niche, matching the 'somewhat specific but could still overlap' anchor.	2 / 3
	Total	8 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 2cafb23

Reviewed: about 15 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.