managing-database-partitions

Process use when you need to work with database partitioning. This skill provides table partitioning strategies with comprehensive guidance and automation. Trigger with phrases like "partition tables", "implement partitioning", or "optimize large tables".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

80%

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 and concise, packed with executable SQL for partitioning, migration, and maintenance across PostgreSQL and MySQL. Its weaknesses are incomplete validation/rollback checkpoints around destructive operations and a monolithic structure that ignores the stubbed bundle files.

Suggestions

Add explicit validation/rollback checkpoints to the destructive workflows: before the partition drop/detach in step 9, require verifying the partition is past retention and backed up; for the migration rename in step 6, document a rollback path if the rename fails.

Move reusable material into the bundled files and reference them from the body — e.g. put the partition DDL templates into assets/partition_template.sql and the design/maintenance logic into scripts/partition_design.py, partition_maintenance.py, then link to them so progressive disclosure is real rather than stubbed READMEs.

Tighten the redundancy between the Overview and step 3 so the four strategies are described once with the 'when to use' rationale, avoiding the duplicate enumeration.

Dimension	Reasoning	Score
Conciseness	The body is dense and actionable, assuming Claude's competence with no padding or explanation of basic database concepts; the only mild waste is that the Overview and step 3 both enumerate the four strategies, but every section earns its place, keeping it at 3 rather than 2.	3 / 3
Actionability	It provides concrete, executable SQL throughout (e.g. 'CREATE TABLE orders (...) PARTITION BY RANGE (created_at)', 'ALTER TABLE orders DETACH PARTITION orders_2022_01', 'INSERT INTO orders_partitioned SELECT * FROM orders_old WHERE...') that is copy-paste ready, matching the fully-executable anchor.	3 / 3
Workflow Clarity	Steps 1-10 are clearly sequenced and the migration includes a verify checkpoint ('Verify row counts match') and step 10 verifies pruning, but destructive/batch operations have validation gaps (no rollback plan for the atomic rename, no pre-drop backup/retention verification before detaching/deleting partitions), triggering the cap-at-2 rule for destructive workflows; not a 1 because the sequence and some checkpoints are present.	2 / 3
Progressive Disclosure	The body is well-sectioned (so not a monolithic wall of text), but it is a single monolithic file with no signaled references to the bundle, and the bundle directories contain only README stubs listing files that do not actually exist; content that should be split out (SQL templates, design/maintenance scripts) is described inline rather than in the stubbed assets/scripts, matching the 'some structure but content that should be separate is inline' anchor.	2 / 3
	Total	10 / 12 Passed

Description

90%

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 clearly states its niche and includes explicit, natural trigger guidance covering both what and when, which is its main strength. Its weakness is the vague, fluff-heavy action language ('comprehensive guidance and automation') that names no concrete partitioning actions.

Dimension	Reasoning	Score
Specificity	It names the domain ('table partitioning strategies') and gestures at actions, but the only action verbs are abstract ('provides... strategies with comprehensive guidance and automation'), which reads as fluff rather than concrete actions like 'create range partitions, migrate data, detach old partitions'; not a 1 because the domain is clearly named, not a 3 because no specific concrete actions are listed.	2 / 3
Completeness	It answers what ('provides table partitioning strategies') and when with an explicit trigger clause ('Process use when you need to work with database partitioning... Trigger with phrases like...'), satisfying the 'Use when' requirement that would otherwise cap at 2.	3 / 3
Trigger Term Quality	Explicit natural trigger phrases ('partition tables', 'implement partitioning', 'optimize large tables') are phrases a user would plausibly say when needing this skill, giving good coverage; not below 3 because the terms are natural and on-domain.	3 / 3
Distinctiveness Conflict Risk	Database partitioning is a well-defined niche with distinct triggers unlikely to conflict with most skills; the only mild overlap risk is 'optimize large tables' (could overlap with generic indexing/optimization), but the dominant framing is specific enough to stay at 3 rather than 2.	3 / 3
	Total	11 / 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: 2 days 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.