generating-database-seed-data

Process this skill enables AI assistant to generate realistic test data and database seed scripts for development and testing environments. it uses faker libraries to create realistic data, maintains relational integrity, and allows configurable data volumes. u... Use when working with databases or data models. Trigger with phrases like 'database', 'query', or 'schema'.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

57%

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

The content is highly actionable with concrete Faker calls and output formats, and the workflow is well sequenced with a validation step, but it is a monolithic single-file document that ignores its own bundle structure and lacks an explicit validation feedback loop.

Suggestions

Move the Faker column-mapping table, the Examples, and the error-handling reference into bundled files under references/ or assets/ and link to them from the body so SKILL.md stays a lean overview.

Weave the error-handling guidance into the workflow as explicit 'if validation fails, fix and re-run from step N' feedback loops rather than a separate table.

Reference the existing bundle scripts (seed_database.py, validate_seed_data.py) inline where relevant so the available tooling is discoverable.

Dimension	Reasoning	Score
Conciseness	The body is mostly actionable and free of basic-concept padding, but the long Examples section, the verbose error-handling table, and explanatory asides (e.g., Zipf distribution rationale) could be tightened to respect the token budget.	2 / 3
Actionability	Provides fully executable, copy-paste-ready guidance: concrete Faker calls (faker.person.firstName(), faker.date.between({from,to})), specific output formats (raw SQL INSERT, prisma.user.createMany, knex insert), and exact commands (ON CONFLICT DO NOTHING, PostgreSQL COPY, batch inserts).	3 / 3
Workflow Clarity	Ten numbered steps are clearly sequenced and step 10 provides validation checks, but the validate->fix->re-validate feedback loop is not framed as an explicit checkpoint loop within the workflow — recovery guidance sits in a separate error-handling table rather than inline checkpoints.	2 / 3
Progressive Disclosure	The body is monolithic: overview, prerequisites, instructions, output, error handling, examples, and resources are all inline, and it never references the existing bundle directories (references/, scripts/, assets/) or signals their contents, matching the monolithic-wall-of-text anchor.	1 / 3
	Total	8 / 12 Passed

Description

77%

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 covers both what the skill does and when to use it with several concrete actions, but it is marred by garbled/truncated text ('Process this skill enables...', 'it uses', 'u...') and trigger terms that are too generic to distinguish it from other database skills.

Suggestions

Fix the malformed opening clause and the truncated 'u...' fragment so the description reads as clean third-person prose.

Replace generic triggers ('database', 'query') with skill-specific natural terms users would say when needing seed data — 'seed data', 'test data', 'fixtures', 'populate database'.

Rephrase to consistent third person ('Generates realistic test data and database seed scripts...') to avoid the 'this skill enables AI assistant' construction.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions such as 'generate realistic test data and database seed scripts', 'maintains relational integrity', and 'configurable data volumes', matching the multiple-specific-actions anchor despite garbled phrasing at the start.	3 / 3
Completeness	Explicitly states both what it does ('generate realistic test data and database seed scripts') and when to use it ('Use when working with databases or data models. Trigger with phrases like...'), satisfying the explicit-what-and-when anchor.	3 / 3
Trigger Term Quality	Provides relevant keywords ('database', 'query', 'schema') but omits the most natural variations for this skill — 'seed', 'seed data', 'test data', 'fixtures' — and 'query' is a stretch for a seeding task, so it lands at 'some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	The niche (seed data) is clear, but the triggers 'database', 'query', and 'schema' are generic database terms that would also fire for general database/query skills, creating overlap rather than a distinct, conflict-free trigger set.	2 / 3
	Total	10 / 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.