data-layer-contracts

Defines the schema-to-factory-to-seeder contract chain — NOT NULL alignment, factory/seeder ownership boundaries, and schema drift rules

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/data-layer-contracts/SKILL.md

Quality

Content

87%

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

The body is a tight, well-organized rule reference with concrete, actionable contract rules and no fluff. Its only real gap is the lack of an explicit validation feedback loop for the destructive database operations it governs.

Suggestions

Add an explicit validation feedback loop for the destructive DB operations: after `migrate:fresh` + `seed`, if SQLSTATE constraint violations or factory/seeder mismatches appear, state the fix→re-validate→proceed steps so workflow clarity is not capped at 2.

Optionally render the contract chain as an ordered checklist (migration change → update factory → update seeder → run migrate:fresh + seed → verify) with a clear checkpoint before tests run.

Dimension	Reasoning	Score
Conciseness	The body is lean MUST/MUST NOT/SHOULD rule lists with no padding or explanation of basic concepts Claude already knows (it never explains what a factory or migration is), so every token earns its place at the level-3 anchor.	3 / 3
Actionability	As an instruction-only contracts skill it gives precise, specific, complete rules (e.g. every NOT NULL column must be covered by a factory, seeder, or explicit DB default) plus one concrete command (`migrate:fresh` + `seed`); per the rubric's instruction-only note, the absence of code is not penalized when guidance is this actionable.	3 / 3
Workflow Clarity	The schema→factory→seeder chain is implied and a validation step is mentioned (migrate:fresh + seed before tests), but there is no explicit validate→fix→re-validate feedback loop for these destructive/batch DB operations, which the rubric caps at 2.	2 / 3
Progressive Disclosure	The skill is under 50 lines with no need for external references and is cleanly organized into well-labeled sections (Schema Contract, Factory Rules, Seeder Rules, Drift Triggers, Identity Rule), meeting the level-3 anchor for simple well-organized skills.	3 / 3
	Total	11 / 12 Passed

Description

57%

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 is clearly scoped to a distinct niche and uses real domain terms, but it describes an abstract contract chain rather than concrete actions and omits any explicit "Use when..." trigger guidance. Adding trigger phrasing and concrete verbs would lift the capped dimensions.

Suggestions

Add an explicit 'Use when...' trigger clause, e.g. 'Use when modifying migrations, factories, or seeders, or diagnosing schema drift / NOT NULL mismatches', to raise completeness and trigger discoverability.

Lead with concrete actions instead of the abstract 'Defines the contract chain' — e.g. 'Aligns NOT NULL columns across migrations, factories, and seeders; flags schema drift between them' — to improve specificity.

Surface common user phrasings as trigger terms such as 'factory not matching migration', 'seeder failing on NOT NULL column', or 'schema drift' to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names a concrete domain and specific sub-aspects ("NOT NULL alignment, factory/seeder ownership boundaries, and schema drift rules"), but the leading verb "Defines the ... contract chain" is a single abstract action rather than a list of multiple concrete actions, so it falls short of the level-3 anchor.	2 / 3
Completeness	It clearly answers "what" (defines the schema→factory→seeder contract chain) but provides no "Use when..." or equivalent trigger guidance, so per the rubric completeness is capped at 2.	2 / 3
Trigger Term Quality	Real developer terms appear ("factory", "seeder", "schema drift", "NOT NULL"), but the phrasing is jargon-heavy and lacks common variations or natural user phrasings, and there is no trigger framing to broaden coverage.	2 / 3
Distinctiveness Conflict Risk	The migration→factory→seeder drift niche is highly specific and unlikely to overlap with other skills, matching the level-3 anchor of a clear distinct niche.	3 / 3
	Total	9 / 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: Bottelet/DaybydayCRM
Path: .claude/skills/data-layer-contracts/SKILL.md
Commit: fb83b36

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.