ci-schema-invariant-gate

Ensures correct execution order of migrations, seeders, and tests in CI

Quality

76%

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/ci-schema-invariant-gate/SKILL.md

Quality

Content

87%Weight 40%Scale 1-5

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

The body is concise, actionable, and well-structured for a single-purpose CI-ordering skill, with copy-paste-ready commands. Its one weakness is workflow clarity: a destructive fresh-migrate CI step runs without any validation checkpoint between setup and test execution.

Suggestions

Add an explicit validation/checkpoint step between 'migrate:fresh --seed' and 'test' (e.g. verify migrations reported success and seed exit code 0 before proceeding to tests).

Define expected feedback behavior when migrate or seed fails mid-pipeline rather than only routing failures to other skills, so the workflow has a recovery loop.

Optionally state how CI should detect and halt on a non-fresh/cached database state to make the determinism requirement enforceable rather than declarative.

Dimension	Reasoning	Score
Conciseness	The body is lean and efficient with no padding or explanation of concepts Claude already knows; every section (execution order, responsibility, failure behavior, determinism, core principle) earns its place. It matches the 'lean and efficient; every token earns its place' anchor and is not 4 because there are no over-explanation instances to trim.	5 / 5
Actionability	It gives fully executable, copy-paste-ready commands ('php artisan migrate:fresh --seed' then 'php artisan test') plus an explicit determinism rule covering the core cases. It matches the 'fully executable; copy-paste ready' anchor and is not 4 because there are no meaningful gaps in the primary guidance.	5 / 5
Workflow Clarity	The strict sequence and determinism requirement are clearly listed, but this is a batch/destructive CI operation (migrate:fresh drops all tables) with no validation checkpoint between migrate and test, and the skill explicitly disclaims failure interpretation. Per the guideline, missing validation in destructive/batch operations caps workflow_clarity at 3, so it cannot score 4 despite clear sequencing.	3 / 5
Progressive Disclosure	This is a simple, single-purpose skill under 50 lines with no need for external references and well-organized numbered sections; the guideline allows such skills to score 5 on progressive disclosure. There are no nested references to penalize, and not 4 because structure is appropriately complete.	5 / 5
	Total	18 / 20 Passed

Description

53%Weight 40%Scale 1-5

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 what the skill does but omits any 'when to use it' trigger guidance, which caps completeness at 3. Trigger-term coverage is domain-relevant but lacks natural conversational phrasing users would say.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases, e.g. 'Use when setting up CI for a Laravel app or when the user asks to ensure migrations and seeders run before tests.'

Broaden trigger terms to include synonyms and file/concept markers users actually say (e.g. 'CI pipeline', 'test ordering', 'fresh database', 'artisan test').

Mention 1-2 additional concrete actions (e.g. 'enforces determinism by requiring a fresh seed') to lift specificity above a single action.

Dimension	Reasoning	Score
Specificity	Names the domain (CI, migrations, seeders, tests) and one concrete action (execution ordering), but coverage is single-focused rather than comprehensive. It is below 4 because only one action is described, and above 2 because it is more than minimal/generic.	3 / 5
Completeness	It has a clear 'what' (ensures execution order) but no 'when' / 'Use when...' clause, which the guideline caps at 3. Not 2 because the 'what' is clear rather than vague, and not 4 because the 'when' is entirely absent.	3 / 5
Trigger Term Quality	Relevant domain keywords (migrations, seeders, tests, CI) appear, but there are no natural conversational trigger phrases, synonyms, or file extensions a user would actually say. It fits the 'some relevant keywords but missing common variations' anchor, not 4 which expects fuller keyword coverage.	3 / 5
Distinctiveness Conflict Risk	The niche (execution ordering of migrations/seeders/tests in CI) is mostly distinct with only minor overlap risk against general CI or testing skills. Not 5 because it could still overlap with broader CI-pipeline skills, and not 3 because it is more specific than 'works with CI pipelines'.	4 / 5
	Total	13 / 20 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/ci-schema-invariant-gate/SKILL.md
Commit: 2199c1e

Reviewed: 14 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.