CtrlK
BlogDocsLog inGet started
Tessl Logo

laravel-tdd

Laravel testing strategies with PHPUnit, Pest, model factories, HTTP tests, Sanctum authentication testing, mocking, and coverage.

66

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

80%

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

A thorough, executable Laravel TDD reference with excellent actionability and token efficiency, held back by a lightly sketched workflow loop and a monolithic single-file structure that underuses progressive disclosure.

Suggestions

Turn the Red-Green-Refactor cycle into an explicit numbered sequence with a validation checkpoint (e.g. 'run vendor/bin/phpunit; if red, fix the smallest thing; only refactor when green').

Add a coverage-threshold feedback loop (run --min=80, fix gaps, re-run) so the batch coverage workflow has an explicit validate-fix-retry step.

Move the larger reference blocks (factory catalog, Sanctum auth tests, fakes catalogue) into references/ files and link to them from a concise overview to improve progressive disclosure.

DimensionReasoningScore

Conciseness

The body is code-forward and lean: it assumes Laravel competence and never explains basic framework concepts, so each section's tokens earn their place.

3 / 3

Actionability

Provides complete, executable PHP/Pest snippets plus concrete coverage commands ('vendor/bin/phpunit --coverage-html coverage --coverage-clover clover.xml') that are copy-paste ready.

3 / 3

Workflow Clarity

The Red-Green-Refactor cycle is named but its steps are inline comments rather than a sequenced procedure, and batch/destructive workflows (e.g. coverage gating, migrations) lack explicit validation checkpoints or error-recovery feedback loops.

2 / 3

Progressive Disclosure

All content lives in a single ~400-line SKILL.md with no bundle files or external references; sections are well organized, but a skill this large would benefit from splitting detailed references (e.g. factories, Sanctum, fakes) into separate files.

2 / 3

Total

10

/

12

Passed

Description

82%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description with good trigger-term coverage and a clear niche, weakened only by the absence of an explicit 'Use when...' clause that would make activation conditions unambiguous.

Suggestions

Append an explicit activation clause, e.g. 'Use when writing or debugging Laravel tests, setting up PHPUnit/Pest, or testing Sanctum-authenticated APIs.'

Consider adding a couple of natural-language trigger variants users might say (e.g. 'Laravel feature tests', 'test factories', 'Pest tests') to broaden match phrasing.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'PHPUnit, Pest, model factories, HTTP tests, Sanctum authentication testing, mocking, and coverage' — rather than vague language.

3 / 3

Completeness

Clearly states what the skill does, but lacks any explicit 'Use when...' trigger clause, so the 'when' guidance is only implied by the listed capabilities.

2 / 3

Trigger Term Quality

Natural terms a Laravel developer would say are well covered: 'Laravel testing', 'PHPUnit', 'Pest', 'model factories', 'HTTP tests', 'Sanctum', 'mocking', 'coverage'.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear Laravel-testing niche and is distinguishable from sibling skills (laravel-patterns, laravel-security, tdd-workflow) named in the body.

3 / 3

Total

11

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (676 lines); consider splitting into references/ and linking

Warning

metadata_version

'metadata.version' is missing

Warning

Total

14

/

16

Passed

Repository
affaan-m/ECC
Reviewed

Table of Contents

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.